133 lines
5.1 KiB
Python
133 lines
5.1 KiB
Python
|
"""校验 `docs/05-接口文档.md` §19「接口总目录」的端点编号唯一性（只读，不连数据库）。
|
|||
|
|
|
|||
|
|
## 为什么需要它
|
|||
|
|
|
|||
|
|
`tools/check_authoritative_docs.py` 只校验 `docs/` 的**文件名编号**与权威性声明，
|
|||
|
|
**不校验 §19 里每个端点的编号**。2026-09-12 出过一次真实事故：两条线各自新增端点时
|
|||
|
|
都占用了 `A034`/`A035`，合并后 §19 同时存在两个 `A034` 与两个 `A035`，
|
|||
|
|
而文档守卫照样通过 —— 编号复用比"编号不够"更麻烦，而且**静默遗留**。
|
|||
|
|
|
|||
|
|
## 口径（含覆盖自检）
|
|||
|
|
|
|||
|
|
- 扫描范围：§19 章节内的**所有**表格行首列；
|
|||
|
|
- **不枚举前缀白名单**，前缀从数据里归纳后打印出来。同一件事上还踩过一次
|
|||
|
|
"扫描正则写成 `[AMKCS]` 就漏掉 `O`/`R` 两段，把 62 个端点报成 55 个" ——
|
|||
|
|
一旦被漏掉的号段将来被复用，脚本仍会报"重复 0"。所以这里把
|
|||
|
|
**"扫到哪几个号段、各多少条、共计多少"** 一并输出，让覆盖范围本身可核对；
|
|||
|
|
- 首列不是 `XXX###` 形状的行会被显式列出来（而不是静默跳过）；
|
|||
|
|
- 只读：不修改任何文件。
|
|||
|
|
|
|||
|
|
用法：
|
|||
|
|
|
|||
|
|
python tools/check_docs_endpoint_ids.py
|
|||
|
|
|
|||
|
|
退出码：0 = 无重复；1 = 有重复或文档结构异常。
|
|||
|
|
"""
|
|||
|
|
|
|||
|
|
from __future__ import annotations
|
|||
|
|
|
|||
|
|
import re
|
|||
|
|
from collections import Counter
|
|||
|
|
from pathlib import Path
|
|||
|
|
|
|||
|
|
PROJECT_ROOT = Path(__file__).resolve().parents[1]
|
|||
|
|
INTERFACE_DOC = PROJECT_ROOT / "docs" / "05-接口文档.md"
|
|||
|
|
|
|||
|
|
#: §19 的起止标题（`: \\s*` 之间允许一个空格，避免依赖标题里的具体文字）。
|
|||
|
|
SECTION_START = re.compile(r"^##\s*19\.")
|
|||
|
|
SECTION_END = re.compile(r"^##\s*20\.")
|
|||
|
|
|
|||
|
|
#: 表格行：只取首列，容忍单元格两侧空白。
|
|||
|
|
TABLE_ROW = re.compile(r"^\|(.+)\|\s*$")
|
|||
|
|
#: Markdown 分隔行：| --- | :---: | 之类。
|
|||
|
|
SEPARATOR = re.compile(r"^[\s\-:|]+$")
|
|||
|
|
#: 端点编号形状：1~4 个大写字母 + 3~4 位数字（A034 / M003 / R001）。
|
|||
|
|
ENDPOINT_ID = re.compile(r"^[A-Z]{1,4}\d{3,4}$")
|
|||
|
|
|
|||
|
|
|
|||
|
|
class DocumentStructureError(RuntimeError):
|
|||
|
|
"""`docs/05` 的 §19 结构不符合预期，无法安全校验。"""
|
|||
|
|
|
|||
|
|
|
|||
|
|
def read_section(path: Path = INTERFACE_DOC) -> list[str]:
|
|||
|
|
"""返回 §19 的正文行（不含起止标题）。"""
|
|||
|
|
if not path.exists():
|
|||
|
|
raise DocumentStructureError(f"缺少接口权威文档：{path}")
|
|||
|
|
|
|||
|
|
lines = path.read_text(encoding="utf-8").splitlines()
|
|||
|
|
start = next((i for i, line in enumerate(lines) if SECTION_START.match(line)), None)
|
|||
|
|
if start is None:
|
|||
|
|
raise DocumentStructureError("接口文档里找不到 §19 章节标题")
|
|||
|
|
end = next(
|
|||
|
|
(i for i in range(start + 1, len(lines)) if SECTION_END.match(lines[i])),
|
|||
|
|
len(lines),
|
|||
|
|
)
|
|||
|
|
return lines[start + 1 : end]
|
|||
|
|
|
|||
|
|
|
|||
|
|
def collect_rows(lines: list[str]) -> tuple[list[str], list[str]]:
|
|||
|
|
"""返回 `(首列编号列表, 无法识别的首列列表)`。
|
|||
|
|
|
|||
|
|
表头行、分隔行、非表格行都会被跳过；非空但形状不对的首列会被归类为
|
|||
|
|
"无法识别"，以便显式暴露而不是静默漏扫。
|
|||
|
|
"""
|
|||
|
|
ids: list[str] = []
|
|||
|
|
unrecognized: list[str] = []
|
|||
|
|
for line in lines:
|
|||
|
|
match = TABLE_ROW.match(line.strip())
|
|||
|
|
if match is None:
|
|||
|
|
continue
|
|||
|
|
first_cell = match.group(1).split("|", 1)[0].strip()
|
|||
|
|
if not first_cell or SEPARATOR.match(first_cell):
|
|||
|
|
continue
|
|||
|
|
if first_cell == "编号": # 表头
|
|||
|
|
continue
|
|||
|
|
if ENDPOINT_ID.match(first_cell):
|
|||
|
|
ids.append(first_cell)
|
|||
|
|
else:
|
|||
|
|
unrecognized.append(first_cell)
|
|||
|
|
return ids, unrecognized
|
|||
|
|
|
|||
|
|
|
|||
|
|
def collect_findings(path: Path = INTERFACE_DOC) -> list[str]:
|
|||
|
|
"""返回问题列表；空列表表示一致。"""
|
|||
|
|
lines = read_section(path)
|
|||
|
|
ids, unrecognized = collect_rows(lines)
|
|||
|
|
|
|||
|
|
problems: list[str] = []
|
|||
|
|
if not ids:
|
|||
|
|
problems.append("§19 没有扫描到任何端点编号，文档结构可能已变化，请人工确认")
|
|||
|
|
|
|||
|
|
counter = Counter(ids)
|
|||
|
|
for endpoint_id in sorted(code for code, count in counter.items() if count > 1):
|
|||
|
|
problems.append(f"端点编号 {endpoint_id} 重复 {counter[endpoint_id]} 次")
|
|||
|
|
|
|||
|
|
for cell in sorted(set(unrecognized)):
|
|||
|
|
problems.append(f"§19 首列无法识别为端点编号：{cell!r}")
|
|||
|
|
|
|||
|
|
return problems
|
|||
|
|
|
|||
|
|
|
|||
|
|
def describe_coverage(path: Path = INTERFACE_DOC) -> str:
|
|||
|
|
"""返回覆盖范围报告 —— 让"扫到了什么"可见，而不是只报"没问题"。"""
|
|||
|
|
ids, _ = collect_rows(read_section(path))
|
|||
|
|
prefixes = Counter(re.match(r"[A-Z]+", code).group() for code in ids)
|
|||
|
|
detail = "、".join(f"{prefix}×{count}" for prefix, count in sorted(prefixes.items()))
|
|||
|
|
return f"§19 覆盖：{len(ids)} 个端点编号 / {len(prefixes)} 个号段（{detail}）"
|
|||
|
|
|
|||
|
|
|
|||
|
|
def main() -> int:
|
|||
|
|
problems = collect_findings()
|
|||
|
|
print(describe_coverage())
|
|||
|
|
if problems:
|
|||
|
|
for problem in problems:
|
|||
|
|
print(f" ✗ {problem}")
|
|||
|
|
print(f"docs/05 §19 端点编号校验失败：{len(problems)} 处问题")
|
|||
|
|
return 1
|
|||
|
|
print("docs/05 §19 端点编号无重复")
|
|||
|
|
return 0
|
|||
|
|
|
|||
|
|
|
|||
|
|
if __name__ == "__main__":
|
|||
|
|
raise SystemExit(main())
|