"""Commercial-delivery readiness report, separate from technical/SEO pass.

It does NOT certify a site's business claims, copyright clearance, legal compliance,
WCAG conformance or any real-world server/SEO outcome. It reports missing items.
"""
from __future__ import annotations
from pathlib import Path
from bs4 import BeautifulSoup
import json

REQUIRED=('index.html','about/index.html','contact/index.html','products/index.html','brands/index.html','news/index.html','cases/index.html','404.html')
DEMO_MARKERS=('example.com','example.test','这是可替换的','虚构示例','演示内容','演示产品','此为 SiteForge','请在后台配置')

def inspect(dist:Path)->dict:
    dist=Path(dist)
    blockers=[];warnings=[];metrics={}
    for f in REQUIRED:
        if not (dist/f).is_file():blockers.append({'code':'page_missing','path':f,'message':'缺少标准栏目页面'})
    homepage=dist/'index.html'
    if homepage.is_file():
        soup=BeautifulSoup(homepage.read_text(encoding='utf-8'),'html.parser')
        logo=soup.select_one('header img.pro-brand-logo')
        if not logo:warnings.append({'code':'brand_logo','message':'尚未替换成企业正式 Logo'})
        if not soup.find('meta',attrs={'name':'description'}):blockers.append({'code':'seo_description','message':'首页缺少 SEO 描述标签'})
        if len(soup.select('h1'))!=1:blockers.append({'code':'home_h1','message':'首页 H1 数量不符合预期'})
    else:soup=None
    # Do not build a 5,000-page HTML string and parse every detail document with
    # BeautifulSoup just to count two static CSS classes. Streaming makes the
    # commercial audit linear in file size, rather than consuming excessive CPU.
    metrics['html_pages']=0
    metrics['artwork_fallbacks']=0
    metrics['pages_with_body']=0
    found_demo=False
    for path in dist.rglob('*.html'):
        html=path.read_text(encoding='utf-8',errors='replace')
        metrics['html_pages']+=1
        metrics['artwork_fallbacks']+=html.count('class="pro-art ')
        metrics['pages_with_body']+=int('pro-rich' in html)
        if not found_demo and any(marker in html for marker in DEMO_MARKERS):found_demo=True
    if metrics['artwork_fallbacks']:
        warnings.append({'code':'placeholder_images','count':metrics['artwork_fallbacks'],'message':'部分页面仍使用示意图，正式发布前请替换为真实且有使用权的图片'})
    if found_demo:
        warnings.append({'code':'demo_content','message':'检测到演示或默认文案，正式发布前请逐页核对'})
    if not (dist/'assets'/'commercial.css').is_file():
        warnings.append({'code':'commercial_style','message':'当前构建未包含商业视觉样式（可能是历史主题版本）'})
    contact=dist/'contact/index.html'
    if contact.is_file():
        con=BeautifulSoup(contact.read_text(encoding='utf-8'),'html.parser')
        if not con.select_one('form.pro-inquiry') and not con.select_one('a[href^="mailto:"]'):
            blockers.append({'code':'contact_method','message':'联系页既无已配置表单，也无有效电子邮箱入口'})
        elif not con.select_one('form.pro-inquiry'):
            warnings.append({'code':'form_not_configured','message':'尚未配置 HTTPS 询盘接收服务；目前仅提供邮件联系'})
    if not any((dist/p).is_file() for p in ('privacy/index.html','privacy-policy/index.html')):
        warnings.append({'code':'legal_pages','message':'请根据目标国家/地区法律审查是否需要隐私政策与 Cookie 声明'})
    return {'ready_for_review':not blockers,'commercially_certified':False,'blockers':blockers,'warnings':warnings,
            'metrics':metrics,'note':'仅为本地结构化交付清单，不等于合法合规、内容准确、无障碍、性能或生产上线认证'}