# -*- coding: utf-8 -*-
"""票 05 全量盘点：.bru 响应示例形态分布 + specimens 覆盖对账。

输出：
  A) 全仓形态统计（占位/真值/双节/错误码节）
  B) 占位残留清单（需处理）
  C) 占位且有真值块（仅需删占位）vs 占位且无真值块（需写数据）
  D) specimens 合并 key 清单 + 对账钥匙映射缺口
"""
from __future__ import annotations

import io
import json
import re
import sys
from pathlib import Path

sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding='utf-8')

A4 = Path('D:/code/crm-api-docs/A4 客户管理')
SP = Path('.scratch/customer-integration-ready')

files = [p for p in A4.rglob('*.bru') if p.name != 'folder.bru']
print(f'[A] 全仓 .bru = {len(files)}（排除 folder.bru）')

# ---------- 形态扫描 ----------
ph_files, tv_files, dual_sec, no_sec = [], [], [], []
key_re = re.compile(r'^\s*`\s*(GET|POST)\s+(/[^\s`]+)\s*`', re.M)
file_key = {}
for p in sorted(files):
    txt = p.read_text(encoding='utf-8')
    rel = str(p.relative_to(A4))
    has_ph = '非真实返回' in txt
    has_tv = 'E2E 实测真值' in txt
    n_sec = len(re.findall(r'^\s*## 响应示例', txt, re.M))
    m = key_re.search(txt)
    if m:
        file_key[rel] = f'{m.group(1)} {m.group(2)}'
    if has_ph:
        ph_files.append(rel)
    if has_tv:
        tv_files.append(rel)
    if n_sec >= 2:
        dual_sec.append(rel)
    if n_sec == 0:
        no_sec.append(rel)

print(f'[A] 含占位标记 = {len(ph_files)}；含真值标记 = {len(tv_files)}；双响应示例节 = {len(dual_sec)}；无响应示例节 = {len(no_sec)}')

# ---------- 分组 ----------
ph_set, tv_set = set(ph_files), set(tv_files)
only_ph = sorted(ph_set - tv_set)      # 有占位、无真值 → 必须写回数据
both = sorted(ph_set & tv_set)         # 占位+真值并存 → 删占位块即可
print(f'[C] 占位+真值并存（删占位即可）= {len(both)}')
for r in both:
    print(f'    {r}')
print(f'[C] 占位且无真值（需写数据）= {len(only_ph)}')
for r in only_ph:
    print(f'    {r}')

# ---------- specimens 合并 ----------
merged = {}
for name in ['specimens-core-r3.json', 'specimens-heavy-r3.json', 'specimens-incr-r3.json',
             'specimens-graph-r3.json', 'specimens-doc-truth.json']:
    data = json.loads((SP / name).read_text(encoding='utf-8'))
    for k, v in data.items():
        merged.setdefault(k, {'src': [], 'v': v})['src'].append(name)
    print(f'[D] {name}: {len(data)} 端点')
print(f'[D] 合并后唯一端点 = {len(merged)}')

# ---------- 对账钥匙 × specimens 覆盖 ----------
covered = missing = 0
missing_list = []
for rel, k in sorted(file_key.items()):
    if k in merged:
        covered += 1
    else:
        missing += 1
        missing_list.append(f'{rel}  ←  {k}')
print(f'[D] 文件端点在 specimens 中 = {covered}，缺 = {missing}')
for r in missing_list:
    print(f'    {r}')

Path('.scratch/customer-integration-ready/audit_t05_out.txt').write_text(
    '\n'.join(['PH:' + r for r in ph_files] + ['TV:' + r for r in tv_files]
              + ['DUAL:' + r for r in dual_sec] + ['NOSEC:' + r for r in no_sec]
              + ['MISS:' + r for r in missing_list]),
    encoding='utf-8')
print('[done] 明细 → audit_t05_out.txt')