时间识别的优化

ccs_base/wizard/batch_get_pod_info_wizard.py

@@ -132,7 +132,7 @@ class BatchGetPodInfoWizard(models.TransientModel):
                     self._merge_pdf_files(successful_files)
 
                 # 如果所有文件都成功了（没有失败的文件），自动勾选"是否同步成功涂抹的提单"
-                if len(successful_files) == len(processed_files) and not failed_files:
+                if len(successful_files) == len(processed_files) and not failed_files and not self.show_error_message:
                     self.sync_successful_processed = True
                     _logger.info(f"所有提单都处理成功，自动勾选同步选项")
                 else:
@@ -312,6 +312,7 @@ class BatchGetPodInfoWizard(models.TransientModel):
             # 若需补推节点，则需判断提取时间-写入节点（不取写入第一个节点）的前序间隔时间是否大于小包当前节点的操作时间。
             # 若不满足以上条件，则不执行生成和自动推送节点，并在小包上新增推送备注（新增该字段）回写备注信息：获取尾程POD，自动推送节点失败，有风险产生倒挂。请手动操作205-10-20 10:20:20（获取时间）
             valid_files = self._validate_node_push_conditions(successful_processed_files)
+            # raise ValidationError('通知')
             if valid_files:
                 self.get_date_sync_match_node(valid_files)
             else:
@@ -1895,6 +1896,7 @@ class BatchGetPodInfoWizard(models.TransientModel):
         extracted_times = []
 
         try:
+            logging.info('ocr_texts:%s' % ocr_texts)
             # 如果没有提供OCR文本，则调用OCR识别
             if ocr_texts is None:
                 pdf_binary = base64.b64decode(file_data)
@@ -1926,6 +1928,8 @@ class BatchGetPodInfoWizard(models.TransientModel):
                     r'DATETIMEOFRELEASE(\d)(\d)(\d{2})(\d{2})-([A-Z]{3})-(\d{4})',
                     # OCR可能将:识别为多个空格，如"DATETIMEOFRELEASE        163420-SEP-2025"
                     r'DATETIMEOFRELEASE\s+(\d)(\d)(\d{2})(\d{2})-([A-Z]{3})-(\d{4})',
+                    # OCR可能将:识别为多个空格，如"DATETIMEOFRELEASE        1623420-SEP-2025"把:识别成了2
+                    r'DATETIMEOFRELEASE\s+(\d)(\d)2(\d{2})(\d{2})-([A-Z]{3})-(\d{4})',
                 ]
 
                 for idx, pattern in enumerate(release_time_patterns):
@@ -1973,7 +1977,6 @@ class BatchGetPodInfoWizard(models.TransientModel):
                                              'JUL': 7, 'AUG': 8, 'SEP': 9, 'OCT': 10, 'NOV': 11, 'DEC': 12}[
                                     month.upper()]
                                 time_obj = datetime(int(year), month_num, int(day), int(hour), int(minute))
-                                match_str = f"{hour}:{minute} {day.zfill(2)}-{month_normalized}-{year}"
                             elif group_count == 6:
                                 # OCR将:识别为数字的情况: ('1', '6', '34', '20', 'SEP', '2025')
                                 hour_tens = release_time_match.group(1)
@@ -1992,7 +1995,6 @@ class BatchGetPodInfoWizard(models.TransientModel):
                                              'JUL': 7, 'AUG': 8, 'SEP': 9, 'OCT': 10, 'NOV': 11, 'DEC': 12}[
                                     month.upper()]
                                 time_obj = datetime(int(year), month_num, int(day), int(hour), int(minute))
-                                match_str = f"{hour}:{minute} {day.zfill(2)}-{month}-{year}"
                             else:
                                 _logger.warning(f"意外的分组数量: {group_count}, 分组: {release_time_match.groups()}")
                                 continue