fix: 智能导入——匹配不上的财务报表科目自动创建KPI定义

- 清理科目前缀(一、/减：/加：)后多级匹配
- ⑤仍未匹配→自动创建KPI(PL_001/CF_001/BS_001)
- 避免205条全部跳过的场景

backend/app/api/data.py

@@ -190,10 +190,16 @@ async def import_excel_smart(file: UploadFile = File(...), db: Session = Depends
     for code in known_codes:
         clean = re.sub(r'[\s\-_（）()]', '', code).lower()
         alias_map[clean] = code
+    # 中文名映射（"营业收入"→F_REVENUE）
+    name_map: dict[str, str] = {}
+    for code, kpi_obj in kpis.items():
+        name_map[kpi_obj.kpi_name] = code
 
-    # 8. 遍历导入
+    # 8. 遍历导入（匹配不上的自动创建KPI）
+    stype_prefix = {"PL": "PL_", "CF": "CF_", "BS": "BS_"}.get(stype or "", "EXT_")
     batch = hashlib.md5(str(datetime.now().timestamp()).encode()).hexdigest()[:12]
     imported = 0
+    created_kpis = 0
     skipped_rows = []
 
     for idx, row in df.iterrows():
@@ -208,24 +214,50 @@ async def import_excel_smart(file: UploadFile = File(...), db: Session = Depends
             skipped_rows.append(f"第{idx+2}行: 无法确定期间")
             continue
 
-        # 智能匹配KPI编码
+        # 清理科目名（去掉"一、""减：""加："等前缀）
+        clean_name = re.sub(r'^[一二三四五六七八九十、\s\+]+', '', raw_kpi)
+        clean_name = re.sub(r'^[减加]?[：:]\s*', '', clean_name).strip()
+        if not clean_name:
+            clean_name = raw_kpi
+
+        # 匹配KPI
         kpi_code = None
+
+        # ① 精确编码匹配（极少情况）
         if raw_kpi in known_codes:
             kpi_code = raw_kpi
-        else:
-            # 别名匹配
+        # ② 别名匹配（去符号小写）
+        if not kpi_code:
             clean_key = re.sub(r'[\s\-_（）()]', '', raw_kpi).lower()
             kpi_code = alias_map.get(clean_key)
-            # 模糊匹配（中文科目名→KPI编码）
-            if not kpi_code:
-                for code, kpi_obj in kpis.items():
-                    if raw_kpi in kpi_obj.kpi_name or kpi_obj.kpi_name in raw_kpi:
-                        kpi_code = code
-                        break
-
+        # ③ 中文名精确匹配
         if not kpi_code:
-            skipped_rows.append(f"第{idx+2}行: 「{raw_kpi}」未匹配到KPI")
-            continue
+            kpi_code = name_map.get(clean_name)
+        # ④ 中文名模糊匹配
+        if not kpi_code:
+            for code, kpi_obj in kpis.items():
+                if clean_name in kpi_obj.kpi_name or kpi_obj.kpi_name in clean_name:
+                    kpi_code = code
+                    break
+
+        # ⑤ 仍未匹配 → 自动创建KPI
+        if not kpi_code:
+            new_code = f"{stype_prefix}{len(kpis) + created_kpis + 1:03d}"
+            new_kpi = KPIDefinition(
+                kpi_code=new_code,
+                kpi_name=clean_name,
+                dimension="finance",
+                category="financial_report",
+                data_source_type="excel",
+                status="active",
+            )
+            db.add(new_kpi)
+            db.flush()
+            kpis[new_code] = new_kpi
+            known_codes.add(new_code)
+            name_map[clean_name] = new_code
+            kpi_code = new_code
+            created_kpis += 1
 
         try:
             val = float(raw_val)
@@ -248,6 +280,8 @@ async def import_excel_smart(file: UploadFile = File(...), db: Session = Depends
     # 9. 返回汇总
     stype_label = {"PL": "利润表", "CF": "现金流量表", "BS": "资产负债表"}.get(stype or "", "数据表")
     msg = f"✅ {stype_label}识别成功，导入{imported}条"
+    if created_kpis:
+        msg += f"，自动创建{created_kpis}个新KPI"
     if skipped_rows:
         msg += f"，{len(skipped_rows)}条跳过:\n" + "\n".join(skipped_rows[:8])
         if len(skipped_rows) > 8: