Refactoring: step3

- вся работа с shelve унесена в report
- вся работа с БД унесена в моделс (крме команд админа)
- ид книги лутца и звука вынесены в константы
- исправлен баг в проверке на смешанный алфавит при определении спама, добавлены константы для более точного выявления
- написаны новые тесты в том числе на цитаты и действия админов

src/commands.py

@@ -1,16 +1,16 @@
 import logging
 import logging.handlers
-import shelve
 
 from telebot import types
 
-from .constants import DATA, LOG_COMM, FAQ, LIB, RULES, RUS, RUS_ENG_TABLE, ENG_RUS_TABLE, PYTHONCHATRU, ZEN
+from .admin_commands import bot
+from .constants import (LOG_COMM, FAQ, LIB, RULES, RUS, RUS_ENG_TABLE, ENG_RUS_TABLE, PYTHONCHATRU, ZEN, LUTZ_ID,
+                        BDMTSS_ID)
 from .filters import in_spam_list, in_caption_spam_list, in_delete_list
 from .helpers import represent_as_get, detect_args, is_admin
-from .admin_commands import bot
+from .report import update_stats, increment
 from .rules import fetch_rule
 from .stan import act, speak
-from .report import update_stats
 
 
 async def send_or_reply(message: types.Message, answer, **kwargs):
@@ -29,8 +29,7 @@ async def moderate_messages(message: types.Message):
     """Ban user and delete their message."""
     await bot.delete_message(message.chat.id, message.id)
     await bot.ban_chat_member(message.chat.id, message.from_user.id)
-    with shelve.open(f"{DATA}{message.chat.id}") as shelve_db:
-        shelve_db["Banned"] += 1
+    increment(message.chat.id, banned=True)
 
 
 @bot.message_handler(func=in_caption_spam_list, content_types=["video"], chat_types=["supergroup", "group"])
@@ -38,8 +37,7 @@ async def catch_videos(message: types.Message):
     """Catch offensive videos"""
     await bot.delete_message(message.chat.id, message.id)
     await bot.ban_chat_member(message.chat.id, message.from_user.id)
-    with shelve.open(f"{DATA}{message.chat.id}") as shelve_db:
-        shelve_db["Banned"] += 1
+    increment(message.chat.id, banned=True)
 
 
 @bot.edited_message_handler(func=in_delete_list, chat_types=["supergroup", "group"])
@@ -47,8 +45,7 @@ async def catch_videos(message: types.Message):
 async def delete_message(message: types.Message):
     """Delete unwanted message."""
     await bot.delete_message(message.chat.id, message.id)
-    with shelve.open(f"{DATA}{message.chat.id}") as shelve_db:
-        shelve_db["Deleted"] += 1
+    increment(message.chat.id, banned=False)
 
 
 """                [ COMMANDS ]             """
@@ -122,11 +119,7 @@ async def send_lutz(message: types.Message):
             message.text,
         )
     )
-    await bot.send_document(
-        message.chat.id,
-        document="BQACAgQAAxkBAAPBYsWJG9Ml0fPrnbU9UyzTQiQSuHkAAjkDAAIstCxSkuRbXAlcqeQpBA",
-        caption="вот, не позорься",
-    )
+    await bot.send_document(message.chat.id, document=LUTZ_ID, caption="вот, не позорься")
     await bot.delete_message(message.chat.id, message.id)
 
 
@@ -141,10 +134,7 @@ async def send_bdmtss_audio(message: types.Message):
             message.text,
         )
     )
-    await bot.send_voice(
-        message.chat.id,
-        "AwACAgIAAxkBAAIJrWOg2WUvLwrf7ahyJxQHB8_nqllwAAL5JQAC2_IJSbhfQIO5YnVmLAQ",
-    )
+    await bot.send_voice(message.chat.id, BDMTSS_ID)
     await bot.delete_message(message.chat.id, message.id)
 
 
@@ -210,7 +200,7 @@ async def send_nometa(message: types.Message):
         )
     )
     markup = types.InlineKeyboardMarkup()
-    markup.add(types.InlineKeyboardButton("❓ nometa.xyz", url="https://nometa.xyz/ru.html"),  row_width=1)
+    markup.add(types.InlineKeyboardButton("❓ nometa.xyz", url="https://nometa.xyz/ru.html"), row_width=1)
     await send_or_reply(
         message,
         """Не задавай мета-вопросов вроде:

src/config.py

@@ -1,9 +1,11 @@
 import logging
 import os
-from .helpers import is_url_reachable
+
 from dotenv import load_dotenv
 from telebot import logger
 
+from .helpers import is_url_reachable
+
 load_dotenv()
 
 TOKEN = os.environ.get("LUTZPYBOT")

src/constants.py

@@ -1,8 +1,8 @@
 import re
+import string
 
 from telebot import types
 
-
 LOG_TEXT = "[%s] %s: %s"
 LOG_COMM = "[%s] [%s] %s: %s"
 LOGGING_LEVEL_DEBUG = 10
@@ -37,6 +37,8 @@ ALLOWED_WORDS = [
 ]
 
 RUS = """ёйцукенгшщзхъфывапролджэячсмитьбю.Ё!"№;%:?ЙЦУКЕНГШЩЗХЪ/ФЫВАПРОЛДЖЭЯЧСМИТЬБЮ,"""
+ONLY_RUS_LETTERS = "ёйцукенгшщзхъфывапролджэячсмитьбю"
+RUS_LETTERS_AND_PUNCTUATION = ONLY_RUS_LETTERS + string.punctuation
 ENG = """`qwertyuiop[]asdfghjkl;'zxcvbnm,./~!@#$%^&QWERTYUIOP{}|ASDFGHJKL:"ZXCVBNM<>?"""
 RUS_ENG_TABLE = str.maketrans(RUS, ENG)
 ENG_RUS_TABLE = str.maketrans(ENG, RUS)
@@ -78,4 +80,5 @@ ZEN = [
     "If the implementation is easy to explain, it may be a good idea.",
     "Namespaces are one honking great idea — let's do more of those!",
 ]
-
+LUTZ_ID = "BQACAgQAAxkBAAPBYsWJG9Ml0fPrnbU9UyzTQiQSuHkAAjkDAAIstCxSkuRbXAlcqeQpBA"
+BDMTSS_ID = "AwACAgIAAxkBAAIJrWOg2WUvLwrf7ahyJxQHB8_nqllwAAL5JQAC2_IJSbhfQIO5YnVmLAQ"

src/filters.py

@@ -5,12 +5,11 @@ from telebot import types
 from .config import WHITEIDS
 from .constants import LOG_COMM, ALLOWED_WORDS, URL_RX
 from .helpers import is_spam, is_in_not_allowed, is_ban_words_in_caption
-from .models import Chat, session
+from .models import is_antispam_enabled
 
 
 def in_spam_list(message: types.Message) -> bool:
-    """Check for mentioning unwanted persons in text."""
-    antispam_is_enabled = session.query(Chat.antispam).filter_by(chat_id=message.chat.id).first()[0]
+    antispam_is_enabled = is_antispam_enabled(message.chat.id)
     from_user_id, title, from_user_name = message.from_user.id, message.chat.title, message.from_user.first_name
     if from_user_id not in WHITEIDS and antispam_is_enabled:
         if is_spam(message.text):
@@ -30,7 +29,7 @@ def in_caption_spam_list(message: types.Message) -> bool:
 
 def in_delete_list(message: types.Message) -> bool:
     """Check for URLs in message and delete."""
-    antispam_is_enabled = session.query(Chat.antispam).filter_by(chat_id=message.chat.id).first()[0]
+    antispam_is_enabled = is_antispam_enabled(message.chat.id)
     from_user_id, title, from_user_name = message.from_user.id, message.chat.title, message.from_user.first_name
     if from_user_id not in WHITEIDS and antispam_is_enabled:
         if URL_RX.search(message.text) and is_in_not_allowed(ALLOWED_WORDS, message.text):

src/helpers.py

@@ -6,7 +6,7 @@ from urllib.request import urlopen
 
 from telebot import types
 
-from .constants import SPAM, RUS, BAN_WORDS, NON_GRATA, ADMIN_ID
+from .constants import SPAM, BAN_WORDS, NON_GRATA, ADMIN_ID, ONLY_RUS_LETTERS, RUS_LETTERS_AND_PUNCTUATION
 
 
 def is_url_reachable(url: str) -> bool:
@@ -17,14 +17,22 @@ def is_url_reachable(url: str) -> bool:
 
 
 def is_spam(message_text: str) -> bool:
+    """
+    Проверяет текст на спам - сначала проверка смешанного алфавита, потом на константный набор спам-слов
+    """
     if is_mixed(message_text):
         return True
     return any(text.casefold() in message_text.casefold() for text in SPAM)
 
 
 def is_mixed(text: str) -> bool:
+    """
+    Разбивает текст на слова и проверяет на смешанный алфавит, спамеры используют его. Слово допускается только
+    полностью на русском или русский + знаки пунктуации
+    """
     for word in text.split():
-        if not all(e in RUS for e in word.strip().lower()):
+        word = word.strip().lower()
+        if any(e in ONLY_RUS_LETTERS for e in word) and not all(e in RUS_LETTERS_AND_PUNCTUATION for e in word):
             return True
     return False
 

src/models.py

@@ -2,6 +2,7 @@ from pathlib import Path
 
 from sqlalchemy import Column, String, Integer, Boolean, ForeignKey
 from sqlalchemy import create_engine
+from sqlalchemy import delete
 from sqlalchemy.orm import relationship, declarative_base, sessionmaker
 
 Base = declarative_base()
@@ -49,3 +50,29 @@ class Chat(Base):
 
     def __repr__(self):
         return f'Chat({self.chat_id=}, {self.title=})'
+
+
+def is_antispam_enabled(chat_id: int) -> bool:
+    try:
+        return session.query(Chat.antispam).filter_by(chat_id=chat_id).first()[0]
+    except TypeError:
+        return False
+
+
+def is_quote_in_chat(text: str, chat_id: int) -> bool:
+    result = session.query(Quote.text).filter_by(text=text, chat_id=chat_id).first()
+    return bool(result)
+
+
+def delete_quote_in_chat(text: str, chat_id: int):
+    session.execute(delete(Quote).filter_by(text=text, chat_id=chat_id))
+    session.commit()
+
+
+def all_chat_quotes(chat_id: int) -> list:
+    return session.query(Quote.text).filter(Quote.chat_id == chat_id).all()
+
+
+def add_quote(chat_id: int, text: str):
+    session.add(Quote(chat_id=chat_id, text=text))
+    session.commit()

src/report.py

@@ -5,10 +5,17 @@ import random
 import shelve
 from pathlib import Path
 
-from telebot import types
-
 from .config import ROLLBACK
-from .constants import DATA
+from .constants import DATA, types
+
+
+def increment(chat_id: int, banned: bool = True):
+    """
+    Увеличивает счетчик банов или удаленных
+    """
+    category = "Banned" if banned else "Deleted"
+    with shelve.open(f"{DATA}{chat_id}") as shelve_db:
+        shelve_db[category] += 1
 
 
 def create_report_text(chat_id):

src/stan.py

@@ -3,21 +3,21 @@ import asyncio
 import html
 import random
 
-from sqlalchemy import delete
 from telebot import types
 
 from .filters import is_white_id
 from .helpers import is_nongrata
-from .models import Quote, session
+from .models import all_chat_quotes, add_quote, is_quote_in_chat, delete_quote_in_chat
 from .robot import bot
 
 TYPING_TIMEOUT = 0.13 / 4  # Reading time is quarter of the same text writing time
 
 
-def speak(chance_of, group_id):
+def speak(chance_of: int, chat_id: int) -> None | str:
     number = random.randint(0, chance_of)
     if number == 0:
-        return random.choice([i[0] for i in session.query(Quote.text).filter(Quote.chat_id == group_id).all()])
+        return random.choice([i[0] for i in all_chat_quotes(chat_id)])
+    return None
 
 
 async def send_quote(after_sec, message, quote):
@@ -39,9 +39,8 @@ async def act(message: types.Message):
 async def add_stan_quote(message: types.Message):
     if message.reply_to_message and message.reply_to_message.text:
         quote = message.reply_to_message.text
-        if quote not in [i[0] for i in session.query(Quote.text).filter(Quote.chat_id == message.chat.id).all()]:
-            session.add(Quote(chat_id=message.chat.id, text=quote.replace("\n", " ")))
-            session.commit()
+        if quote not in {i[0] for i in all_chat_quotes(message.chat.id)}:
+            add_quote(message.chat.id, quote.replace("\n", " "))
             await bot.send_message(message.chat.id, "➕\n  └ " + quote.replace("\n", " "), parse_mode='Markdown')
             await bot.delete_message(message.chat.id, message.id)
         else:
@@ -52,10 +51,8 @@ async def add_stan_quote(message: types.Message):
 async def remove_stan_quote(message: types.Message):
     if message.reply_to_message and message.reply_to_message.text:
         quote = message.reply_to_message.text
-        already_exist = session.query(Quote.text).filter_by(text=quote, chat_id=message.chat.id).first()
-        if already_exist:
-            session.execute(delete(Quote).filter_by(text=quote, chat_id=message.chat.id))
-            session.commit()
+        if is_quote_in_chat(quote, message.chat.id):
+            delete_quote_in_chat(quote, message.chat.id)
             await bot.send_message(message.chat.id, f"➖ \n  └ {quote}", parse_mode='Markdown')
             await bot.delete_message(message.chat.id, message.id)
         else: