feat(供应商管理): 新增规则引擎与词典配置支持

refactor(处理器): 重构通用供应商处理器以支持规则引擎
docs: 更新README与文档说明供应商管理功能
build: 更新打包脚本注入版本信息
test: 添加规则引擎单元测试

app/core/processors/supplier_processors/generic_supplier_processor.py

@@ -11,6 +11,7 @@ from pathlib import Path
 
 from ..base import BaseProcessor
 from ...utils.log_utils import get_logger
+from ...handlers.rule_engine import apply_rules
 
 logger = get_logger(__name__)
 
@@ -118,10 +119,17 @@ class GenericSupplierProcessor(BaseProcessor):
                 self.logger.error("数据清洗失败")
                 self.log_processing_end(input_file, success=False)
                 return None
+            try:
+                rules = self.supplier_config.get('rules', [])
+                dictionary = self.supplier_config.get('dictionary')
+                standardized_df = apply_rules(cleaned_df, rules, dictionary)
+            except Exception as e:
+                self.logger.warning(f"规则执行失败: {e}")
+                standardized_df = cleaned_df
             
             # 步骤4: 计算处理
             self.logger.info("步骤4/4: 计算处理...")
-            calculated_df = self._apply_calculations(cleaned_df)
+            calculated_df = self._apply_calculations(standardized_df)
             if calculated_df is None:
                 self.logger.error("计算处理失败")
                 self.log_processing_end(input_file, success=False)
@@ -205,15 +213,26 @@ class GenericSupplierProcessor(BaseProcessor):
             数据DataFrame或None
         """
         try:
-            df = self._read_excel_safely(file_path)
-            
-            if df.empty:
+            specified = self.supplier_config.get('header_row')
+            if specified is not None:
+                try:
+                    df = self._read_excel_safely(file_path, header=int(specified))
+                except Exception:
+                    df = self._read_excel_safely(file_path)
+            else:
+                df0 = self._read_excel_safely(file_path, header=None)
+                if df0 is None:
+                    return None
+                header_row = self._find_header_row(df0)
+                if header_row is not None:
+                    df = self._read_excel_safely(file_path, header=header_row)
+                else:
+                    df = self._read_excel_safely(file_path)
+            if df is None or df.empty:
                 self.logger.warning("数据文件为空")
                 return None
-            
             self.logger.info(f"成功读取数据，形状: {df.shape}")
             return df
-            
         except Exception as e:
             self.logger.error(f"读取数据失败: {e}")
             return None
@@ -235,6 +254,40 @@ class GenericSupplierProcessor(BaseProcessor):
         except Exception as e:
             self.logger.error(f"读取Excel失败: {file_path} - {e}")
             raise
+
+    def _find_header_row(self, df: pd.DataFrame) -> Optional[int]:
+        try:
+            header_keywords = [
+                '条码','条形码','商品编码','商品名称','名称','数量','单位','单价','规格',
+                '金额','小计','总计','合计','合计金额'
+            ]
+            scores = []
+            rows_to_check = min(30, len(df))
+            for r in range(rows_to_check):
+                row = df.iloc[r]
+                score = 0
+                for cell in row:
+                    if isinstance(cell, str):
+                        s = cell.strip().lower()
+                        for kw in header_keywords:
+                            if kw.lower() in s:
+                                score += 5
+                non_empty = row.count()
+                if non_empty / max(1, len(row)) > 0.5:
+                    score += 2
+                str_count = sum(1 for c in row if isinstance(c, str))
+                if str_count / max(1, len(row)) > 0.5:
+                    score += 3
+                scores.append((r, score))
+            scores.sort(key=lambda x: x[1], reverse=True)
+            if scores and scores[0][1] >= 5:
+                return scores[0][0]
+            for r in range(len(df)):
+                if df.iloc[r].notna().sum() > 3:
+                    return r
+            return None
+        except Exception:
+            return None
     
     def _apply_column_mapping(self, df: pd.DataFrame) -> Optional[pd.DataFrame]:
         """应用列映射