matplobbot-shared 0.1.330__tar.gz → 0.1.332__tar.gz

{matplobbot_shared-0.1.330 → matplobbot_shared-0.1.332}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: matplobbot-shared
-Version: 0.1.330
+Version: 0.1.332
 Summary: Shared library for the Matplobbot ecosystem.
 Author: Ackrome
 Author-email: ivansergeyevich@gmail.com

{matplobbot_shared-0.1.330 → matplobbot_shared-0.1.332}/README.md

@@ -59,7 +59,8 @@ The project currently includes:
 - View live usage stats over WebSockets.
 - See popular commands, text activity, action-type breakdowns, and activity trends.
 - Inspect user-specific pages with paginated history, filtering, and CSV export.
-- Stream the bot log into the dashboard for real-time monitoring.
+- View bot logs with `docker compose logs -f mpb-telegram-bot`; the legacy log WebSocket is intentionally disabled.
+- Configure private mailbox forwarding with `/mail` (requires `MAIL_CREDENTIAL_KEY`).
 
 ## Screenshots
 
@@ -102,6 +103,10 @@ Create a `.env` file in the project root. This is a minimal example for local st
 BOT_TOKEN=123456:ABC-DEF1234ghIkl-zyx57W2v1u123ew11
 ADMIN_USER_IDS=123456789,987654321
 GITHUB_TOKEN=ghp_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
+JWT_SECRET_KEY=change_this_to_a_secure_random_jwt_secret_in_production
+STATS_USER=admin
+STATS_PASS=change_this_admin_password_in_production
+ENVIRONMENT=development
 
 POSTGRES_USER=user
 POSTGRES_PASSWORD=password

{matplobbot_shared-0.1.330 → matplobbot_shared-0.1.332}/matplobbot_shared.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: matplobbot-shared
-Version: 0.1.330
+Version: 0.1.332
 Summary: Shared library for the Matplobbot ecosystem.
 Author: Ackrome
 Author-email: ivansergeyevich@gmail.com

{matplobbot_shared-0.1.330 → matplobbot_shared-0.1.332}/matplobbot_shared.egg-info/SOURCES.txt

@@ -12,6 +12,7 @@ shared_lib/celery_app.py
 shared_lib/constants.py
 shared_lib/database.py
 shared_lib/egress.py
+shared_lib/html_tools.py
 shared_lib/i18n.py
 shared_lib/mail_bridge.py
 shared_lib/models.py
@@ -41,6 +42,7 @@ tests/test_dashboard_text_encoding.py
 tests/test_egress.py
 tests/test_fastapi_config.py
 tests/test_keyboards.py
+tests/test_latex_task_security.py
 tests/test_localization_completeness.py
 tests/test_mail_bridge.py
 tests/test_myschedule_filters_settings.py
@@ -50,9 +52,11 @@ tests/test_proxy_config.py
 tests/test_rate_limit.py
 tests/test_schedule_search_api.py
 tests/test_schedule_service_calendar.py
+tests/test_scheduler_html_splitter.py
 tests/test_scheduler_service.py
 tests/test_search_center_helpers.py
 tests/test_stats_action_users_api.py
+tests/test_stats_avatar_security.py
 tests/test_stats_export_api.py
 tests/test_stats_leaderboard_api.py
 tests/test_stats_profile_api.py

{matplobbot_shared-0.1.330 → matplobbot_shared-0.1.332}/setup.py

@@ -2,7 +2,7 @@ from setuptools import find_packages, setup
 
 setup(
     name="matplobbot-shared",
-    version="0.1.330",  # Bump version
+    version="0.1.332",  # Bump version
     packages=find_packages(include=["shared_lib", "shared_lib.*"]),
     description="Shared library for the Matplobbot ecosystem.",
     author="Ackrome",

{matplobbot_shared-0.1.330 → matplobbot_shared-0.1.332}/shared_lib/database.py

@@ -815,14 +815,17 @@ async def delete_old_inactive_subscriptions(days_inactive: int = 30):
 
 
 async def get_subscriptions_for_notification(notification_time: str) -> list:
+    try:
+        target_time = datetime.time.fromisoformat(notification_time)
+    except (TypeError, ValueError):
+        logger.warning("Ignoring invalid notification time: %r", notification_time)
+        return []
+
     async with get_session() as session:
-        # notification_time comes as "HH:MM"
-        # We use PostgreSQL TO_CHAR on the Time column
         stmt = select(UserScheduleSubscription).where(
             and_(
                 UserScheduleSubscription.is_active.is_(True),
-                func.to_char(UserScheduleSubscription.notification_time, "HH24:MI")
-                == notification_time,
+                UserScheduleSubscription.notification_time == target_time,
             )
         )
         result = await session.execute(stmt)
@@ -1004,20 +1007,46 @@ async def batch_update_subscription_hashes(entity_type: str, entity_id: str, new
 
 
 # --- Cached Schedules ---
+def _cached_entity_name(entity_type: str, data: list | dict, fallback: str) -> str:
+    """Extract a stable display name without querying/expanding JSON later."""
+    if not isinstance(data, list):
+        return fallback
+    field_by_type = {
+        "group": "group",
+        "person": "lecturer_title",
+        "auditorium": "auditorium",
+    }
+    field = field_by_type.get(entity_type)
+    if not field:
+        return fallback
+    for lesson in data:
+        if isinstance(lesson, dict):
+            value = str(lesson.get(field) or "").strip()
+            if value:
+                return value[:255]
+    return fallback
+
+
 async def upsert_cached_schedule(entity_type: str, entity_id: str, data: list | dict):
     json_data = json.loads(json.dumps(data, default=str))  # Ensure serializable
+    entity_name = _cached_entity_name(entity_type, json_data, str(entity_id))
     async with get_session() as session:
         stmt = (
             pg_insert(CachedSchedule)
             .values(
                 entity_type=entity_type,
                 entity_id=str(entity_id),
+                entity_name=entity_name,
                 schedule_data=json_data,
                 updated_at=datetime.datetime.now(),
             )
             .on_conflict_do_update(
                 constraint="uq_cached_schedule_entity",
-                set_=dict(schedule_data=json_data, updated_at=datetime.datetime.now()),
+                set_=dict(
+                    entity_name=entity_name,
+                    schedule_data=json_data,
+                    updated_at=datetime.datetime.now(),
+                ),
             )
         )
         await session.execute(stmt)
@@ -1324,7 +1353,14 @@ async def get_leaderboard_data_from_db(session: AsyncSession):
         ORDER BY actions_count DESC LIMIT 100;
     """)
     result = await session.execute(stmt)
-    return [dict(row._mapping) for row in result]
+    rows = []
+    for row in result:
+        item = dict(row._mapping)
+        avatar = item.get("avatar_pic_url")
+        if avatar and "api.telegram.org/file/bot" in avatar:
+            item["avatar_pic_url"] = f"/api/stats/users/{item['user_id']}/avatar"
+        rows.append(item)
+    return rows
 
 
 async def get_popular_commands_data_from_db(session: AsyncSession):
@@ -1462,11 +1498,15 @@ async def get_user_profile_data_from_db(
         for r in rows
     ]
 
+    avatar_url = user.avatar_pic_url
+    if avatar_url and "api.telegram.org/file/bot" in avatar_url:
+        avatar_url = f"/api/stats/users/{user.user_id}/avatar"
+
     user_details = {
         "user_id": user.user_id,
         "full_name": user.full_name,
         "username": user.username or "Нет username",
-        "avatar_pic_url": user.avatar_pic_url,
+        "avatar_pic_url": avatar_url,
         "total_actions": total_actions,
     }
 
@@ -1587,6 +1627,7 @@ async def merge_cached_schedule(
         # merged_data.sort(key=lambda x: (x.get('date', ''), x.get('beginLesson', '')))
 
         json_data = json.loads(json.dumps(merged_data, default=str))
+        entity_name = _cached_entity_name(entity_type, json_data, str(entity_id))
 
         # 4. Upsert (вставка или обновление)
         stmt_insert = (
@@ -1594,12 +1635,17 @@ async def merge_cached_schedule(
             .values(
                 entity_type=entity_type,
                 entity_id=str(entity_id),
+                entity_name=entity_name,
                 schedule_data=json_data,
                 updated_at=datetime.datetime.now(),
             )
             .on_conflict_do_update(
                 constraint="uq_cached_schedule_entity",
-                set_=dict(schedule_data=json_data, updated_at=datetime.datetime.now()),
+                set_=dict(
+                    entity_name=entity_name,
+                    schedule_data=json_data,
+                    updated_at=datetime.datetime.now(),
+                ),
             )
         )
 

matplobbot_shared-0.1.332/shared_lib/html_tools.py

@@ -0,0 +1,121 @@
+import re
+
+HTML_TAG_RE = re.compile(r"(</?([a-zA-Z0-9_-]+)(?:\s+[^>]*)?>)")
+
+
+def split_telegram_html_message(text: str, max_chars: int = 3800) -> list[str]:
+    """
+    Safely split an HTML-formatted message into valid HTML chunks under max_chars.
+    Guarantees that:
+    1. HTML tags are never split in half.
+    2. Tags left open at the end of a chunk are safely closed.
+    3. The same open tags are reopened at the beginning of the next chunk.
+    """
+    if not isinstance(max_chars, int) or max_chars < 1:
+        raise ValueError("max_chars must be a positive integer")
+
+    text = text.strip()
+    if not text:
+        return []
+    if len(text) <= max_chars:
+        return [text]
+
+    tokens: list[tuple[str, str, bool, bool, str]] = []
+    last_end = 0
+    for match in HTML_TAG_RE.finditer(text):
+        start, end = match.span()
+        if start > last_end:
+            tokens.append(("text", text[last_end:start], False, False, ""))
+        full_tag = match.group(1)
+        tag_name = match.group(2).lower()
+        is_closing = full_tag.startswith("</")
+        is_self_closing = full_tag.endswith("/>")
+        tokens.append(("tag", full_tag, is_closing, is_self_closing, tag_name))
+        last_end = end
+    if last_end < len(text):
+        tokens.append(("text", text[last_end:], False, False, ""))
+
+    chunks: list[str] = []
+    current_tokens: list[str] = []
+    current_len = 0
+    open_tags: list[tuple[str, str]] = []
+
+    def get_closing_tags() -> str:
+        return "".join(f"</{tag_name}>" for tag_name, _ in reversed(open_tags))
+
+    def get_opening_tags() -> str:
+        return "".join(full_tag for _, full_tag in open_tags)
+
+    def flush_chunk():
+        nonlocal current_tokens, current_len
+        if not current_tokens:
+            return
+        closing = get_closing_tags()
+        if closing:
+            current_tokens.append(closing)
+        chunk_str = "".join(current_tokens).strip()
+        if chunk_str:
+            chunks.append(chunk_str)
+        reopened = get_opening_tags()
+        current_tokens = [reopened] if reopened else []
+        current_len = len(reopened)
+
+    for kind, content, is_closing, is_self_closing, tag_name in tokens:
+        if kind == "tag":
+            overhead = len(get_closing_tags())
+            if current_len + len(content) + overhead > max_chars and current_tokens:
+                flush_chunk()
+
+            current_tokens.append(content)
+            current_len += len(content)
+
+            if not is_self_closing:
+                if is_closing:
+                    for idx in range(len(open_tags) - 1, -1, -1):
+                        if open_tags[idx][0] == tag_name:
+                            open_tags.pop(idx)
+                            break
+                else:
+                    open_tags.append((tag_name, content))
+        else:
+            remaining = content
+            while remaining:
+                overhead = len(get_closing_tags())
+                available = max_chars - current_len - overhead
+                if len(remaining) <= available:
+                    current_tokens.append(remaining)
+                    current_len += len(remaining)
+                    break
+                else:
+                    if available <= 0:
+                        if len(get_opening_tags()) + len(get_closing_tags()) >= max_chars:
+                            raise ValueError(
+                                "max_chars is too small to preserve the open HTML tags"
+                            )
+                        flush_chunk()
+                        continue
+
+                    slice_candidate = remaining[:available]
+                    split_idx = -1
+                    for delim in ["\n\n", "\n", " "]:
+                        pos = slice_candidate.rfind(delim)
+                        if pos > 0:
+                            split_idx = pos + len(delim)
+                            break
+                    if split_idx <= 0:
+                        split_idx = available
+
+                    piece = remaining[:split_idx]
+                    remaining = remaining[split_idx:]
+                    current_tokens.append(piece)
+                    flush_chunk()
+
+    if current_tokens:
+        closing = get_closing_tags()
+        if closing:
+            current_tokens.append(closing)
+        chunk_str = "".join(current_tokens).strip()
+        if chunk_str:
+            chunks.append(chunk_str)
+
+    return chunks

{matplobbot_shared-0.1.330 → matplobbot_shared-0.1.332}/shared_lib/locales/en.json

@@ -157,6 +157,7 @@
     "help_btn_lec_search": "📚 /lec_search - Search notes",
     "help_btn_lec_all": "📂 /lec_all - Browse notes",
     "help_btn_favorites": "⭐ /favorites - Favorites",
+    "help_btn_mail": "✉️ /mail - Mailboxes",
     "help_btn_settings": "⚙️ /settings - Settings",
     "help_btn_latex": "🧮 /latex - Render LaTeX",
     "help_btn_mermaid": "🎨 /mermaid - Render Mermaid",

{matplobbot_shared-0.1.330 → matplobbot_shared-0.1.332}/shared_lib/locales/ru.json

@@ -136,6 +136,7 @@
     "help_btn_lec_search": "📚 /lec_search - Поиск по конспектам",
     "help_btn_lec_all": "📂 /lec_all - Просмотр конспектов",
     "help_btn_favorites": "⭐ /favorites - Избранное",
+    "help_btn_mail": "✉️ /mail - Почтовые ящики",
     "help_btn_settings": "⚙️ /settings - Настройки",
     "help_btn_latex": "🧮 /latex - Рендер LaTeX",
     "help_btn_mermaid": "🎨 /mermaid - Рендер Mermaid",

{matplobbot_shared-0.1.330 → matplobbot_shared-0.1.332}/shared_lib/mail_bridge.py

@@ -13,9 +13,10 @@ from html import escape
 
 from bs4 import BeautifulSoup
 from cryptography.fernet import Fernet
-from sqlalchemy import BigInteger, Boolean, Column, Integer, LargeBinary, String, UniqueConstraint
 
-from shared_lib.models import Base
+from shared_lib.models import MailAccount
+
+__all__ = ["MailAccount", "cipher", "seal", "unseal", "validate_host", "poll_mail", "parse_mail"]
 
 MAX_MAIL_BYTES = 35 * 1024 * 1024
 PASSWORD_PROMPT = "Пароль приложения для почты"
@@ -41,24 +42,6 @@ def sensitive_mail_update(event, data):
     )
 
 
-class MailAccount(Base):
-    __tablename__ = "mail_accounts"
-    __table_args__ = (
-        UniqueConstraint("user_id", "address", "host", name="uq_mail_owner_address_host"),
-    )
-    id = Column(Integer, primary_key=True)
-    user_id = Column(BigInteger, nullable=False, index=True)
-    address = Column(String(320), nullable=False)
-    host = Column(String(253), nullable=False)
-    protocol = Column(String(8), nullable=False)
-    port = Column(Integer, nullable=False, default=993)
-    credential = Column(LargeBinary, nullable=False)
-    enabled = Column(Boolean, nullable=False, default=True)
-    checkpoint = Column(LargeBinary, nullable=False)
-    pending = Column(LargeBinary, nullable=True)
-    status = Column(String(80), nullable=False, default="ready")
-
-
 def cipher():
     return Fernet(os.environ["MAIL_CREDENTIAL_KEY"].encode("ascii"))
 

{matplobbot_shared-0.1.330 → matplobbot_shared-0.1.332}/shared_lib/models.py

@@ -6,6 +6,7 @@ from sqlalchemy import (
     Column,
     DateTime,
     ForeignKey,
+    Index,
     Integer,
     LargeBinary,
     String,
@@ -35,10 +36,14 @@ class UserAction(Base):
     __tablename__ = "user_actions"
 
     id = Column(Integer, primary_key=True, autoincrement=True)
-    user_id = Column(BigInteger, ForeignKey("users.user_id", ondelete="CASCADE"), nullable=False)
-    action_type = Column(String, nullable=False)
+    user_id = Column(
+        BigInteger, ForeignKey("users.user_id", ondelete="CASCADE"), nullable=False, index=True
+    )
+    action_type = Column(String, nullable=False, index=True)
     action_details = Column(String, nullable=True)
-    timestamp = Column(DateTime(timezone=True), server_default=func.now())
+    timestamp = Column(DateTime(timezone=True), server_default=func.now(), index=True)
+
+    __table_args__ = (Index("ix_user_actions_user_id_timestamp", "user_id", "timestamp"),)
 
 
 class UserFavorite(Base):
@@ -75,7 +80,12 @@ class UserScheduleSubscription(Base):
     __tablename__ = "user_schedule_subscriptions"
 
     id = Column(Integer, primary_key=True, autoincrement=True)
-    user_id = Column(BigInteger, ForeignKey("users.user_id", ondelete="CASCADE"), nullable=False)
+    user_id = Column(
+        BigInteger,
+        ForeignKey("users.user_id", ondelete="CASCADE"),
+        nullable=False,
+        index=True,
+    )
     chat_id = Column(BigInteger, nullable=False)
     entity_type = Column(String, nullable=False)
     entity_id = Column(String, nullable=False)
@@ -92,6 +102,11 @@ class UserScheduleSubscription(Base):
         UniqueConstraint(
             "chat_id", "entity_type", "entity_id", "notification_time", name="uq_schedule_subs"
         ),
+        Index(
+            "ix_user_subscriptions_notification_time_active",
+            "notification_time",
+            "is_active",
+        ),
     )
 
 
@@ -129,6 +144,7 @@ class CachedSchedule(Base):
     id = Column(Integer, primary_key=True, autoincrement=True)
     entity_type = Column(String, nullable=False)
     entity_id = Column(String, nullable=False)
+    entity_name = Column(String(255), nullable=True)
     schedule_data = Column(JSONB, nullable=False)
     updated_at = Column(DateTime(timezone=True), server_default=func.now(), onupdate=func.now())
 
@@ -137,6 +153,31 @@ class CachedSchedule(Base):
     )
 
 
+class MailAccount(Base):
+    """Encrypted mailbox connection owned by a Telegram user."""
+
+    __tablename__ = "mail_accounts"
+    __table_args__ = (
+        UniqueConstraint("user_id", "address", "host", name="uq_mail_owner_address_host"),
+    )
+    id = Column(Integer, primary_key=True)
+    user_id = Column(
+        BigInteger,
+        ForeignKey("users.user_id", ondelete="CASCADE"),
+        nullable=False,
+        index=True,
+    )
+    address = Column(String(320), nullable=False)
+    host = Column(String(253), nullable=False)
+    protocol = Column(String(8), nullable=False)
+    port = Column(Integer, nullable=False, default=993)
+    credential = Column(LargeBinary, nullable=False)
+    enabled = Column(Boolean, nullable=False, default=True)
+    checkpoint = Column(LargeBinary, nullable=False)
+    pending = Column(LargeBinary, nullable=True)
+    status = Column(String(80), nullable=False, default="ready")
+
+
 class SearchDocument(Base):
     __tablename__ = "search_documents"
 

{matplobbot_shared-0.1.330 → matplobbot_shared-0.1.332}/shared_lib/redis_client.py

@@ -1,5 +1,6 @@
 import json
 import logging
+import os
 
 import redis.asyncio as redis
 
@@ -67,4 +68,7 @@ class RedisClient:
 
 
 # Создаем единственный экземпляр клиента
-redis_client = RedisClient(host="redis")
+redis_client = RedisClient(
+    host=os.getenv("REDIS_HOST", "redis"),
+    port=int(os.getenv("REDIS_PORT", "6379")),
+)

{matplobbot_shared-0.1.330 → matplobbot_shared-0.1.332}/shared_lib/services/university_api.py

@@ -31,8 +31,10 @@ class RuzAPIClient:
         self.initial_delay = initial_delay
         self.backoff_factor = backoff_factor
 
-    async def _request(self, sub_url: str) -> dict[str, Any] | list[dict[str, Any]]:
-        full_url = self.HOST + sub_url
+    async def _request(
+        self, path: str, params: dict[str, str] | None = None
+    ) -> dict[str, Any] | list[dict[str, Any]]:
+        full_url = self.HOST + path
         ssl_context = ssl.create_default_context(cafile=certifi.where())
         last_exception = None
 
@@ -40,7 +42,10 @@ class RuzAPIClient:
             try:
                 # Добавляем явный таймаут на запрос, чтобы не висеть бесконечно
                 async with self.session.get(
-                    full_url, ssl=ssl_context, timeout=aiohttp.ClientTimeout(total=15)
+                    full_url,
+                    params=params,
+                    ssl=ssl_context,
+                    timeout=aiohttp.ClientTimeout(total=15),
                 ) as response:
                     if response.status == 200:
                         try:
@@ -73,14 +78,17 @@ class RuzAPIClient:
 
     async def search(self, term: str, search_type: str) -> list[dict[str, Any]]:
         """Generic search function."""
-        return await self._request(f"/api/search?term={term}&type={search_type}")
+        return await self._request(
+            "/api/search", params={"term": term, "type": search_type}
+        )
 
     async def get_schedule(
         self, entity_type: str, entity_id: str, start: str, finish: str
     ) -> list[dict[str, Any]]:
         """Generic function to get a schedule."""
         return await self._request(
-            f"/api/schedule/{entity_type}/{entity_id}?start={start}&finish={finish}&lng=1"
+            f"/api/schedule/{entity_type}/{entity_id}",
+            params={"start": start, "finish": finish, "lng": "1"},
         )