# -*- coding: utf-8 -*-
"""对 24 个残留旧引用，尝试在当前新结构里找近似等价文件。"""
import os, re, 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 全部文件相对路径
allfiles = []
for root, _, fs in os.walk(ROOT):
    for f in fs:
        rel = os.path.relpath(os.path.join(root, f), ROOT).replace(os.sep, '/')
        allfiles.append(rel)

pat = re.compile(r'(?:%s)/[^\s\)\]]+' % '|'.join(OLD_DIRS))
residual = {}  # basename -> oldref (去尾反引号)
for root, _, fs in os.walk(ROOT):
    for f in fs:
        if not f.endswith('.md'):
            continue
        with open(os.path.join(root, f), encoding='utf-8') as fh:
            for line in fh:
                for m in pat.finditer(line):
                    oldref = m.group(0).rstrip('`')
                    bn = oldref.split('/')[-1]
                    residual.setdefault(bn, oldref)

def candidates(bn):
    # 关键词：去掉版本/日期/扩展名，取核心词
    core = re.sub(r'[-_ ]?(v?\d+\.\d+.*|2026\d\d\d\d|\d{8}|备份|archived).*$', '', bn)
    core = core.replace('.md', '').replace('.html', '')
    # 取连续中文/英文关键词片段
    keys = [k for k in re.split(r'[-_ ]', core) if len(k) >= 2]
    hits = []
    for af in allfiles:
        afb = af.split('/')[-1]
        if bn == afb:
            continue
        if any(k.lower() in afb.lower() for k in keys if len(k) >= 3):
            hits.append(af)
    return hits[:5]

print("残留 basename 数:", len(residual))
for bn, oldref in sorted(residual.items()):
    if bn in ('', '`'):
        continue
    c = candidates(bn)
    print("\n● %s" % bn)
    print("  旧: %s" % oldref)
    print("  候选(新结构): " + ("; ".join(c) if c else "*** 无近似文件（确属死链） ***"))