from pathlib import Path
import re
from datetime import datetime

SRC = Path('/tmp/adblock_import')
OUT = Path('rules/adblock_domains.txt')
files = [
    SRC / 'easylistchina.txt',
    SRC / 'gitee_adblock/adblock.txt',
    SRC / 'gitee_adblock/adblock_lite.txt',
    SRC / 'gitee_adblock/adblock_plus.txt',
    SRC / 'gitee_adblock/adblock_privacy.txt',
    SRC / 'github_adblock/ADBLOCK_RULE_COLLECTION_DOMAIN.txt',
    SRC / 'github_adblock/ADBLOCK_RULE_COLLECTION_DOMAIN_Lite.txt',
]
# 宽松域名提取，后面再过滤明显非域名/静态资源片段
DOMAIN_RE = re.compile(r'(?i)(?:\|\|)?\b([a-z0-9](?:[a-z0-9-]{0,61}[a-z0-9])?(?:\.[a-z0-9](?:[a-z0-9-]{0,61}[a-z0-9])?)+)\b')
BAD_SUFFIX = {'.js', '.css', '.jpg', '.jpeg', '.png', '.gif', '.webp', '.svg', '.ico', '.mp4', '.m3u8', '.json', '.xml', '.php', '.html'}
COMMON_ALLOW = {
    'github.com','gitee.com','google.com','microsoft.com','apple.com','qq.com','weixin.qq.com','telegram.org',
    't.me','youtube.com','bilibili.com','baidu.com','cloudflare.com','jquery.com','vuejs.org','npmjs.com'
}

def valid_domain(d: str) -> bool:
    d = d.lower().strip('.-_^*/')
    if not d or d in COMMON_ALLOW:
        return False
    if any(d.endswith(s) for s in BAD_SUFFIX):
        return False
    parts = d.split('.')
    if len(parts) < 2 or any(not p or len(p) > 63 for p in parts):
        return False
    tld = parts[-1]
    if len(tld) < 2 or not re.fullmatch(r'[a-z][a-z0-9-]{1,23}', tld):
        return False
    # 排除纯数字/IP
    if all(p.isdigit() for p in parts):
        return False
    return True

domains = set()
source_counts = {}
for path in files:
    if not path.exists():
        continue
    count_before = len(domains)
    with path.open('r', encoding='utf-8', errors='ignore') as f:
        for raw in f:
            line = raw.strip()
            if not line or line.startswith(('!', '#', '[')) or line.startswith('@@'):
                continue
            # 跳过元素隐藏/CSS 规则
            if '##' in line or '#?#' in line or '#@#' in line:
                continue
            # 去掉 options，减少误提取
            line = line.split('$', 1)[0]
            for m in DOMAIN_RE.finditer(line):
                d = m.group(1).lower().strip('.-_^*/')
                if valid_domain(d):
                    domains.add(d)
    source_counts[str(path.relative_to(SRC))] = len(domains) - count_before

OUT.parent.mkdir(parents=True, exist_ok=True)
existing_header = ''
if OUT.exists():
    backup = OUT.with_suffix(f'.txt.bak-{datetime.now().strftime("%Y%m%d%H%M%S")}')
    OUT.replace(backup)
lines = [
    '# Adblock 域名过滤库（自动导入）',
    '# 来源：gitee.com/uniartisan2018/adblock_list、github.com/REIJI007/Adblock-Rule-Collection、EasyList China',
    '# 用途：仅当聊天消息中出现 URL/域名时匹配，不作为普通关键词扫描，避免误杀与性能问题。',
    f'# 更新时间：{datetime.now().isoformat(timespec="seconds")}',
    f'# 有效域名：{len(domains)}',
]
for k, v in source_counts.items():
    lines.append(f'# source {k}: +{v}')
lines.append('')
lines.extend(sorted(domains))
OUT.write_text('\n'.join(lines) + '\n', encoding='utf-8')
print({'domains': len(domains), 'sources': source_counts, 'output': str(OUT)})