chore: import SiteForge Factory V5 source (baseline)

导入 SiteForge Factory V5 基线源码： - FastAPI + SQLite + Docker Compose（Web + Worker）架构 - 四套商业主题 × 14 页面模板（1.1.0，含历史版本快照） - 四种建站模式骨架 + 迁移审计 + 发布门禁 - 52 项 pytest 测试 - 补全计划主文档 docs/superpowers/plans/ Co-Authored-By: Claude Code <noreply@anthropic.com>
2026-10-22 10:42:19 +08:00
commit 3c57c167f2
264 changed files with 11682 additions and 0 deletions
@@ -0,0 +1,56 @@
+"""Offline static-build quality gate. No external network requests or speculative SEO scores."""
+from pathlib import Path
+from urllib.parse import urlsplit,unquote
+from bs4 import BeautifulSoup
+from . import db
+
+def report(site_id, build_id):
+    root=(db.DATA/'builds'/site_id/build_id/'dist').resolve()
+    if not root.is_dir():raise FileNotFoundError('构建版本不存在')
+    files=list(root.rglob('*.html'))
+    site=db.one('SELECT domain FROM sites WHERE id=?',(site_id,)) or {}
+    hostname=urlsplit(site.get('domain') or '').hostname
+    issues=[];seen_titles={};seen_descriptions={}
+    for p in files:
+        rel=p.relative_to(root).as_posix()
+        soup=BeautifulSoup(p.read_text(encoding='utf-8',errors='replace'),'html.parser')
+        title=(soup.title.get_text(' ',strip=True) if soup.title else '')
+        h1=soup.find_all('h1')
+        if not title:issues.append({'file':rel,'type':'missing_title','severity':'error'})
+        if len(h1)!=1:issues.append({'file':rel,'type':'h1_count','severity':'warning','count':len(h1)})
+        if title and title in seen_titles and p.name!='404.html':issues.append({'file':rel,'type':'duplicate_title','severity':'warning','other':seen_titles[title]})
+        seen_titles[title]=rel
+        description=soup.find('meta',attrs={'name':'description'})
+        desc=description.get('content','').strip() if description else ''
+        if not desc:issues.append({'file':rel,'type':'missing_description','severity':'warning'})
+        if desc and desc in seen_descriptions:issues.append({'file':rel,'type':'duplicate_description','severity':'warning','other':seen_descriptions[desc]})
+        seen_descriptions[desc]=rel
+        for img in soup.find_all('img'):
+            if not img.get('alt'):issues.append({'file':rel,'type':'missing_image_alt','severity':'warning','src':img.get('src','')[:180]})
+        for node in soup.find_all(['a','img','script','link']):
+            attr='href' if node.name in ('a','link') else 'src'
+            target=node.get(attr)
+            if not target:continue
+            parsed=urlsplit(target)
+            if parsed.scheme in ('http','https'):
+                if parsed.hostname!=hostname:continue
+                path=parsed.path
+            elif parsed.scheme or target.startswith('//'):continue
+            elif target.startswith('#'):continue
+            else:path=parsed.path
+            if not path:continue
+            if node.name=='link' and node.get('rel') and 'canonical' in node.get('rel'):continue
+            from_root=path.startswith('/')
+            # HTML uses <base href="/">, which makes relative paths site-root relative.
+            base=soup.find('base',href=True)
+            if base and base.get('href')=='/':from_root=True
+            raw=unquote(path.lstrip('/'))
+            if not from_root:raw=(p.relative_to(root).parent/raw).as_posix()
+            test=(root/raw)
+            if target.endswith('/') or not Path(raw).suffix:test=test/'index.html'
+            if not test.resolve().is_relative_to(root) or not test.is_file():
+                if node.name=='link' and ('alternate' in (node.get('rel') or [])):continue
+                issues.append({'file':rel,'type':'broken_internal_reference','severity':'error','target':target[:220]})
+    return {'files':len(files),'errors':sum(i['severity']=='error' for i in issues),
+            'warnings':sum(i['severity']=='warning' for i in issues),
+            'passed':not any(i['severity']=='error' for i in issues),'issues':issues[:500]}