fix: 凭证号提取改进

- 双管线OCR：原图提取头部(凭证号/日期) + 预处理提取表格
- 正则兼容更宽松格式(空格、破折号)
- 修复预处理破坏小字导致65/66号凭证漏识别的问题

core/parser.py

@@ -43,13 +43,20 @@ class K3VoucherParser:
                     except:
                         pass
             
-            elif '凭证号' in text:
-                m = re.search(r'[\u8bb0\u51ed\u8bc1]-\s*(\d+)', text)
+            elif '凭证' in text:
+                # 兼容各种格式：记-45、记 - 45、记-45（1/3）、45(1/3)
+                m = re.search(r'[记凭证]\s*[-—]\s*(\d+)', text)
                 if m:
                     result['voucher_no'] = int(m.group(1))
-                m2 = re.search(r'(\d+)（\d+/\d+）', text)  # 多页凭证：123（1/3）
-                if m2:
-                    result['voucher_no'] = int(m2.group(1))
+                if not result['voucher_no']:
+                    m2 = re.search(r'(?:记\s*)?[-—]?\s*(\d+)\s*[（(]\d+[/]\d+[）)]', text)
+                    if m2:
+                        result['voucher_no'] = int(m2.group(1))
+                # 兜底：直接找"凭证号"后面的数字
+                if not result['voucher_no']:
+                    m3 = re.search(r'凭证号\s*[：:]\s*记?\s*[-—]?\s*(\d+)', text)
+                    if m3:
+                        result['voucher_no'] = int(m3.group(1))
                     
             elif '附件数' in text:
                 m = re.search(r'附件数[：:](\d+)', text)

kocr.py

@@ -159,7 +159,19 @@ def process_single(image_path, config, output_path=None, verbose=False, mark_don
         print(f"   📊 图像分析: 类型={quality.photo_type}, "
               f"亮度={quality.brightness}, 模糊={quality.blur_score}")
     
-    # 2. 自动调参 + 预处理
+    # 2. 双管线：先对原图OCR提取头部（凭证号、日期对小字更敏感）
+    ocr_config = config.get('ocr', {})
+    
+    # 2a. 原图OCR → 提取头部信息（预处理会破坏小字）
+    if verbose:
+        print(f"   📋 原图OCR提取头部...")
+    lines_raw = run_ocr(img, ocr_config, quality.photo_type, verbose=verbose)
+    parser_raw = K3VoucherParser(lines_raw)
+    header_info = parser_raw.parse()
+    if verbose and header_info['voucher_no']:
+        print(f"   ✅ 原图识别到凭证号: 记-{header_info['voucher_no']}")
+    
+    # 2b. 自动调参 + 预处理 → 提取表格内容
     preproc_config = config.get('preprocessing', {})
     preprocessor = VoucherPreprocessor.from_config(preproc_config, quality.photo_type)
     processed = preprocessor.process(img)
@@ -169,17 +181,26 @@ def process_single(image_path, config, output_path=None, verbose=False, mark_don
               f"去阴影={preprocessor.remove_shadow}, "
               f"锐化={preprocessor.sharpen}")
     
-    # 3. OCR 识别（自动选参数）
-    ocr_config = config.get('ocr', {})
     lines = run_ocr(processed, ocr_config, quality.photo_type, verbose=verbose)
     
     if verbose:
-        print(f"   OCR: {len(lines)} 行文字")
+        print(f"   OCR: {len(lines)} 行文字（预处理后）")
     
-    # 4. 凭证解析
+    # 3. 解析（合并原图头部 + 预处理表格）
     parser = K3VoucherParser(lines)
     voucher = parser.parse()
     
+    # 如果原图识别到了凭证号但预处理后没识别到，补回来
+    if voucher['voucher_no'] is None and header_info['voucher_no'] is not None:
+        voucher['voucher_no'] = header_info['voucher_no']
+        if verbose:
+            print(f"   ✅ 使用原图凭证号: 记-{header_info['voucher_no']}")
+    # 同理补日期
+    if voucher['date'] is None and header_info['date'] is not None:
+        voucher['date'] = header_info['date']
+        if verbose:
+            print(f"   ✅ 使用原图日期: {header_info['date'].strftime('%Y-%m-%d')}")
+    
     if verbose:
         print(f"   公司: {voucher['company']}")
         print(f"   日期: {voucher['date'].strftime('%Y-%m-%d') if voucher['date'] else '未识别'}")