浅念
601451f22b
Overlay ~150 upstream items onto our V8.12 base, preserving trade-pro
theme, registry tests, and design docs. Re-applied our patch set
(discovery/env_for/blocks.css/type-mapping/theme_color/frontend entries,
test_theme_pro_v3 mods) — all anchors survived upstream evolution.
New platform enhancement (fixes upgrade-introduced regression):
multilingual.site_locale now honors settings_json.locale, plus
PUT /api/i18n/sites/{id}/locale — standalone English sites get
<html lang='en'> under the V8.15 locale-rewrite pipeline.
compose: adopt V8.21.3 (image 8.21.3-dev.1, /api/ready probes, MySQL/S3
env) with project name pinned to siteforge-v8-10 (data volumes).
Tests: 356 passed / 11 failed — all 11 confirmed pre-existing in
pristine V8.21.3 on this host (10 upstream Windows env + our build test
now green after locale fix). Patch registry updated in plan doc.
Co-Authored-By: Claude Code <noreply@anthropic.com>
101 lines
4.6 KiB
Python
101 lines
4.6 KiB
Python
#!/usr/bin/env python3
|
||
"""Convert an authorized WXR or Sitemap XML file into a URL-preservation baseline.
|
||
|
||
Offline only. Uses defusedxml; hard input limit 32 MiB. Does not download sites.
|
||
"""
|
||
import argparse
|
||
import sys
|
||
from pathlib import Path
|
||
from urllib.parse import urlsplit, unquote
|
||
|
||
try:
|
||
from defusedxml import ElementTree as DET
|
||
except ImportError:
|
||
print('需要先安装 defusedxml：python -m pip install defusedxml', file=sys.stderr)
|
||
raise SystemExit(3)
|
||
|
||
WP_NS = '{http://wordpress.org/export/1.2/}'
|
||
SITEMAP_NS = '{http://www.sitemaps.org/schemas/sitemap/0.9}'
|
||
MAX_XML = 32 * 1024 * 1024
|
||
|
||
|
||
def route_from_url(raw, allowed_hosts):
|
||
p = urlsplit(raw.strip())
|
||
if p.scheme not in ('http', 'https') or not p.hostname:
|
||
return None
|
||
if p.hostname.lower().rstrip('.') not in allowed_hosts:
|
||
return None
|
||
# Encoded dots/slashes would introduce ambiguous paths, so reject them.
|
||
path = unquote(p.path or '/')
|
||
if '\\' in path or '\x00' in path or '//' in path or any(seg in ('.', '..') for seg in path.split('/')):
|
||
return None
|
||
# Query-based legacy WordPress URLs require explicit redirect mapping.
|
||
if p.query or p.fragment:
|
||
return None
|
||
return path
|
||
|
||
|
||
def extract(root, hosts, include_unpublished=False):
|
||
routes = set()
|
||
ignored = []
|
||
if root.tag.endswith('urlset'):
|
||
items = root.findall(f'.//{SITEMAP_NS}url') or root.findall('.//url')
|
||
for item in items:
|
||
loc = item.findtext(f'{SITEMAP_NS}loc') or item.findtext('loc') or ''
|
||
route = route_from_url(loc, hosts)
|
||
if route: routes.add(route)
|
||
elif loc: ignored.append('sitemap: 无法映射的 loc')
|
||
elif root.tag == 'rss' or root.tag.endswith('rss'):
|
||
items = root.findall('./channel/item')
|
||
for item in items:
|
||
status = (item.findtext(f'{WP_NS}status') or '').strip()
|
||
kind = (item.findtext(f'{WP_NS}post_type') or '').strip()
|
||
# WXR can contain attachments and revision records: only published content pages.
|
||
if kind in ('attachment', 'revision', 'nav_menu_item'):
|
||
continue
|
||
if not include_unpublished and status != 'publish':
|
||
continue
|
||
link = item.findtext('link') or ''
|
||
route = route_from_url(link, hosts)
|
||
if route: routes.add(route)
|
||
elif link: ignored.append('WXR: 无法映射的 link')
|
||
else:
|
||
raise ValueError('仅支持 WXR RSS 或 sitemap urlset XML（不支持 sitemapindex 的递归远端访问）')
|
||
return sorted(routes), ignored
|
||
|
||
|
||
def main(argv=None):
|
||
ap = argparse.ArgumentParser(description='从授权的 WordPress WXR 或 Sitemap 导出原始 URL 基线，离线运行')
|
||
ap.add_argument('xml', type=Path)
|
||
ap.add_argument('--host', required=True, help='旧站域名，不带 scheme 或路径，例如 example.com')
|
||
ap.add_argument('--allow-host', action='append', default=[], help='手动允许其他同站主机名（例如 www.example.com）')
|
||
ap.add_argument('--include-unpublished', action='store_true', help='WXR 包含草稿（默认仅 publish）')
|
||
ap.add_argument('--output', type=Path, required=True)
|
||
args = ap.parse_args(argv)
|
||
allowed = set()
|
||
for host in [args.host] + args.allow_host:
|
||
if not host or any(c in host for c in '/:@?#') or any(c.isspace() for c in host):
|
||
ap.error('--host/--allow-host 只接受域名，不接受 URL、端口或路径')
|
||
allowed.add(host.lower().rstrip('.'))
|
||
try:
|
||
size = args.xml.stat().st_size
|
||
if size > MAX_XML: raise ValueError('XML 超过 32 MiB 上限，请分割或使用离线批处理')
|
||
if not size: raise ValueError('XML 文件为空')
|
||
root = DET.parse(args.xml).getroot()
|
||
routes, ignored = extract(root, allowed, args.include_unpublished)
|
||
except (OSError, ValueError, DET.ParseError, DET.EntitiesForbidden, DET.DTDForbidden) as e:
|
||
print('导入失败：' + str(e), file=sys.stderr)
|
||
return 2
|
||
if not routes:
|
||
print('没有找到匹配已发布内容的 URL，请检查旧站域名和 XML 格式', file=sys.stderr)
|
||
return 2
|
||
args.output.parent.mkdir(parents=True, exist_ok=True)
|
||
args.output.write_text('# WordPress 旧站原始 URL 路径基线（不可修改路径语义）\n' + '\n'.join(routes) + '\n', encoding='utf-8')
|
||
print(f'导出 {len(routes)} 条；无法映射 {len(ignored)} 条。保存：{args.output}')
|
||
if ignored:
|
||
print('警告：有 URL 包含查询参数或使用了非指定域名；需人工建立 301 路径映射。', file=sys.stderr)
|
||
return 0
|
||
|
||
if __name__ == '__main__':
|
||
raise SystemExit(main())
|