chore: baseline V8.10.0-dev.1 with v8_workflows type-mapping fix and trade-pro spec

- SiteForge Enterprise V8.10.0-dev.1 upstream source (210 tests) - Fix: v8_workflows._mapped_input now reads both 类型/分类 columns so WXR imports keep post/product types instead of collapsing to page - Docs: trade-pro theme port spec (R3) and implementation plan Co-Authored-By: Claude Code <noreply@anthropic.com>
2026-10-22 16:49:25 +08:00
commit 8cea7dee20
354 changed files with 20736 additions and 0 deletions
@@ -0,0 +1,126 @@
+"""Declarative mapping from arbitrary tabular source data to SiteForge content.
+Never eval mappings, no AI hallucinated fields, preview shows all errors.
+"""
+import json,re
+from . import db
+from .core import route_path,slug_of,save_entry
+
+ALIASES={
+ 'title':('title','name','product_name','model_name','名称','标题','产品名称','车型','车型名称','商品名称'),
+ 'route':('route','url','path','permalink','链接','路径','旧站链接','原网址'),
+ 'summary':('summary','description','excerpt','简介','摘要','产品简介'),
+ 'body':('body','content','html','正文','内容','详细介绍'),
+ 'cover':('cover','image','thumbnail','featured_image','图片','封面','主图'),
+ 'brand':('brand','manufacturer','品牌','厂商'),
+ 'category':('category','分类','类目'),
+ 'seo_title':('seo_title','meta_title','SEO标题','seo标题'),
+ 'seo_description':('seo_description','meta_description','SEO描述','seo描述'),
+ 'canonical':('canonical','规范网址'),
+ 'model':('model','model_name','车型型号','型号','规格型号'),
+ 'energy':('energy','energy_type','fuel_type','动力形式','能源类型','燃料类型'),
+ 'range':('range','battery_range','纯电续航','续航','续航里程'),
+ 'year':('year','model_year','年款','年份'),
+ 'sku':('sku','product_sku','产品编号','货号'),
+ 'gallery':('gallery','images','image_gallery','产品图片','图库','详情图片'),
+ 'price':('price','msrp','售价','价格'),
+ 'specs':('specs','attributes','parameters','技术参数','产品参数'),
+
+}
+SYSTEM_FIELDS={'title','route','summary','body','cover','seo_title','seo_description','canonical'}
+
+
+def setup():
+    with db.connect() as c:
+        c.executescript('''CREATE TABLE IF NOT EXISTS mapping_profiles (
+          id TEXT PRIMARY KEY,site_id TEXT NOT NULL REFERENCES sites(id) ON DELETE CASCADE,
+          name TEXT NOT NULL,content_type TEXT NOT NULL, rules_json TEXT NOT NULL,
+          created_at TEXT NOT NULL,updated_at TEXT NOT NULL);
+          CREATE TABLE IF NOT EXISTS import_batches (
+          id TEXT PRIMARY KEY,site_id TEXT NOT NULL REFERENCES sites(id) ON DELETE CASCADE,
+          profile_id TEXT, source TEXT NOT NULL, result_json TEXT NOT NULL,
+          created_at TEXT NOT NULL);
+        ''')
+
+
+def suggest(columns):
+    clean=lambda x:re.sub(r'[\s\-_]+','',str(x).casefold())
+    src={clean(col):col for col in columns}
+    mapping={}
+    for target,aliases in ALIASES.items():
+        for alias in aliases:
+            if clean(alias) in src:
+                mapping[target]=src[clean(alias)];break
+    return mapping
+
+
+def validate_rules(rules,columns):
+    if not isinstance(rules,dict) or len(rules)>100:raise ValueError('字段映射规则不合法')
+    for dest,src in rules.items():
+        if not re.fullmatch(r'[\w\-]{1,60}',dest,re.UNICODE):raise ValueError('目标字段名称不合法')
+        if not isinstance(src,str) or src not in columns:raise ValueError(f'来源字段不存在: {src}')
+    if 'title' not in rules:raise ValueError('必须映射标题字段')
+
+
+def transform(rows,rules,kind='product',prefix=None):
+    if kind not in ('product','post','page','brand','vehicle','service','case','other'):raise ValueError('不支持的内容类型')
+    columns=set().union(*(r.keys() for r in rows)) if rows else set()
+    validate_rules(rules,columns)
+    seen=set();out=[];errors=[]
+    for index,row in enumerate(rows):
+        vals={}
+        for target,src in rules.items():
+            raw=row.get(src)
+            vals[target]=(json.dumps(raw,ensure_ascii=False) if isinstance(raw,(dict,list)) else str(raw if raw is not None else '')).strip()
+        title=vals.get('title','')
+        if not title:
+            errors.append({'row':index+1,'error':'标题为空'});continue
+        route=vals.get('route','')
+        if not route:
+            route=f'/{prefix or kind}/{slug_of(title)}/'
+        try:route=route_path(route)
+        except ValueError as exc:
+            errors.append({'row':index+1,'error':f'路径非法：{exc}'});continue
+        if route in seen:
+            errors.append({'row':index+1,'error':'导入文件内 URL 重复：'+route});continue
+        seen.add(route)
+        fields={k:v for k,v in vals.items() if k not in SYSTEM_FIELDS}
+        if fields.get('gallery'):
+            try:
+                values=json.loads(fields['gallery'])
+                if isinstance(values,list):fields['gallery']=[str(x.get('url','') if isinstance(x,dict) else x) for x in values if x]
+            except ValueError:
+                fields['gallery']=[x.strip() for x in fields['gallery'].split(';') if x.strip()][:40]
+        out.append({'type':kind,'title':title,'route':route,'summary':vals.get('summary',''),
+                    'body':vals.get('body',''),'cover':vals.get('cover',''),
+                    'seo_title':vals.get('seo_title',''),'seo_description':vals.get('seo_description',''),
+                    'canonical':vals.get('canonical',''),'meta':{'fields':fields}})
+    return out,errors
+
+
+def dry_run(site_id,rows,rules,kind='product',prefix=None):
+    if len(rows)>1000:raise ValueError('单批最多1000条内容')
+    items,errors=transform(rows,rules,kind,prefix)
+    existing={r['route'] for r in db.rows('SELECT route FROM entries WHERE site_id=?',(site_id,))}
+    collisions=[r['route'] for r in items if r['route'] in existing]
+    return {'input':len(rows),'mapped':len(items),'errors':errors,'conflicts':collisions,
+            'unmapped_columns':sorted(set().union(*(x.keys() for x in rows)) - set(rules.values())) if rows else [],
+            'sample':items[:10], 'items':items}
+
+
+def commit(site_id,rows,rules,kind='product',on_conflict='skip',prefix=None):
+    if on_conflict not in ('skip','replace'):raise ValueError('冲突策略只能为 skip 或 replace')
+    report=dry_run(site_id,rows,rules,kind,prefix)
+    created=0;updated=0;skipped=0;errors=list(report['errors'])
+    for idx,item in enumerate(report['items'],1):
+        try:
+            existing=db.one('SELECT id FROM entries WHERE site_id=? AND route=?',(site_id,item['route']))
+            if existing and on_conflict=='skip':skipped+=1;continue
+            save_entry(site_id,item,existing_id=existing['id'] if existing else None,source='mapped-import')
+            if existing:updated+=1
+            else:created+=1
+        except Exception as exc:
+            errors.append({'row':idx,'error':str(exc)[:250]})
+    summary={'created':created,'updated':updated,'skipped':skipped,'errors':errors,'mapped':report['mapped']}
+    from .core import uid
+    db.insert('INSERT INTO import_batches VALUES (?,?,?,?,?,?)',(uid(),site_id,'',f'content-map:{kind}',json.dumps(summary,ensure_ascii=False),db.now()))
+    return summary