"""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]}