Merge pull request #123 from ChangingSelf/debug

将错别字生成提取到配置

src/plugins/chat/config.py

@@ -70,6 +70,12 @@ class BotConfig:
 
     keywords_reaction_rules = [] # 关键词回复规则
 
+    chinese_typo_enable=True # 是否启用中文错别字生成器
+    chinese_typo_error_rate=0.03 # 单字替换概率
+    chinese_typo_min_freq=7 # 最小字频阈值
+    chinese_typo_tone_error_rate=0.2 # 声调错误概率
+    chinese_typo_word_replace_rate=0.02 # 整词替换概率
+
     # 默认人设
     PROMPT_PERSONALITY=[
         "曾经是一个学习地质的女大学生，现在学习心理学和脑科学，你会刷贴吧",
@@ -283,6 +289,14 @@ class BotConfig:
             if keywords_reaction_config.get("enable", False):
                 config.keywords_reaction_rules = keywords_reaction_config.get("rules", config.keywords_reaction_rules)
 
+        def chinese_typo(parent: dict):
+            chinese_typo_config = parent["chinese_typo"]
+            config.chinese_typo_enable = chinese_typo_config.get("enable", config.chinese_typo_enable)
+            config.chinese_typo_error_rate = chinese_typo_config.get("error_rate", config.chinese_typo_error_rate)
+            config.chinese_typo_min_freq = chinese_typo_config.get("min_freq", config.chinese_typo_min_freq)
+            config.chinese_typo_tone_error_rate = chinese_typo_config.get("tone_error_rate", config.chinese_typo_tone_error_rate)
+            config.chinese_typo_word_replace_rate = chinese_typo_config.get("word_replace_rate", config.chinese_typo_word_replace_rate)
+
         def groups(parent: dict):
             groups_config = parent["groups"]
             config.talk_allowed_groups = set(groups_config.get("talk_allowed", []))
@@ -341,6 +355,11 @@ class BotConfig:
                 "support": ">=0.0.2",
                 "necessary": False
             },
+            "chinese_typo": {
+                "func": chinese_typo,
+                "support": ">=0.0.3",
+                "necessary": False
+            },
             "groups": {
                 "func": groups,
                 "support": ">=0.0.0"

src/plugins/chat/utils.py

@@ -332,18 +332,21 @@ def process_llm_response(text: str) -> List[str]:
         return ['懒得说']
     # 处理长消息
     typo_generator = ChineseTypoGenerator(
-        error_rate=0.03,
+        error_rate=global_config.chinese_typo_error_rate,
-        min_freq=7,
+        min_freq=global_config.chinese_typo_min_freq,
-        tone_error_rate=0.2,
+        tone_error_rate=global_config.chinese_typo_tone_error_rate,
-        word_replace_rate=0.02
+        word_replace_rate=global_config.chinese_typo_word_replace_rate
     )
     split_sentences = split_into_sentences_w_remove_punctuation(text)
     sentences = []
     for sentence in split_sentences:
-        typoed_text, typo_corrections = typo_generator.create_typo_sentence(sentence)
+        if global_config.chinese_typo_enable:
-        sentences.append(typoed_text)
+            typoed_text, typo_corrections = typo_generator.create_typo_sentence(sentence)
-        if typo_corrections:
+            sentences.append(typoed_text)
-            sentences.append(typo_corrections)
+            if typo_corrections:
+                sentences.append(typo_corrections)
+        else:
+            sentences.append(sentence)
     # 检查分割后的消息数量是否过多（超过3条）
     
     if len(sentences) > 5:

template/bot_config_template.toml

@@ -1,5 +1,5 @@
 [inner]
-version = "0.0.2"
+version = "0.0.3"
 
 [bot]
 qq = 123
@@ -67,6 +67,13 @@ enable = false # 仅作示例，不会触发
 keywords = ["测试关键词回复","test",""]
 reaction = "回答“测试成功”"
 
+[chinese_typo]
+enable = true # 是否启用中文错别字生成器
+error_rate=0.03 # 单字替换概率
+min_freq=7 # 最小字频阈值
+tone_error_rate=0.2 # 声调错误概率
+word_replace_rate=0.02 # 整词替换概率
+
 [others]
 enable_advance_output = true # 是否启用高级输出
 enable_kuuki_read = true # 是否启用读空气功能