You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
49 lines
2.0 KiB
49 lines
2.0 KiB
2 days ago
|
# -*- coding: utf-8 -*-
|
||
|
|
"""诊断 A4 文档响应表“说明”列的真实质量，不只看表头。"""
|
||
|
|
import re, json
|
||
|
|
from pathlib import Path
|
||
|
|
|
||
|
|
DOCS = Path(r"D:\code\crm-api-docs\A4 客户管理")
|
||
|
|
PLACEHOLDER_DESCS = {
|
||
|
|
"无业务返回数据",
|
||
|
|
"标量业务返回值",
|
||
|
|
"二进制文件流；成功时不使用 JSON 信封",
|
||
|
|
"返回对象；源码未找到可静态展开的字段",
|
||
|
|
"分页内容，元素结构如下",
|
||
|
|
"总条数", "每页条数", "当前页", "总页数", "是否为空",
|
||
|
|
}
|
||
|
|
stats = {"total_rows": 0, "empty": 0, "field_name_copy": 0, "placeholder": 0, "meaningful": 0}
|
||
|
|
per_file = []
|
||
|
|
for f in sorted(DOCS.rglob("*.bru")):
|
||
|
|
if f.name == "folder.bru":
|
||
|
|
continue
|
||
|
|
text = f.read_text(encoding="utf-8-sig")
|
||
|
|
m = re.search(r'## 响应 data 结构\s*\n(.*?)(?=\n ## |\n\}\s*$|\Z)', text, re.S)
|
||
|
|
if not m:
|
||
|
|
continue
|
||
|
|
table = m.group(1)
|
||
|
|
file_bad = 0
|
||
|
|
file_total = 0
|
||
|
|
for line in table.splitlines():
|
||
|
|
rm = re.match(r'\s*\|\s*([^|]+?)\s*\|\s*([^|]+?)\s*\|\s*([^|]*?)\s*\|$', line)
|
||
|
|
if not rm:
|
||
|
|
continue
|
||
|
|
field, ftype, desc = (g.strip() for g in rm.groups())
|
||
|
|
if field in ("字段",) or set(field) <= {"-"}:
|
||
|
|
continue
|
||
|
|
stats["total_rows"] += 1
|
||
|
|
file_total += 1
|
||
|
|
if desc == "":
|
||
|
|
stats["empty"] += 1; file_bad += 1
|
||
|
|
elif desc == field or desc == field.replace("content[].", "").replace("[].", ""):
|
||
|
|
stats["field_name_copy"] += 1; file_bad += 1
|
||
|
|
elif desc in PLACEHOLDER_DESCS:
|
||
|
|
stats["placeholder"] += 1; file_bad += 1
|
||
|
|
else:
|
||
|
|
stats["meaningful"] += 1
|
||
|
|
if file_total and file_bad == file_total:
|
||
|
|
per_file.append(("全行糊弄", f.relative_to(DOCS).as_posix()))
|
||
|
|
elif file_bad and file_bad >= file_total * 0.5:
|
||
|
|
per_file.append(("半数糊弄", f.relative_to(DOCS).as_posix()))
|
||
|
|
print(json.dumps({"stats": stats, "bad_files_count": len(per_file), "bad_files_sample": per_file[:20]}, ensure_ascii=False, indent=2))
|