# -*- coding: utf-8 -*-
"""第二遍：对残留的旧路径引用，按 basename 在当前 docs 反查真实落点。"""
import os, re, json, collections

ROOT = "docs"
OLD_DIRS = ["02-产品需求", "03-技术架构", "04-原型设计",
            "09-部署运维", "10-项目管理", "01-产品设计", "06-测试质量"]

# 当前 docs 所有文件：basename -> 完整相对路径列表
basemap = collections.defaultdict(list)
for root, _, fs in os.walk(ROOT):
    for f in fs:
        full = os.path.normpath(os.path.join(root, f))
        rel = os.path.relpath(full, ROOT).replace(os.sep, '/')
        basemap[f].append(rel)

# 扫描残留引用
pat = re.compile(r'(?:%s)/[^\s\)\]]+' % '|'.join(OLD_DIRS))
refs = collections.defaultdict(set)  # basename -> set of old refs
for root, _, fs in os.walk(ROOT):
    for f in fs:
        if not f.endswith('.md'):
            continue
        fp = os.path.join(root, f)
        with open(fp, encoding='utf-8') as fh:
            for line in fh:
                for m in pat.finditer(line):
                    oldref = m.group(0)
                    bn = oldref.split('/')[-1]
                    refs[bn].add(oldref)

print("残留引用涉及的不同 basename 数:", len(refs))
for bn, olds in sorted(refs.items()):
    locs = basemap.get(bn, [])
    status = "FOUND@" + "; ".join(locs) if locs else "*** NOT FOUND (死链?) ***"
    print("\n%s" % bn)
    print("  旧引用:", "; ".join(sorted(olds)))
    print("  现状:", status)