perf(methods): 通过移除不必要的 self 参数优化方法签名

在包括 chat、plugin_system、schedule 和 mais4u 在内的多个模块中，消除冗余的实例引用。此次改动将无需访问实例状态的实用函数转换为静态方法，从而提升了内存效率，并使方法依赖关系更加清晰。
2025-09-20 10:55:06 +08:00
parent aba4f1a947
commit 93542cadef
111 changed files with 705 additions and 465 deletions
--- a/src/person_info/person_info.py
+++ b/src/person_info/person_info.py
@@ -1,16 +1,18 @@
+import copy
+import datetime
 import hashlib
-import asyncio
-import orjson
 import time
-
-from json_repair import repair_json
 from typing import Any, Callable, Dict, Union, Optional
+
+import orjson
+from json_repair import repair_json
 from sqlalchemy import select
-from src.common.logger import get_logger
-from src.common.database.sqlalchemy_models import PersonInfo
+
 from src.common.database.sqlalchemy_database_api import get_db_session
-from src.llm_models.utils_model import LLMRequest
+from src.common.database.sqlalchemy_models import PersonInfo
+from src.common.logger import get_logger
 from src.config.config import global_config, model_config
+from src.llm_models.utils_model import LLMRequest

 logger = get_logger("person_info")

@@ -444,7 +446,8 @@ class PersonInfoManager:
            logger.error(f"检查用户 {person_id} 是否已知时出错 (SQLAlchemy): {e}")
            return False

-    async def get_person_id_by_person_name(self, person_name: str) -> str:
+    @staticmethod
+    async def get_person_id_by_person_name(person_name: str) -> str:
        """根据用户名获取用户ID"""
        try:
            # 在需要时获取会话
@@ -516,7 +519,8 @@ class PersonInfoManager:

        await _db_create_async(final_data)

-    async def _safe_create_person_info(self, person_id: str, data: Optional[dict] = None):
+    @staticmethod
+    async def _safe_create_person_info(person_id: str, data: Optional[dict] = None):
        """安全地创建用户信息，处理竞态条件"""
        if not person_id:
            logger.debug("创建失败，person_id不存在")
--- a/src/person_info/relationship_builder.py
+++ b/src/person_info/relationship_builder.py
@@ -3,7 +3,7 @@ import traceback
 import os
 import pickle
 import random
-from typing import List, Dict, Any
+from typing import List, Dict, Any, Coroutine
 from src.config.config import global_config
 from src.common.logger import get_logger
 from src.person_info.relationship_manager import get_relationship_manager
@@ -203,7 +203,7 @@ class RelationshipBuilder:
        messages = get_raw_msg_by_timestamp_with_chat_inclusive(self.chat_id, start_time, end_time)
        return len(messages)

-    def _count_messages_between(self, start_time: float, end_time: float) -> int:
+    def _count_messages_between(self, start_time: float, end_time: float) -> Coroutine[Any, Any, int]:
        """计算两个时间点之间的消息数量（不包含边界），用于间隔检查"""
        return num_new_messages_since(self.chat_id, start_time, end_time)

@@ -316,18 +316,12 @@ class RelationshipBuilder:
        if not self.person_engaged_cache:
            return f"{self.log_prefix} 关系缓存为空"

-        status_lines = [f"{self.log_prefix} 关系缓存状态："]
-        status_lines.append(
-            f"最后处理消息时间：{time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(self.last_processed_message_time)) if self.last_processed_message_time > 0 else '未设置'}"
-        )
-        status_lines.append(
-            f"最后清理时间：{time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(self.last_cleanup_time)) if self.last_cleanup_time > 0 else '未执行'}"
-        )
-        status_lines.append(f"总用户数：{len(self.person_engaged_cache)}")
-        status_lines.append(
-            f"清理配置：{'启用' if SEGMENT_CLEANUP_CONFIG['enable_cleanup'] else '禁用'} (最大保存{SEGMENT_CLEANUP_CONFIG['max_segment_age_days']}天, 每用户最多{SEGMENT_CLEANUP_CONFIG['max_segments_per_user']}段)"
-        )
-        status_lines.append("")
+        status_lines = [f"{self.log_prefix} 关系缓存状态：",
+                        f"最后处理消息时间：{time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(self.last_processed_message_time)) if self.last_processed_message_time > 0 else '未设置'}",
+                        f"最后清理时间：{time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(self.last_cleanup_time)) if self.last_cleanup_time > 0 else '未执行'}",
+                        f"总用户数：{len(self.person_engaged_cache)}",
+                        f"清理配置：{'启用' if SEGMENT_CLEANUP_CONFIG['enable_cleanup'] else '禁用'} (最大保存{SEGMENT_CLEANUP_CONFIG['max_segment_age_days']}天, 每用户最多{SEGMENT_CLEANUP_CONFIG['max_segments_per_user']}段)",
+                        ""]

        for person_id, segments in self.person_engaged_cache.items():
            total_count = self._get_total_message_count(person_id)
--- a/src/person_info/relationship_manager.py
+++ b/src/person_info/relationship_manager.py
@@ -533,7 +533,8 @@ class RelationshipManager:
        


-    def calculate_time_weight(self, point_time: str, current_time: str) -> float:
+    @staticmethod
+    def calculate_time_weight(point_time: str, current_time: str) -> float:
        """计算基于时间的权重系数"""
        try:
            point_timestamp = datetime.strptime(point_time, "%Y-%m-%d %H:%M:%S")
@@ -557,7 +558,69 @@ class RelationshipManager:
            logger.error(f"计算时间权重失败: {e}")
            return 0.5  # 发生错误时返回中等权重

-init_prompt()
+    @staticmethod
+    def tfidf_similarity(s1, s2):
+        """
+        使用 TF-IDF 和余弦相似度计算两个句子的相似性。
+        """
+        # 确保输入是字符串类型
+        if isinstance(s1, list):
+            s1 = " ".join(str(x) for x in s1)
+        if isinstance(s2, list):
+            s2 = " ".join(str(x) for x in s2)
+
+        # 转换为字符串类型
+        s1 = str(s1)
+        s2 = str(s2)
+
+        # 1. 使用 jieba 进行分词
+        s1_words = " ".join(jieba.cut(s1))
+        s2_words = " ".join(jieba.cut(s2))
+
+        # 2. 将两句话放入一个列表中
+        corpus = [s1_words, s2_words]
+
+        # 3. 创建 TF-IDF 向量化器并进行计算
+        try:
+            vectorizer = TfidfVectorizer()
+            tfidf_matrix = vectorizer.fit_transform(corpus)
+        except ValueError:
+            # 如果句子完全由停用词组成，或者为空，可能会报错
+            return 0.0
+
+        # 4. 计算余弦相似度
+        similarity_matrix = cosine_similarity(tfidf_matrix)
+
+        # 返回 s1 和 s2 的相似度
+        return similarity_matrix[0, 1]
+
+    @staticmethod
+    def sequence_similarity(s1, s2):
+        """
+        使用 SequenceMatcher 计算两个句子的相似性。
+        """
+        return SequenceMatcher(None, s1, s2).ratio()
+
+    def check_similarity(self, text1, text2, tfidf_threshold=0.5, seq_threshold=0.6):
+        """
+        使用两种方法检查文本相似度，只要其中一种方法达到阈值就认为是相似的。
+
+        Args:
+            text1: 第一个文本
+            text2: 第二个文本
+            tfidf_threshold: TF-IDF相似度阈值
+            seq_threshold: SequenceMatcher相似度阈值
+
+        Returns:
+            bool: 如果任一方法达到阈值则返回True
+        """
+        # 计算两种相似度
+        tfidf_sim = self.tfidf_similarity(text1, text2)
+        seq_sim = self.sequence_similarity(text1, text2)
+
+        # 只要其中一种方法达到阈值就认为是相似的
+        return tfidf_sim > tfidf_threshold or seq_sim > seq_threshold
+

 relationship_manager = None