feat: 添加转堆作业解析功能

- 新增 _parse_relocation() 方法解析转堆作业
- 新增 _parse_log_entry() 方法复用解析逻辑
- 转堆作业使用 '转堆作业' 作为船名标识

src/confluence/log_parser.py

@@ -241,6 +241,12 @@ class HandoverLogParser:
     def _parse_ships(self, content: str, date: str, shift: str, logs: List[ShipLog]) -> None:
         """解析船次"""
         try:
+            # 首先解析转堆作业（无船名）
+            relocation_content = self._parse_relocation(content, date, shift)
+            if relocation_content:
+                logs.append(relocation_content)
+            
+            # 然后解析实船作业（按 "实船作业：" 分割）
             parts = content.split('实船作业：')
             
             for part in parts:
@@ -259,71 +265,163 @@ class HandoverLogParser:
                 # 移除二次靠泊等标注
                 ship_name = re.sub(r'（二次靠泊）|（再次靠泊）|\(二次靠泊\)|\(再次靠泊\)', '', ship_name).strip()
 
-                vehicles_match = re.search(r'上场车辆数：(\d+)', cleaned)
-                teu_eff_match = re.search(
-                    r'作业量/效率：(\d+)TEU[，,\s]*', cleaned
-                )
-                
-                # 解析TEU
-                teu = None
-                if teu_eff_match:
-                    try:
-                        teu = int(teu_eff_match.group(1))
-                    except ValueError as e:
-                        logger.warning(f"TEU解析失败: {teu_eff_match.group(1)}, 错误: {e}")
-                
-                # 解析车辆数
-                vehicles = None
-                if vehicles_match:
-                    try:
-                        vehicles = int(vehicles_match.group(1))
-                    except ValueError as e:
-                        logger.warning(f"车辆数解析失败: {vehicles_match.group(1)}, 错误: {e}")
-                
-                # 解析尺寸箱量
-                twenty_feet = None
-                forty_feet = None
-                
-                # 查找作业量/效率后面的括号内的尺寸信息
-                # 匹配模式：TEU数字后跟括号，括号内包含尺寸信息
-                size_pattern = re.search(r'TEU[，,\s]*（([^）]+)）', cleaned)
-                if not size_pattern:
-                    # 也尝试匹配没有逗号的情况
-                    size_pattern = re.search(r'TEU\s*（([^）]+)）', cleaned)
-                
-                if size_pattern:
-                    size_text = size_pattern.group(1)
-                    # 匹配20尺*数字
-                    twenty_match = re.search(r'20尺\*(\d+)', size_text)
-                    if twenty_match:
-                        try:
-                            twenty_feet = int(twenty_match.group(1))
-                        except ValueError as e:
-                            logger.warning(f"20尺箱量解析失败: {twenty_match.group(1)}, 错误: {e}")
-                    
-                    # 匹配40尺*数字
-                    forty_match = re.search(r'40尺\*(\d+)', size_text)
-                    if forty_match:
-                        try:
-                            forty_feet = int(forty_match.group(1))
-                        except ValueError as e:
-                            logger.warning(f"40尺箱量解析失败: {forty_match.group(1)}, 错误: {e}")
-                
-                log = ShipLog(
-                    date=date,
-                    shift=shift,
-                    ship_name=ship_name,
-                    teu=teu,
-                    efficiency=None,  # 目前日志中没有效率数据
-                    vehicles=vehicles,
-                    twenty_feet=twenty_feet,
-                    forty_feet=forty_feet
-                )
-                logs.append(log)
+                # 解析车辆数、TEU、尺寸箱量
+                self._parse_log_entry(cleaned, date, shift, ship_name, logs)
                 
         except Exception as e:
             logger.warning(f"解析船次失败: {date} {shift}, 错误: {e}")
     
+    def _parse_relocation(self, content: str, date: str, shift: str) -> Optional[ShipLog]:
+        """
+        解析转堆作业（无船名的作业类型）
+        
+        参数:
+            content: 班次内容
+            date: 日期
+            shift: 班次
+        
+        返回:
+            ShipLog 对象，如果未找到转堆作业则返回 None
+        """
+        try:
+            # 检查是否包含转堆作业
+            if '转堆作业：' not in content:
+                return None
+            
+            # 提取转堆作业部分（从 "转堆作业：" 到下一个空行或下一个实船作业）
+            relocation_start = content.find('转堆作业：') + len('转堆作业：')
+            
+            # 查找下一个 "实船作业：" 作为结束标记
+            next_ship = content.find('实船作业：', relocation_start)
+            if next_ship == -1:
+                relocation_content = content[relocation_start:]
+            else:
+                relocation_content = content[relocation_start:next_ship]
+            
+            cleaned = relocation_content.replace('\xa0', ' ').strip()
+            
+            # 解析车辆数、TEU、尺寸箱量
+            vehicles_match = re.search(r'上场车辆数：(\d+)', cleaned)
+            teu_eff_match = re.search(r'作业量/效率：(\d+)TEU', cleaned)
+            
+            teu = None
+            if teu_eff_match:
+                try:
+                    teu = int(teu_eff_match.group(1))
+                except ValueError as e:
+                    logger.warning(f"转堆作业 TEU 解析失败: {teu_eff_match.group(1)}, 错误: {e}")
+            
+            vehicles = None
+            if vehicles_match:
+                try:
+                    vehicles = int(vehicles_match.group(1))
+                except ValueError as e:
+                    logger.warning(f"转堆作业车辆数解析失败: {vehicles_match.group(1)}, 错误: {e}")
+            
+            # 解析尺寸箱量
+            twenty_feet = None
+            forty_feet = None
+            size_pattern = re.search(r'TEU[，,\s]*（([^）]+)）', cleaned)
+            if not size_pattern:
+                size_pattern = re.search(r'TEU\s*（([^）]+)）', cleaned)
+            
+            if size_pattern:
+                size_text = size_pattern.group(1)
+                twenty_match = re.search(r'20尺\*(\d+)', size_text)
+                if twenty_match:
+                    try:
+                        twenty_feet = int(twenty_match.group(1))
+                    except ValueError as e:
+                        logger.warning(f"转堆作业 20尺箱量解析失败: {twenty_match.group(1)}, 错误: {e}")
+                
+                forty_match = re.search(r'40尺\*(\d+)', size_text)
+                if forty_match:
+                    try:
+                        forty_feet = int(forty_match.group(1))
+                    except ValueError as e:
+                        logger.warning(f"转堆作业 40尺箱量解析失败: {forty_match.group(1)}, 错误: {e}")
+            
+            # 使用 "转堆作业" 作为船名标识
+            log = ShipLog(
+                date=date,
+                shift=shift,
+                ship_name='转堆作业',
+                teu=teu,
+                efficiency=None,
+                vehicles=vehicles,
+                twenty_feet=twenty_feet,
+                forty_feet=forty_feet
+            )
+            
+            logger.info(f"解析转堆作业: {date} {shift} {log.teu}TEU")
+            return log
+            
+        except Exception as e:
+            logger.warning(f"解析转堆作业失败: {date} {shift}, 错误: {e}")
+            return None
+    
+    def _parse_log_entry(self, cleaned: str, date: str, shift: str, ship_name: str, logs: List[ShipLog]) -> None:
+        """解析单条日志记录（车辆数、TEU、尺寸箱量）"""
+        try:
+            vehicles_match = re.search(r'上场车辆数：(\d+)', cleaned)
+            teu_eff_match = re.search(r'作业量/效率：(\d+)TEU[，,\s]*', cleaned)
+            
+            # 解析TEU
+            teu = None
+            if teu_eff_match:
+                try:
+                    teu = int(teu_eff_match.group(1))
+                except ValueError as e:
+                    logger.warning(f"TEU解析失败: {teu_eff_match.group(1)}, 错误: {e}")
+            
+            # 解析车辆数
+            vehicles = None
+            if vehicles_match:
+                try:
+                    vehicles = int(vehicles_match.group(1))
+                except ValueError as e:
+                    logger.warning(f"车辆数解析失败: {vehicles_match.group(1)}, 错误: {e}")
+            
+            # 解析尺寸箱量
+            twenty_feet = None
+            forty_feet = None
+            
+            # 查找作业量/效率后面的括号内的尺寸信息
+            size_pattern = re.search(r'TEU[，,\s]*（([^）]+)）', cleaned)
+            if not size_pattern:
+                size_pattern = re.search(r'TEU\s*（([^）]+)）', cleaned)
+            
+            if size_pattern:
+                size_text = size_pattern.group(1)
+                twenty_match = re.search(r'20尺\*(\d+)', size_text)
+                if twenty_match:
+                    try:
+                        twenty_feet = int(twenty_match.group(1))
+                    except ValueError as e:
+                        logger.warning(f"20尺箱量解析失败: {twenty_match.group(1)}, 错误: {e}")
+                
+                forty_match = re.search(r'40尺\*(\d+)', size_text)
+                if forty_match:
+                    try:
+                        forty_feet = int(forty_match.group(1))
+                    except ValueError as e:
+                        logger.warning(f"40尺箱量解析失败: {forty_match.group(1)}, 错误: {e}")
+            
+            log = ShipLog(
+                date=date,
+                shift=shift,
+                ship_name=ship_name,
+                teu=teu,
+                efficiency=None,
+                vehicles=vehicles,
+                twenty_feet=twenty_feet,
+                forty_feet=forty_feet
+            )
+            logs.append(log)
+            
+        except Exception as e:
+            logger.warning(f"解析日志记录失败: {date} {shift} {ship_name}, 错误: {e}")
+    
     def parse_from_file(self, filepath: str) -> List[ShipLog]:
         """
         从文件解析日志