"""CMS adapter framework: bounded public-site detection and WP REST import.

Private/paid/SSO content is intentionally not accessed by this adapter. Other
platforms should provide a compatible adapter for their authorised APIs.
"""
from dataclasses import dataclass
from urllib.parse import urljoin,urlparse
from bs4 import BeautifulSoup
import httpx
from .core import ensure_public_url, route_path, save_entry
from . import db, safe_http

USER_AGENT='SiteForge/1.0 (+authorized-migration)'

@dataclass(frozen=True)
class SiteAnalysis:
    url:str
    platform:str
    title:str
    rest_api:str|None
    hints:list[str]

def _get(client,url):
    # TCP is pinned to the public IP returned by the security validation,
    # while HTTPS still validates against the original hostname.
    response=safe_http.fetch(url,max_bytes=4_000_000,timeout=13,redirects=0)
    response.raise_for_status()
    return response

def analyze(url):
    ensure_public_url(url)
    with httpx.Client(timeout=httpx.Timeout(13,connect=5),trust_env=False,headers={'User-Agent':USER_AGENT}) as client:
        r=_get(client,url)
        soup=BeautifulSoup(r.text,'html.parser')
        generator=soup.find('meta',attrs={'name':'generator'})
        gen=(generator.get('content','') if generator else '').lower()
        rest=soup.find('link',rel='https://api.w.org/')
        api_url=rest.get('href') if rest else None
        platform='WordPress' if 'wordpress' in gen or api_url or 'wp-content/' in r.text[:200000] else ('Drupal' if 'drupal' in gen else 'Joomla' if 'joomla' in gen else 'Unknown / Custom')
        hints=[]
        if soup.find('meta',attrs={'name':'robots'}):hints.append('检测到 robots meta')
        if soup.find('link',rel='canonical'):hints.append('检测到 Canonical')
        if soup.find('script',attrs={'type':'application/ld+json'}):hints.append('检测到结构化数据')
        if not api_url and platform=='WordPress':api_url=urljoin(url,'/wp-json/')
        return SiteAnalysis(url,platform,soup.title.get_text(' ',strip=True)[:200] if soup.title else '',api_url,hints).__dict__

def import_wordpress_rest(site_id,origin,max_items=150,on_conflict='skip'):
    """Import public published posts/pages from a WP REST API, preserving URL paths.

    Special Elementor/ACF/Yoast fields require additional adapter support.
    """
    if max_items<1 or max_items>1000:raise ValueError('允许导入 1-1000 条公开内容')
    if on_conflict not in ('skip','update'):raise ValueError('无效的冲突策略')
    root=origin.rstrip('/')+'/'
    ensure_public_url(root)
    result={'imported':0,'updated':0,'skipped':0,'errors':[]}
    with httpx.Client(timeout=httpx.Timeout(18,connect=6),trust_env=False,headers={'User-Agent':USER_AGENT}) as client:
        for kind in ('pages','posts'):
            batch_size=min(100,max_items)
            remaining=max_items-(result['imported']+result['updated']+result['skipped'])
            if remaining<=0:break
            page=1
            while remaining>0 and page<=20:
                api=urljoin(root,f'wp-json/wp/v2/{kind}?per_page={batch_size}&page={page}&_embed=1')
                try:
                    response=_get(client,api)
                    content=response.json()
                    if not isinstance(content,list):raise ValueError('API 返回内容不是数组')
                except safe_http.OutboundError as exc:
                    if str(exc) in ('Upstream HTTP 400','Upstream HTTP 404'):break
                    result['errors'].append({'source':kind,'page':page,'error':str(exc)[:150]});break
                except (ValueError,httpx.HTTPError) as exc:
                    result['errors'].append({'source':kind,'page':page,'error':str(exc)[:150]});break
                if not content:break
                for item in content:
                    try:
                        permalink=item.get('link') or ''
                        parsed=urlparse(permalink)
                        if not parsed.path:raise ValueError('未返回页面 URL')
                        if parsed.hostname!=urlparse(root).hostname:raise ValueError('返回了不同域名的链接，需手动映射')
                        route=route_path(parsed.path)
                        title=BeautifulSoup(item.get('title',{}).get('rendered',''),'html.parser').get_text(' ',strip=True)
                        excerpt=BeautifulSoup(item.get('excerpt',{}).get('rendered',''),'html.parser').get_text(' ',strip=True)
                        seo=item.get('yoast_head_json') or {}
                        data={'type':'post' if kind=='posts' else 'page', 'route':route,'title':title,
                              'summary':excerpt,'body':item.get('content',{}).get('rendered',''),
                              'seo_title':seo.get('title',''),'seo_description':seo.get('description',''),
                              'canonical':seo.get('canonical',''),'meta':{'wp_id':item.get('id'),'wp_slug':item.get('slug'),'wp_modified':item.get('modified')}}
                        previous=db.one('SELECT id FROM entries WHERE site_id=? AND route=?',(site_id,route))
                        if previous and on_conflict=='skip':result['skipped']+=1;continue
                        save_entry(site_id,data,existing_id=previous['id'] if previous else None,source='wp-rest')
                        result['updated' if previous else 'imported']+=1
                    except Exception as exc:
                        result['errors'].append({'item':item.get('id'),'error':str(exc)[:180]})
                    remaining-=1
                    if remaining<=0:break
                if len(content)<batch_size:break
                page+=1
    return result