message_builder重构完成

src/chat/utils/chat_message_builder.py

@@ -1,8 +1,8 @@
-import time  # 导入 time 模块以获取当前时间
+import time
 import random
 import re
 
-from typing import List, Dict, Any, Tuple, Optional, Callable, Union
+from typing import List, Dict, Any, Tuple, Optional, Callable
 from rich.traceback import install
 
 from src.config.config import global_config
@@ -648,7 +648,7 @@ def build_readable_actions(actions: List[Dict[str, Any]]) -> str:
 
 
 async def build_readable_messages_with_list(
-    messages: List[Dict[str, Any]],
+    messages: List[DatabaseMessages],
     replace_bot_name: bool = True,
     timestamp_mode: str = "relative",
     truncate: bool = False,
@@ -658,7 +658,7 @@ async def build_readable_messages_with_list(
     允许通过参数控制格式化行为。
     """
     formatted_string, details_list, pic_id_mapping, _ = _build_readable_messages_internal(
-        messages, replace_bot_name, timestamp_mode, truncate
+        convert_DatabaseMessages_to_MessageAndActionModel(messages), replace_bot_name, timestamp_mode, truncate
     )
 
     if pic_mapping_info := build_pic_mapping_info(pic_id_mapping):
@@ -675,7 +675,7 @@ def build_readable_messages_with_id(
     truncate: bool = False,
     show_actions: bool = False,
     show_pic: bool = True,
-) -> Tuple[str, List[Dict[str, Any]]]:
+) -> Tuple[str, List[DatabaseMessages]]:
     """
     将消息列表转换为可读的文本格式，并返回原始(时间戳, 昵称, 内容)列表。
     允许通过参数控制格式化行为。
@@ -818,7 +818,6 @@ def build_readable_messages(
         formatted_before, _, pic_id_mapping, pic_counter = _build_readable_messages_internal(
             messages_before_mark,
             replace_bot_name,
-            merge_messages,
             timestamp_mode,
             truncate,
             pic_id_mapping,
@@ -829,7 +828,6 @@ def build_readable_messages(
         formatted_after, _, pic_id_mapping, _ = _build_readable_messages_internal(
             messages_after_mark,
             replace_bot_name,
-            merge_messages,
             timestamp_mode,
             False,
             pic_id_mapping,
@@ -998,3 +996,22 @@ async def get_person_id_list(messages: List[Dict[str, Any]]) -> List[str]:
             person_ids_set.add(person_id)
 
     return list(person_ids_set)  # 将集合转换为列表返回
+
+
+def convert_DatabaseMessages_to_MessageAndActionModel(message: List[DatabaseMessages]) -> List[MessageAndActionModel]:
+    """
+    将 DatabaseMessages 列表转换为 MessageAndActionModel 列表。
+    """
+    return [
+        MessageAndActionModel(
+            time=msg.time,
+            user_id=msg.user_info.user_id,
+            user_platform=msg.user_info.platform,
+            user_nickname=msg.user_info.user_nickname,
+            user_cardname=msg.user_info.user_cardname,
+            processed_plain_text=msg.processed_plain_text,
+            display_message=msg.display_message,
+            chat_info_platform=msg.chat_info.platform,
+        )
+        for msg in message
+    ]

src/chat/utils/utils.py

@@ -12,6 +12,7 @@ from typing import Optional, Tuple, Dict, List, Any
 
 from src.common.logger import get_logger
 from src.common.data_models.info_data_model import TargetPersonInfo
+from src.common.data_models.database_data_model import DatabaseMessages
 from src.common.message_repository import find_messages, count_messages
 from src.config.config import global_config, model_config
 from src.chat.message_receive.message import MessageRecv
@@ -152,10 +153,13 @@ def get_recent_group_speaker(chat_stream_id: str, sender, limit: int = 12) -> li
         if (
             (db_msg.user_info.platform, db_msg.user_info.user_id) != sender
             and db_msg.user_info.user_id != global_config.bot.qq_account
-            and (db_msg.user_info.platform, db_msg.user_info.user_id, db_msg.user_info.user_nickname) not in who_chat_in_group
+            and (db_msg.user_info.platform, db_msg.user_info.user_id, db_msg.user_info.user_nickname)
+            not in who_chat_in_group
             and len(who_chat_in_group) < 5
         ):  # 排除重复，排除消息发送者，排除bot，限制加载的关系数目
-            who_chat_in_group.append((db_msg.user_info.platform, db_msg.user_info.user_id, db_msg.user_info.user_nickname))
+            who_chat_in_group.append(
+                (db_msg.user_info.platform, db_msg.user_info.user_id, db_msg.user_info.user_nickname)
+            )
 
     return who_chat_in_group
 
@@ -641,9 +645,9 @@ def get_chat_type_and_target_info(chat_id: str) -> Tuple[bool, Optional[Dict]]:
                 target_info = TargetPersonInfo(
                     platform=platform,
                     user_id=user_id,
-                    user_nickname=user_info.user_nickname, # type: ignore
+                    user_nickname=user_info.user_nickname,  # type: ignore
                     person_id=None,
-                    person_name=None
+                    person_name=None,
                 )
 
                 # Try to fetch person info
@@ -670,7 +674,7 @@ def get_chat_type_and_target_info(chat_id: str) -> Tuple[bool, Optional[Dict]]:
     return is_group_chat, chat_target_info
 
 
-def assign_message_ids(messages: List[Any]) -> List[Dict[str, Any]]:
+def assign_message_ids(messages: List[DatabaseMessages]) -> List[DatabaseMessages]:
     """
     为消息列表中的每个消息分配唯一的简短随机ID
 
@@ -678,9 +682,9 @@ def assign_message_ids(messages: List[Any]) -> List[Dict[str, Any]]:
         messages: 消息列表
 
     Returns:
-        包含 {'id': str, 'message': any} 格式的字典列表
+        List[DatabaseMessages]: 分配了唯一ID的消息列表(写入message_id属性)
     """
-    result = []
+    result: List[DatabaseMessages] = list(messages)  # 复制原始消息列表
     used_ids = set()
     len_i = len(messages)
     if len_i > 100:
@@ -690,72 +694,62 @@ def assign_message_ids(messages: List[Any]) -> List[Dict[str, Any]]:
         a = 1
         b = 9
 
-    for i, message in enumerate(messages):
+    for i, _ in enumerate(result):
         # 生成唯一的简短ID
         while True:
             # 使用索引+随机数生成简短ID
             random_suffix = random.randint(a, b)
-            message_id = f"m{i+1}{random_suffix}"
+            message_id = f"m{i + 1}{random_suffix}"
 
             if message_id not in used_ids:
                 used_ids.add(message_id)
                 break
-        
+        result[i].message_id = message_id
-        result.append({
-            'id': message_id,
-            'message': message
-        })
 
     return result
 
 
-def assign_message_ids_flexible(
+# def assign_message_ids_flexible(
-    messages: list, 
+#     messages: list, prefix: str = "msg", id_length: int = 6, use_timestamp: bool = False
-    prefix: str = "msg", 
+# ) -> list:
-    id_length: int = 6,
+#     """
-    use_timestamp: bool = False
+#     为消息列表中的每个消息分配唯一的简短随机ID（增强版）
-) -> list:
-    """
-    为消息列表中的每个消息分配唯一的简短随机ID（增强版）
 
-    Args:
+#     Args:
-        messages: 消息列表
+#         messages: 消息列表
-        prefix: ID前缀，默认为"msg"
+#         prefix: ID前缀，默认为"msg"
-        id_length: ID的总长度（不包括前缀），默认为6
+#         id_length: ID的总长度（不包括前缀），默认为6
-        use_timestamp: 是否在ID中包含时间戳，默认为False
+#         use_timestamp: 是否在ID中包含时间戳，默认为False
 
-    Returns:
+#     Returns:
-        包含 {'id': str, 'message': any} 格式的字典列表
+#         包含 {'id': str, 'message': any} 格式的字典列表
-    """
+#     """
-    result = []
+#     result = []
-    used_ids = set()
+#     used_ids = set()
 
-    for i, message in enumerate(messages):
+#     for i, message in enumerate(messages):
-        # 生成唯一的ID
+#         # 生成唯一的ID
-        while True:
+#         while True:
-            if use_timestamp:
+#             if use_timestamp:
-                # 使用时间戳的后几位 + 随机字符
+#                 # 使用时间戳的后几位 + 随机字符
-                timestamp_suffix = str(int(time.time() * 1000))[-3:]
+#                 timestamp_suffix = str(int(time.time() * 1000))[-3:]
-                remaining_length = id_length - 3
+#                 remaining_length = id_length - 3
-                random_chars = ''.join(random.choices(string.ascii_lowercase + string.digits, k=remaining_length))
+#                 random_chars = "".join(random.choices(string.ascii_lowercase + string.digits, k=remaining_length))
-                message_id = f"{prefix}{timestamp_suffix}{random_chars}"
+#                 message_id = f"{prefix}{timestamp_suffix}{random_chars}"
-            else:
+#             else:
-                # 使用索引 + 随机字符
+#                 # 使用索引 + 随机字符
-                index_str = str(i + 1)
+#                 index_str = str(i + 1)
-                remaining_length = max(1, id_length - len(index_str))
+#                 remaining_length = max(1, id_length - len(index_str))
-                random_chars = ''.join(random.choices(string.ascii_lowercase + string.digits, k=remaining_length))
+#                 random_chars = "".join(random.choices(string.ascii_lowercase + string.digits, k=remaining_length))
-                message_id = f"{prefix}{index_str}{random_chars}"
+#                 message_id = f"{prefix}{index_str}{random_chars}"
 
-            if message_id not in used_ids:
+#             if message_id not in used_ids:
-                used_ids.add(message_id)
+#                 used_ids.add(message_id)
-                break
+#                 break
 
-        result.append({
+#         result.append({"id": message_id, "message": message})
-            'id': message_id,
-            'message': message
-        })
 
-    return result
+#     return result
 
 
 # 使用示例:
@@ -773,6 +767,7 @@ def assign_message_ids_flexible(
 # result3 = assign_message_ids_flexible(messages, prefix="ts", use_timestamp=True)
 # # 结果: [{'id': 'ts123a1b', 'message': 'Hello'}, {'id': 'ts123c2d', 'message': 'World'}, {'id': 'ts123e3f', 'message': 'Test message'}]
 
+
 def parse_keywords_string(keywords_input) -> list[str]:
     # sourcery skip: use-contextlib-suppress
     """
@@ -826,7 +821,7 @@ def parse_keywords_string(keywords_input) -> list[str]:
         pass
 
     # 尝试不同的分隔符
-    separators = ['/', ',', ' ', '|', ';']
+    separators = ["/", ",", " ", "|", ";"]
 
     for separator in separators:
         if separator in keywords_str:

src/common/data_models/__init__.py

@@ -1,26 +1,27 @@
+import copy
 from typing import Dict, Any
 
 
-class AbstractClassFlag:
+class BaseDataModel:
-    pass
+    def deepcopy(self):
-
+        return copy.deepcopy(self)
 
 def temporarily_transform_class_to_dict(obj: Any) -> Any:
     """
-    将对象或容器中的 AbstractClassFlag 子类（类对象）或 AbstractClassFlag 实例
+    将对象或容器中的 BaseDataModel 子类（类对象）或 BaseDataModel 实例
     递归转换为普通 dict，不修改原对象。
-    - 对于类对象（isinstance(value, type) 且 issubclass(..., AbstractClassFlag)），
+    - 对于类对象（isinstance(value, type) 且 issubclass(..., BaseDataModel)），
       读取类的 __dict__ 中非 dunder 项并递归转换。
-    - 对于实例（isinstance(value, AbstractClassFlag)），读取 vars(instance) 并递归转换。
+    - 对于实例（isinstance(value, BaseDataModel)），读取 vars(instance) 并递归转换。
     """
 
     def _transform(value: Any) -> Any:
-        # 值是类对象且为 AbstractClassFlag 的子类
+        # 值是类对象且为 BaseDataModel 的子类
-        if isinstance(value, type) and issubclass(value, AbstractClassFlag):
+        if isinstance(value, type) and issubclass(value, BaseDataModel):
             return {k: _transform(v) for k, v in value.__dict__.items() if not k.startswith("__") and not callable(v)}
 
-        # 值是 AbstractClassFlag 的实例
+        # 值是 BaseDataModel 的实例
-        if isinstance(value, AbstractClassFlag):
+        if isinstance(value, BaseDataModel):
             return {k: _transform(v) for k, v in vars(value).items()}
 
         # 常见容器类型，递归处理

src/common/data_models/database_data_model.py

@@ -1,11 +1,11 @@
-from typing import Optional, Dict, Any
+from typing import Optional, Any
-from dataclasses import dataclass, field, fields, MISSING
+from dataclasses import dataclass, field
 
-from . import AbstractClassFlag
+from . import BaseDataModel
 
 
 @dataclass
-class DatabaseUserInfo(AbstractClassFlag):
+class DatabaseUserInfo(BaseDataModel):
     platform: str = field(default_factory=str)
     user_id: str = field(default_factory=str)
     user_nickname: str = field(default_factory=str)
@@ -21,7 +21,7 @@ class DatabaseUserInfo(AbstractClassFlag):
 
 
 @dataclass
-class DatabaseGroupInfo(AbstractClassFlag):
+class DatabaseGroupInfo(BaseDataModel):
     group_id: str = field(default_factory=str)
     group_name: str = field(default_factory=str)
     group_platform: Optional[str] = None
@@ -35,7 +35,7 @@ class DatabaseGroupInfo(AbstractClassFlag):
 
 
 @dataclass
-class DatabaseChatInfo(AbstractClassFlag):
+class DatabaseChatInfo(BaseDataModel):
     stream_id: str = field(default_factory=str)
     platform: str = field(default_factory=str)
     create_time: float = field(default_factory=float)
@@ -55,7 +55,7 @@ class DatabaseChatInfo(AbstractClassFlag):
 
 
 @dataclass(init=False)
-class DatabaseMessages(AbstractClassFlag):
+class DatabaseMessages(BaseDataModel):
     def __init__(
         self,
         message_id: str = "",

src/common/data_models/info_data_model.py

@@ -1,8 +1,10 @@
 from dataclasses import dataclass, field
 from typing import Optional
 
+from . import BaseDataModel
+
 @dataclass
-class TargetPersonInfo:
+class TargetPersonInfo(BaseDataModel):
     platform: str = field(default_factory=str)
     user_id: str = field(default_factory=str)
     user_nickname: str = field(default_factory=str)

src/common/data_models/message_data_model.py

@@ -1,9 +1,10 @@
 from typing import Optional
 from dataclasses import dataclass, field
 
+from . import BaseDataModel
 
 @dataclass
-class MessageAndActionModel:
+class MessageAndActionModel(BaseDataModel):
     time: float = field(default_factory=float)
     user_id: str = field(default_factory=str)
     user_platform: str = field(default_factory=str)