"""Conservative WordPress WXR adapter helpers.

Never execute PHP, Elementor widgets, shortcodes or serialized metadata.
Only known text/image widgets are converted to sanitized HTML with warnings
for unknown proprietary elements; original metadata is always retained.
"""
import json, re
from html import escape
from .core import sanitize

WIDGETS={'heading','text-editor','image','button','icon-box','image-box','divider','spacer','video','html'}

def elementor_to_html(raw):
    if not isinstance(raw,str) or not raw.strip():return {'html':'','warnings':[],'widgets':0}
    try:data=json.loads(raw)
    except (ValueError,TypeError):return {'html':'','warnings':['Elementor JSON 解析失败：保留原始字段，需人工检查'],'widgets':0}
    if not isinstance(data,list):return {'html':'','warnings':['Elementor 数据根节点不是数组，需人工检查'],'widgets':0}
    parts=[];warnings=[];count=[0]
    def walk(elements,depth=0):
        if depth>12: warnings.append('Elementor 嵌套超过安全限制');return
        if not isinstance(elements,list):return
        for item in elements[:300]:
            if not isinstance(item,dict):continue
            typ=item.get('widgetType') or ''
            settings=item.get('settings') or {}
            if not isinstance(settings,dict):settings={}
            if typ:
                count[0]+=1
                if typ not in WIDGETS:
                    if len(warnings)<60:warnings.append('未转换的 Elementor 组件：'+str(typ)[:65])
                elif typ=='heading':
                    size=settings.get('header_size','h2');size=size if size in ('h1','h2','h3','h4','h5','h6') else 'h2'
                    parts.append(f'<{size}>{escape(str(settings.get("title") or ""))}</{size}>')
                elif typ=='text-editor':
                    parts.append(sanitize(str(settings.get('editor') or '')))
                elif typ in ('image','image-box'):
                    image=settings.get('image') or {}
                    url=image.get('url','') if isinstance(image,dict) else ''
                    if isinstance(url,str) and url.startswith(('https://','http://','/')):
                        parts.append(f'<p><img src="{escape(url,quote=True)}" alt="{escape(str(settings.get("title") or ""),quote=True)}"></p>')
                    if typ=='image-box' and settings.get('title_text'):
                        parts.append('<h3>'+escape(str(settings['title_text']))+'</h3>')
                    if typ=='image-box' and settings.get('description_text'):
                        parts.append('<p>'+escape(str(settings['description_text']))+'</p>')
                elif typ=='button':
                    href=settings.get('link') or {}
                    dest=href.get('url','') if isinstance(href,dict) else ''
                    if isinstance(dest,str) and dest.startswith(('https://','http://','/')):
                        parts.append(f'<a href="{escape(dest,quote=True)}">{escape(str(settings.get("text") or "更多信息"))}</a>')
                elif typ=='html':
                    parts.append(sanitize(str(settings.get('html') or '')))
                elif typ in ('video','divider','spacer','icon-box'):
                    if len(warnings)<60:warnings.append(f'{typ} 布局/嵌入需人工复核')
            walk(item.get('elements') or [],depth+1)
    walk(data)
    return {'html':'\n'.join(parts),'warnings':warnings,'widgets':count[0]}

def wp_taxonomy(item):
    data={}
    for node in item:
        if node.tag.rsplit('}',1)[-1]!='category':continue
        domain=node.get('domain','')
        name=(node.text or '').strip()
        if not name:continue
        if domain in ('category','product_cat','vehicle_cat'):data['category']=name
        elif domain in ('product_brand','brand','pa_brand'):data['brand']=name
        elif domain=='product_type':data['product_type']=name
        elif domain.startswith('pa_'):data[domain[3:]]=name
    return data

def wp_media_map(root):
    """WXR attachment ID -> original URL, useful for featured and gallery images."""
    media={}
    for item in root.findall('./channel/item'):
        typ=post_id=url=''
        for node in item:
            local=node.tag.rsplit('}',1)[-1]
            if local=='post_type':typ=node.text or ''
            elif local=='post_id':post_id=node.text or ''
            elif local=='attachment_url':url=node.text or ''
        if typ=='attachment' and post_id and url and url.startswith(('http://','https://')):
            media[post_id]=url
    return media