Losita/mai-bot
0
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Ruff Fix & format

Browse Source
This commit is contained in:
墨梓柒
2025-11-29 14:38:42 +08:00
parent d7932595e8
commit 3935ce817e
31 changed files with 678 additions and 684 deletions
Download Patch File Download Diff File Expand all files Collapse all files

37
src/jargon/jargon_explainer.py
View File

@@ -44,9 +44,7 @@ class JargonExplainer:
request_type="jargon.explain",
)
def match_jargon_from_messages(
self, messages: List[Any]
) -> List[Dict[str, str]]:
def match_jargon_from_messages(self, messages: List[Any]) -> List[Dict[str, str]]:
"""
通过直接匹配数据库中的jargon字符串来提取黑话
@@ -57,7 +55,7 @@ class JargonExplainer:
List[Dict[str, str]]: 提取到的黑话列表，每个元素包含content
"""
start_time = time.time()
if not messages:
return []
@@ -67,8 +65,10 @@ class JargonExplainer:
# 跳过机器人自己的消息
if is_bot_message(msg):
continue
msg_text = (getattr(msg, "display_message", None) or getattr(msg, "processed_plain_text", None) or "").strip()
msg_text = (
getattr(msg, "display_message", None) or getattr(msg, "processed_plain_text", None) or ""
).strip()
if msg_text:
message_texts.append(msg_text)
@@ -79,9 +79,7 @@ class JargonExplainer:
combined_text = " ".join(message_texts)
# 查询所有有meaning的jargon记录
query = Jargon.select().where(
(Jargon.meaning.is_null(False)) & (Jargon.meaning != "")
)
query = Jargon.select().where((Jargon.meaning.is_null(False)) & (Jargon.meaning != ""))
# 根据all_global配置决定查询逻辑
if global_config.jargon.all_global:
@@ -98,7 +96,7 @@ class JargonExplainer:
# 执行查询并匹配
matched_jargon: Dict[str, Dict[str, str]] = {}
query_time = time.time()
for jargon in query:
content = jargon.content or ""
if not content or not content.strip():
@@ -123,13 +121,13 @@ class JargonExplainer:
pattern = re.escape(content)
# 使用单词边界或中文字符边界来匹配，避免部分匹配
# 对于中文，使用Unicode字符类；对于英文，使用单词边界
if re.search(r'[\u4e00-\u9fff]', content):
if re.search(r"[\u4e00-\u9fff]", content):
# 包含中文，使用更宽松的匹配
search_pattern = pattern
else:
# 纯英文/数字，使用单词边界
search_pattern = r'\b' + pattern + r'\b'
search_pattern = r"\b" + pattern + r"\b"
if re.search(search_pattern, combined_text, re.IGNORECASE):
# 找到匹配，记录（去重）
if content not in matched_jargon:
@@ -139,7 +137,7 @@ class JargonExplainer:
total_time = match_time - start_time
query_duration = query_time - start_time
match_duration = match_time - query_time
logger.info(
f"黑话匹配完成: 查询耗时 {query_duration:.3f}s, 匹配耗时 {match_duration:.3f}s, "
f"总耗时 {total_time:.3f}s, 匹配到 {len(matched_jargon)} 个黑话"
@@ -147,9 +145,7 @@ class JargonExplainer:
return list(matched_jargon.values())
async def explain_jargon(
self, messages: List[Any], chat_context: str
) -> Optional[str]:
async def explain_jargon(self, messages: List[Any], chat_context: str) -> Optional[str]:
"""
解释上下文中的黑话
@@ -183,7 +179,7 @@ class JargonExplainer:
jargon_explanations: List[str] = []
for entry in jargon_list:
content = entry["content"]
# 根据是否开启全局黑话，决定查询方式
if global_config.jargon.all_global:
# 开启全局黑话：查询所有is_global=True的记录
@@ -239,9 +235,7 @@ class JargonExplainer:
return summary
async def explain_jargon_in_context(
chat_id: str, messages: List[Any], chat_context: str
) -> Optional[str]:
async def explain_jargon_in_context(chat_id: str, messages: List[Any], chat_context: str) -> Optional[str]:
"""
解释上下文中的黑话（便捷函数）
@@ -255,4 +249,3 @@ async def explain_jargon_in_context(
"""
explainer = JargonExplainer(chat_id)
return await explainer.explain_jargon(messages, chat_context)

28
src/jargon/jargon_miner.py
View File

@@ -17,20 +17,18 @@ from src.chat.utils.chat_message_builder import (
)
from src.chat.utils.prompt_builder import Prompt, global_prompt_manager
from src.jargon.jargon_utils import (
is_bot_message,
build_context_paragraph,
contains_bot_self_name,
parse_chat_id_list,
is_bot_message,
build_context_paragraph,
contains_bot_self_name,
parse_chat_id_list,
chat_id_list_contains,
update_chat_id_list
update_chat_id_list,
)
logger = get_logger("jargon")
def _init_prompt() -> None:
prompt_str = """
**聊天内容，其中的{bot_name}的发言内容是你自己的发言，[msg_id] 是消息ID**
@@ -126,7 +124,6 @@ _init_prompt()
_init_inference_prompts()
def _should_infer_meaning(jargon_obj: Jargon) -> bool:
"""
判断是否需要进行含义推断
@@ -211,7 +208,9 @@ class JargonMiner:
processed_pairs = set()
for idx, msg in enumerate(messages):
msg_text = (getattr(msg, "display_message", None) or getattr(msg, "processed_plain_text", None) or "").strip()
msg_text = (
getattr(msg, "display_message", None) or getattr(msg, "processed_plain_text", None) or ""
).strip()
if not msg_text or is_bot_message(msg):
continue
@@ -270,7 +269,7 @@ class JargonMiner:
prompt1 = await global_prompt_manager.format_prompt(
"jargon_inference_with_context_prompt",
content=content,
bot_name = global_config.bot.nickname,
bot_name=global_config.bot.nickname,
raw_content_list=raw_content_text,
)
@@ -588,7 +587,6 @@ class JargonMiner:
content = entry["content"]
raw_content_list = entry["raw_content"] # 已经是列表
try:
# 查询所有content匹配的记录
query = Jargon.select().where(Jargon.content == content)
@@ -782,15 +780,15 @@ def search_jargon(
# 如果记录是is_global=True，或者chat_id列表包含目标chat_id，则包含
if not jargon.is_global and not chat_id_list_contains(chat_id_list, chat_id):
continue
# 只返回有meaning的记录
if not jargon.meaning or jargon.meaning.strip() == "":
continue
results.append({"content": jargon.content or "", "meaning": jargon.meaning or ""})
# 达到限制数量后停止
if len(results) >= limit:
break
return results
return results

26
src/jargon/jargon_utils.py
View File

@@ -13,19 +13,20 @@ from src.chat.utils.utils import parse_platform_accounts
logger = get_logger("jargon")
def parse_chat_id_list(chat_id_value: Any) -> List[List[Any]]:
"""
解析chat_id字段，兼容旧格式（字符串）和新格式（JSON列表）
Args:
chat_id_value: 可能是字符串（旧格式）或JSON字符串（新格式）
Returns:
List[List[Any]]: 格式为 [[chat_id, count], ...] 的列表
"""
if not chat_id_value:
return []
# 如果是字符串，尝试解析为JSON
if isinstance(chat_id_value, str):
# 尝试解析JSON
@@ -54,12 +55,12 @@ def parse_chat_id_list(chat_id_value: Any) -> List[List[Any]]:
def update_chat_id_list(chat_id_list: List[List[Any]], target_chat_id: str, increment: int = 1) -> List[List[Any]]:
"""
更新chat_id列表，如果target_chat_id已存在则增加计数，否则添加新条目
Args:
chat_id_list: 当前的chat_id列表，格式为 [[chat_id, count], ...]
target_chat_id: 要更新或添加的chat_id
increment: 增加的计数，默认为1
Returns:
List[List[Any]]: 更新后的chat_id列表
"""
@@ -74,22 +75,22 @@ def update_chat_id_list(chat_id_list: List[List[Any]], target_chat_id: str, incr
item.append(increment)
found = True
break
if not found:
# 未找到，添加新条目
chat_id_list.append([target_chat_id, increment])
return chat_id_list
def chat_id_list_contains(chat_id_list: List[List[Any]], target_chat_id: str) -> bool:
"""
检查chat_id列表中是否包含指定的chat_id
Args:
chat_id_list: chat_id列表，格式为 [[chat_id, count], ...]
target_chat_id: 要查找的chat_id
Returns:
bool: 如果包含则返回True
"""
@@ -168,10 +169,7 @@ def is_bot_message(msg: Any) -> bool:
.strip()
.lower()
)
user_id = (
str(getattr(msg, "user_id", "") or getattr(getattr(msg, "user_info", None), "user_id", "") or "")
.strip()
)
user_id = str(getattr(msg, "user_id", "") or getattr(getattr(msg, "user_info", None), "user_id", "") or "").strip()
if not platform or not user_id:
return False
@@ -196,4 +194,4 @@ def is_bot_message(msg: Any) -> bool:
bot_accounts[plat] = account
bot_account = bot_accounts.get(platform)
return bool(bot_account and user_id == bot_account)
return bool(bot_account and user_id == bot_account)