feat: follow same logic as search shouts for authors. Store them to Reddis cache + pagination

:

.gitea/workflows/main.yml

@@ -29,7 +29,16 @@ jobs:
         if: github.ref == 'refs/heads/dev'
         uses: dokku/github-action@master
         with:
-          branch: 'dev'
+          branch: 'main'
           force: true
           git_remote_url: 'ssh://dokku@v2.discours.io:22/core'
           ssh_private_key: ${{ secrets.SSH_PRIVATE_KEY }}
+
+      - name: Push to dokku for staging branch
+        if: github.ref == 'refs/heads/staging'
+        uses: dokku/github-action@master
+        with:
+          branch: 'dev'
+          git_remote_url: 'ssh://dokku@staging.discours.io:22/core'
+          ssh_private_key: ${{ secrets.SSH_PRIVATE_KEY }}
+          git_push_flags: '--force'

.gitignore

@@ -128,6 +128,9 @@ dmypy.json
 .idea
 temp.*
 
+# Debug
+DEBUG.log
+
 discours.key
 discours.crt
 discours.pem
@@ -161,4 +164,5 @@ views.json
 *.key
 *.crt
 *cache.json
-.cursor
+.cursor
+.devcontainer/

CHANGELOG.md

@@ -1,9 +1,29 @@
+#### [0.4.19] - 2025-04-14
+- dropped `Shout.description` and `Draft.description` to be UX-generated
+- use redis to init views counters after migrator
+
+#### [0.4.18] - 2025-04-10
+- Fixed `Topic.stat.authors` and `Topic.stat.comments`
+- Fixed unique constraint violation for empty slug values:
+  - Modified `update_draft` resolver to handle empty slug values
+  - Modified `create_draft` resolver to prevent empty slug values
+  - Added validation to prevent inserting or updating drafts with empty slug
+  - Fixed database error "duplicate key value violates unique constraint draft_slug_key"
+
+#### [0.4.17] - 2025-03-26
+- Fixed `'Reaction' object is not subscriptable` error in hierarchical comments:
+  - Modified `get_reactions_with_stat()` to convert Reaction objects to dictionaries
+  - Added default values for limit/offset parameters
+  - Fixed `load_first_replies()` implementation with proper parameter passing
+  - Added doctest with example usage
+  - Limited child comments to 100 per parent for performance
+
 #### [0.4.16] - 2025-03-22
 - Added hierarchical comments pagination:
   - Created new GraphQL query `load_comments_branch` for efficient loading of hierarchical comments
   - Ability to load root comments with their first N replies
   - Added pagination for both root and child comments
-  - Using existing `commented` field in `Stat` type to display number of replies
+  - Using existing `comments_count` field in `Stat` type to display number of replies
   - Added special `first_replies` field to store first replies to a comment
   - Optimized SQL queries for efficient loading of comment hierarchies
   - Implemented flexible comment sorting system (by time, rating)
@@ -41,8 +61,7 @@
   - Implemented persistent Redis caching for author queries without TTL (invalidated only on changes)
   - Optimized author retrieval with separate endpoints:
     - `get_authors_all` - returns all non-deleted authors without statistics
-    - `get_authors_paginated` - returns authors with statistics and pagination support
-    - `load_authors_by` - optimized to use caching and efficient sorting
+    - `load_authors_by` - optimized to use caching and efficient sorting and pagination
   - Improved SQL queries with optimized JOIN conditions and efficient filtering
   - Added pre-aggregation of statistics (shouts count, followers count) in single efficient queries
   - Implemented robust cache invalidation on author updates
@@ -54,7 +73,6 @@
   - Implemented persistent Redis caching for topic queries (no TTL, invalidated only on changes)
   - Optimized topic retrieval with separate endpoints for different use cases:
     - `get_topics_all` - returns all topics without statistics for lightweight listing
-    - `get_topics_paginated` - returns topics with statistics and pagination support
     - `get_topics_by_community` - adds pagination and optimized filtering by community
   - Added SQLAlchemy-managed indexes directly in ORM models for automatic schema maintenance
   - Created `sync_indexes()` function for automatic index synchronization during app startup
@@ -152,7 +170,7 @@
 #### [0.4.4]
 - `followers_stat` removed for shout
 - sqlite3 support added
-- `rating_stat` and `commented_stat` fixes
+- `rating_stat` and `comments_count` fixes
 
 #### [0.4.3]
 - cache reimplemented

app/resolvers/draft.py

@@ -0,0 +1 @@
+ 

cache/cache.py

@@ -545,8 +545,9 @@ async def get_cached_data(key: str) -> Optional[Any]:
     try:
         cached_data = await redis.execute("GET", key)
         if cached_data:
-            logger.debug(f"Данные получены из кеша по ключу {key}")
-            return orjson.loads(cached_data)
+            loaded = orjson.loads(cached_data)
+            logger.debug(f"Данные получены из кеша по ключу {key}: {len(loaded)}")
+            return loaded
         return None
     except Exception as e:
         logger.error(f"Ошибка при получении данных из кеша: {e}")

docs/comments-pagination.md

@@ -45,7 +45,7 @@ query LoadCommentsBranch(
     reply_to
     stat {
       rating
-      commented
+      comments_count
     }
     first_replies {
       id
@@ -61,7 +61,7 @@ query LoadCommentsBranch(
       reply_to
       stat {
         rating
-        commented
+        comments_count
       }
     }
   }
@@ -92,7 +92,7 @@ query LoadCommentsBranch(
 - `reply_to`: ID родительского комментария (null для корневых)
 - `first_replies`: Первые N дочерних комментариев
 - `stat`: Статистика комментария, включающая:
-  - `commented`: Количество ответов на комментарий
+  - `comments_count`: Количество ответов на комментарий
   - `rating`: Рейтинг комментария
 
 ## Примеры использования
@@ -150,7 +150,7 @@ const { data } = await client.query({
 1. Для эффективной работы со сложными ветками обсуждений рекомендуется:
 
    - Сначала загружать только корневые комментарии с первыми N ответами
-   - При наличии дополнительных ответов (когда `stat.commented > first_replies.length`) 
+   - При наличии дополнительных ответов (когда `stat.comments_count > first_replies.length`) 
      добавить кнопку "Показать все ответы"
    - При нажатии на кнопку загружать дополнительные ответы с помощью запроса с указанным `parentId`
 

docs/features.md

@@ -42,7 +42,7 @@
 - Отдельный запрос `load_comments_branch` для оптимизированной загрузки ветки комментариев
 - Возможность загрузки корневых комментариев статьи с первыми ответами на них
 - Гибкая пагинация как для корневых, так и для дочерних комментариев
-- Использование поля `stat.commented` для отображения количества ответов на комментарий
+- Использование поля `stat.comments_count` для отображения количества ответов на комментарий
 - Добавление специального поля `first_replies` для хранения первых ответов на комментарий
 - Поддержка различных методов сортировки (новые, старые, популярные)
 - Оптимизированные SQL запросы для минимизации нагрузки на базу данных

main.py

@@ -17,7 +17,8 @@ from cache.revalidator import revalidation_manager
 from services.exception import ExceptionHandlerMiddleware
 from services.redis import redis
 from services.schema import create_all_tables, resolvers
-from services.search import search_service
+#from services.search import search_service
+from services.search import search_service, initialize_search_index
 from services.viewed import ViewedStorage
 from services.webhook import WebhookEndpoint, create_webhook_endpoint
 from settings import DEV_SERVER_PID_FILE_NAME, MODE
@@ -34,24 +35,67 @@ async def start():
                 f.write(str(os.getpid()))
     print(f"[main] process started in {MODE} mode")
 
+async def check_search_service():
+    """Check if search service is available and log result"""
+    info = await search_service.info()
+    if info.get("status") in ["error", "unavailable"]:
+        print(f"[WARNING] Search service unavailable: {info.get('message', 'unknown reason')}")
+    else:
+        print(f"[INFO] Search service is available: {info}")
 
+
+# indexing DB data
+# async def indexing():
+#     from services.db import fetch_all_shouts
+#     all_shouts = await fetch_all_shouts()
+#     await initialize_search_index(all_shouts)
 async def lifespan(_app):
     try:
+        print("[lifespan] Starting application initialization")
         create_all_tables()
         await asyncio.gather(
             redis.connect(),
             precache_data(),
             ViewedStorage.init(),
             create_webhook_endpoint(),
-            search_service.info(),
+            check_search_service(),
             start(),
             revalidation_manager.start(),
         )
+        print("[lifespan] Basic initialization complete")
+
+        # Add a delay before starting the intensive search indexing
+        print("[lifespan] Waiting for system stabilization before search indexing...")
+        await asyncio.sleep(10)  # 10-second delay to let the system stabilize
+
+        # Start search indexing as a background task with lower priority
+        asyncio.create_task(initialize_search_index_background())
+
         yield
     finally:
+        print("[lifespan] Shutting down application services")
         tasks = [redis.disconnect(), ViewedStorage.stop(), revalidation_manager.stop()]
         await asyncio.gather(*tasks, return_exceptions=True)
+        print("[lifespan] Shutdown complete")
 
+# Initialize search index in the background
+async def initialize_search_index_background():
+    """Run search indexing as a background task with low priority"""
+    try:
+        print("[search] Starting background search indexing process")
+        from services.db import fetch_all_shouts
+        
+        # Get total count first (optional)
+        all_shouts = await fetch_all_shouts()
+        total_count = len(all_shouts) if all_shouts else 0
+        print(f"[search] Fetched {total_count} shouts for background indexing")
+        
+        # Start the indexing process with the fetched shouts
+        print("[search] Beginning background search index initialization...")
+        await initialize_search_index(all_shouts)
+        print("[search] Background search index initialization complete")
+    except Exception as e:
+        print(f"[search] Error in background search indexing: {str(e)}")
 
 # Создаем экземпляр GraphQL
 graphql_app = GraphQL(schema, debug=True)

orm/draft.py

@@ -31,6 +31,7 @@ class Draft(Base):
     # required
     created_at: int = Column(Integer, nullable=False, default=lambda: int(time.time()))
     created_by: int = Column(ForeignKey("author.id"), nullable=False)
+    community: int = Column(ForeignKey("community.id"), nullable=False, default=1)
 
     # optional
     layout: str = Column(String, nullable=True, default="article")
@@ -38,7 +39,6 @@ class Draft(Base):
     title: str = Column(String, nullable=True)
     subtitle: str | None = Column(String, nullable=True)
     lead: str | None = Column(String, nullable=True)
-    description: str | None = Column(String, nullable=True)
     body: str = Column(String, nullable=False, comment="Body")
     media: dict | None = Column(JSON, nullable=True)
     cover: str | None = Column(String, nullable=True, comment="Cover image url")

orm/shout.py

@@ -71,6 +71,34 @@ class ShoutAuthor(Base):
 class Shout(Base):
     """
     Публикация в системе.
+
+    Attributes:
+        body (str)
+        slug (str)
+        cover (str) : "Cover image url"
+        cover_caption (str) : "Cover image alt caption"
+        lead (str) 
+        title (str)
+        subtitle (str)
+        layout (str)
+        media (dict)
+        authors (list[Author])
+        topics (list[Topic])
+        reactions (list[Reaction])
+        lang (str)
+        version_of (int)
+        oid (str)
+        seo (str) : JSON
+        draft (int)
+        created_at (int)
+        updated_at (int)
+        published_at (int)
+        featured_at (int)
+        deleted_at (int)
+        created_by (int)
+        updated_by (int)
+        deleted_by (int)
+        community (int)
     """
 
     __tablename__ = "shout"
@@ -91,7 +119,6 @@ class Shout(Base):
     cover: str | None = Column(String, nullable=True, comment="Cover image url")
     cover_caption: str | None = Column(String, nullable=True, comment="Cover image alt caption")
     lead: str | None = Column(String, nullable=True)
-    description: str | None = Column(String, nullable=True)
     title: str = Column(String, nullable=False)
     subtitle: str | None = Column(String, nullable=True)
     layout: str = Column(String, nullable=False, default="article")

requirements.txt

@@ -13,5 +13,10 @@ starlette
 gql
 ariadne
 granian
+
+# NLP and search
+httpx
+
 orjson
-pydantic
+pydantic
+trafilatura

resolvers/__init__.py

@@ -8,6 +8,7 @@ from resolvers.author import (  # search_authors,
     get_author_id,
     get_authors_all,
     load_authors_by,
+    load_authors_search,
     update_author,
 )
 from resolvers.community import get_communities_all, get_community
@@ -71,6 +72,7 @@ __all__ = [
     "get_author_follows_authors",
     "get_authors_all",
     "load_authors_by",
+    "load_authors_search",
     "update_author",
     ## "search_authors",
     # community

resolvers/author.py

@@ -20,6 +20,7 @@ from services.auth import login_required
 from services.db import local_session
 from services.redis import redis
 from services.schema import mutation, query
+from services.search import search_service
 from utils.logger import root_logger as logger
 
 DEFAULT_COMMUNITIES = [1]
@@ -232,22 +233,6 @@ async def get_authors_all(_, _info):
     return await get_all_authors()
 
 
-@query.field("get_authors_paginated")
-async def get_authors_paginated(_, _info, limit=50, offset=0, by=None):
-    """
-    Получает список авторов с пагинацией и статистикой.
-
-    Args:
-        limit: Максимальное количество возвращаемых авторов
-        offset: Смещение для пагинации
-        by: Параметр сортировки (new/active)
-
-    Returns:
-        list: Список авторов с их статистикой
-    """
-    return await get_authors_with_stats(limit, offset, by)
-
-
 @query.field("get_author")
 async def get_author(_, _info, slug="", author_id=0):
     author_dict = None
@@ -317,6 +302,46 @@ async def load_authors_by(_, _info, by, limit, offset):
     return await get_authors_with_stats(limit, offset, by)
 
 
+@query.field("load_authors_search")
+async def load_authors_search(_, info, text: str, limit: int = 10, offset: int = 0):
+    """
+    Resolver for searching authors by text. Works with txt-ai search endpony.
+    Args:
+        text: Search text
+        limit: Maximum number of authors to return
+        offset: Offset for pagination
+    Returns:
+        list: List of authors matching the search criteria
+    """
+    
+    # Get author IDs from search engine (already sorted by relevance)
+    search_results = await search_service.search_authors(text, limit, offset)
+
+    if not search_results:
+        return []
+
+    author_ids = [result.get("id") for result in search_results if result.get("id")]
+    if not author_ids:
+        return []
+
+    # Fetch full author objects from DB
+    with local_session() as session:
+        # Simple query to get authors by IDs - no need for stats here
+        authors_query = select(Author).filter(Author.id.in_(author_ids))
+        db_authors = session.execute(authors_query).scalars().all()
+    
+    if not db_authors:
+        return []
+
+    # Create a dictionary for quick lookup
+    authors_dict = {str(author.id): author for author in db_authors}
+    
+    # Keep the order from search results (maintains the relevance sorting)
+    ordered_authors = [authors_dict[author_id] for author_id in author_ids if author_id in authors_dict]
+
+    return ordered_authors
+
+
 def get_author_id_from(slug="", user=None, author_id=None):
     try:
         author_id = None

resolvers/draft.py

@@ -1,6 +1,7 @@
 import time
 from operator import or_
 
+import trafilatura
 from sqlalchemy.sql import and_
 
 from cache.cache import (
@@ -30,7 +31,6 @@ def create_shout_from_draft(session, draft, author_id):
         cover=draft.cover,
         cover_caption=draft.cover_caption,
         lead=draft.lead,
-        description=draft.description,
         title=draft.title,
         subtitle=draft.subtitle,
         layout=draft.layout,
@@ -105,12 +105,17 @@ async def create_draft(_, info, draft_input):
     if "title" not in draft_input or not draft_input["title"]:
         draft_input["title"] = ""  # Пустая строка вместо NULL
 
+    # Проверяем slug - он должен быть или не пустым, или не передаваться вообще
+    if "slug" in draft_input and (draft_input["slug"] is None or draft_input["slug"] == ""):
+        # При создании черновика удаляем пустой slug из входных данных
+        del draft_input["slug"]
+
     try:
         with local_session() as session:
             # Remove id from input if present since it's auto-generated
             if "id" in draft_input:
                 del draft_input["id"]
-
+                
             # Добавляем текущее время создания
             draft_input["created_at"] = int(time.time())
 
@@ -122,6 +127,11 @@ async def create_draft(_, info, draft_input):
         logger.error(f"Failed to create draft: {e}", exc_info=True)
         return {"error": f"Failed to create draft: {str(e)}"}
 
+def generate_teaser(body, limit=300):
+    body_text = trafilatura.extract(body, include_comments=False, include_tables=False)
+    body_teaser = ". ".join(body_text[:limit].split(". ")[:-1])
+    return body_teaser
+
 
 @mutation.field("update_draft")
 @login_required
@@ -142,14 +152,65 @@ async def update_draft(_, info, draft_id: int, draft_input):
     if not user_id or not author_id:
         return {"error": "Author ID are required"}
 
+    # Проверяем slug - он должен быть или не пустым, или не передаваться вообще
+    if "slug" in draft_input and (draft_input["slug"] is None or draft_input["slug"] == ""):
+        # Если slug пустой, либо удаляем его из входных данных, либо генерируем временный уникальный
+        # Вариант 1: просто удаляем ключ из входных данных, чтобы оставить старое значение
+        del draft_input["slug"]
+        # Вариант 2 (если нужно обновить): генерируем временный уникальный slug
+        # import uuid
+        # draft_input["slug"] = f"draft-{uuid.uuid4().hex[:8]}"
+
     with local_session() as session:
         draft = session.query(Draft).filter(Draft.id == draft_id).first()
         if not draft:
             return {"error": "Draft not found"}
 
+        # Generate SEO description if not provided and not already set
+        if "seo" not in draft_input and not draft.seo:
+            body_src = draft_input.get("body") if "body" in draft_input else draft.body
+            lead_src = draft_input.get("lead") if "lead" in draft_input else draft.lead
+
+            body_text = None
+            if body_src:
+                try:
+                    # Extract text, excluding comments and tables
+                    body_text = trafilatura.extract(body_src, include_comments=False, include_tables=False)
+                except Exception as e:
+                    logger.warning(f"Trafilatura failed to extract body text for draft {draft_id}: {e}")
+
+            lead_text = None
+            if lead_src:
+                try:
+                    # Extract text from lead
+                    lead_text = trafilatura.extract(lead_src, include_comments=False, include_tables=False)
+                except Exception as e:
+                    logger.warning(f"Trafilatura failed to extract lead text for draft {draft_id}: {e}")
+
+            # Generate body teaser only if body_text was successfully extracted
+            body_teaser = generate_teaser(body_text, 300) if body_text else ""
+
+            # Prioritize lead_text for SEO, fallback to body_teaser. Ensure it's a string.
+            generated_seo = lead_text if lead_text else body_teaser
+            draft_input["seo"] = generated_seo if generated_seo else ""
+
+        # Update the draft object with new data from draft_input
+        # Assuming Draft.update is a helper that iterates keys or similar.
+        # A more standard SQLAlchemy approach would be:
+        # for key, value in draft_input.items():
+        #     if hasattr(draft, key):
+        #         setattr(draft, key, value)
+        # But we stick to the existing pattern for now.
         Draft.update(draft, draft_input)
-        draft.updated_at = int(time.time())
+
+        # Set updated timestamp and author
+        current_time = int(time.time())
+        draft.updated_at = current_time
+        draft.updated_by = author_id # Assuming author_id is correctly fetched context
+
         session.commit()
+        # Invalidate cache related to this draft if necessary (consider adding)
+        # await invalidate_draft_cache(draft_id)
         return {"draft": draft}
 
 
@@ -249,7 +310,6 @@ async def publish_shout(_, info, shout_id: int):
                 shout.cover = draft.cover
                 shout.cover_caption = draft.cover_caption
                 shout.lead = draft.lead
-                shout.description = draft.description
                 shout.layout = draft.layout
                 shout.media = draft.media
                 shout.lang = draft.lang

resolvers/editor.py

@@ -1,6 +1,7 @@
 import time
 
 import orjson
+import trafilatura
 from sqlalchemy import and_, desc, select
 from sqlalchemy.orm import joinedload
 from sqlalchemy.sql.functions import coalesce
@@ -176,9 +177,16 @@ async def create_shout(_, info, inp):
 
                 logger.info(f"Creating shout with input: {inp}")
                 # Создаем публикацию без topics
+                body = inp.get("body", "")
+                lead = inp.get("lead", "")
+                body_text = trafilatura.extract(body)
+                lead_text = trafilatura.extract(lead)
+                seo = inp.get("seo", lead_text or body_text[:300].split(". ")[:-1].join(". "))
                 new_shout = Shout(
                     slug=slug,
-                    body=inp.get("body", ""),
+                    body=body,
+                    seo=seo,
+                    lead=lead,
                     layout=inp.get("layout", "article"),
                     title=inp.get("title", ""),
                     created_by=author_id,
@@ -380,7 +388,7 @@ def patch_topics(session, shout, topics_input):
 # @login_required
 async def update_shout(_, info, shout_id: int, shout_input=None, publish=False):
     logger.info(f"Starting update_shout with id={shout_id}, publish={publish}")
-    logger.debug(f"Full shout_input: {shout_input}")
+    logger.debug(f"Full shout_input: {shout_input}")  # DraftInput
 
     user_id = info.context.get("user_id")
     roles = info.context.get("roles", [])

resolvers/reaction.py

@@ -67,30 +67,35 @@ def add_reaction_stat_columns(q):
     return q
 
 
-def get_reactions_with_stat(q, limit, offset):
+def get_reactions_with_stat(q, limit=10, offset=0):
     """
     Execute the reaction query and retrieve reactions with statistics.
 
     :param q: Query with reactions and statistics.
     :param limit: Number of reactions to load.
     :param offset: Pagination offset.
-    :return: List of reactions.
+    :return: List of reactions as dictionaries.
+
+    >>> get_reactions_with_stat(q, 10, 0)  # doctest: +SKIP
+    [{'id': 1, 'body': 'Текст комментария', 'stat': {'rating': 5, 'comments_count': 3}, ...}]
     """
     q = q.limit(limit).offset(offset)
     reactions = []
 
     with local_session() as session:
         result_rows = session.execute(q)
-        for reaction, author, shout, commented_stat, rating_stat in result_rows:
+        for reaction, author, shout, comments_count, rating_stat in result_rows:
             # Пропускаем реакции с отсутствующими shout или author
             if not shout or not author:
                 logger.error(f"Пропущена реакция из-за отсутствия shout или author: {reaction.dict()}")
                 continue
 
-            reaction.created_by = author.dict()
-            reaction.shout = shout.dict()
-            reaction.stat = {"rating": rating_stat, "comments": commented_stat}
-            reactions.append(reaction)
+            # Преобразуем Reaction в словарь для доступа по ключу
+            reaction_dict = reaction.dict()
+            reaction_dict["created_by"] = author.dict()
+            reaction_dict["shout"] = shout.dict()
+            reaction_dict["stat"] = {"rating": rating_stat, "comments_count": comments_count}
+            reactions.append(reaction_dict)
 
     return reactions
 
@@ -393,7 +398,7 @@ async def update_reaction(_, info, reaction):
 
             result = session.execute(reaction_query).unique().first()
             if result:
-                r, author, _shout, commented_stat, rating_stat = result
+                r, author, _shout, comments_count, rating_stat = result
                 if not r or not author:
                     return {"error": "Invalid reaction ID or unauthorized"}
 
@@ -408,7 +413,7 @@ async def update_reaction(_, info, reaction):
                 session.commit()
 
                 r.stat = {
-                    "commented": commented_stat,
+                    "comments_count": comments_count,
                     "rating": rating_stat,
                 }
 
@@ -713,7 +718,7 @@ async def load_comments_branch(
 
 async def load_replies_count(comments):
     """
-    Загружает количество ответов для списка комментариев и обновляет поле stat.commented.
+    Загружает количество ответов для списка комментариев и обновляет поле stat.comments_count.
 
     :param comments: Список комментариев, для которых нужно загрузить количество ответов.
     """
@@ -748,7 +753,7 @@ async def load_replies_count(comments):
             comment["stat"] = {}
 
         # Обновляем счетчик комментариев в stat
-        comment["stat"]["commented"] = replies_count.get(comment["id"], 0)
+        comment["stat"]["comments_count"] = replies_count.get(comment["id"], 0)
 
 
 async def load_first_replies(comments, limit, offset, sort="newest"):
@@ -793,8 +798,9 @@ async def load_first_replies(comments, limit, offset, sort="newest"):
 
     q = q.order_by(order_by_stmt, Reaction.reply_to)
 
-    # Выполняем запрос
-    replies = get_reactions_with_stat(q)
+    # Выполняем запрос - указываем limit для неограниченного количества ответов
+    # но не более 100 на родительский комментарий
+    replies = get_reactions_with_stat(q, limit=100, offset=0)
 
     # Группируем ответы по родительским ID
     replies_by_parent = {}

resolvers/reader.py

@@ -10,7 +10,7 @@ from orm.shout import Shout, ShoutAuthor, ShoutTopic
 from orm.topic import Topic
 from services.db import json_array_builder, json_builder, local_session
 from services.schema import query
-from services.search import search_text
+from services.search import search_text, get_search_count
 from services.viewed import ViewedStorage
 from utils.logger import root_logger as logger
 
@@ -187,12 +187,10 @@ def get_shouts_with_links(info, q, limit=20, offset=0):
     """
     shouts = []
     try:
-        # logger.info(f"Starting get_shouts_with_links with limit={limit}, offset={offset}")
         q = q.limit(limit).offset(offset)
 
         with local_session() as session:
             shouts_result = session.execute(q).all()
-            # logger.info(f"Got {len(shouts_result) if shouts_result else 0} shouts from query")
 
             if not shouts_result:
                 logger.warning("No shouts found in query result")
@@ -203,7 +201,6 @@ def get_shouts_with_links(info, q, limit=20, offset=0):
                     shout = None
                     if hasattr(row, "Shout"):
                         shout = row.Shout
-                        # logger.debug(f"Processing shout#{shout.id} at index {idx}")
                     if shout:
                         shout_id = int(f"{shout.id}")
                         shout_dict = shout.dict()
@@ -225,26 +222,22 @@ def get_shouts_with_links(info, q, limit=20, offset=0):
                             elif isinstance(row.stat, dict):
                                 stat = row.stat
                             viewed = ViewedStorage.get_shout(shout_id=shout_id) or 0
-                            shout_dict["stat"] = {**stat, "viewed": viewed, "commented": stat.get("comments_count", 0)}
+                            shout_dict["stat"] = {**stat, "viewed": viewed}
 
                         # Обработка main_topic и topics
                         topics = None
                         if has_field(info, "topics") and hasattr(row, "topics"):
                             topics = orjson.loads(row.topics) if isinstance(row.topics, str) else row.topics
-                            # logger.debug(f"Shout#{shout_id} topics: {topics}")
                             shout_dict["topics"] = topics
 
                         if has_field(info, "main_topic"):
                             main_topic = None
                             if hasattr(row, "main_topic"):
-                                # logger.debug(f"Raw main_topic for shout#{shout_id}: {row.main_topic}")
                                 main_topic = (
                                     orjson.loads(row.main_topic) if isinstance(row.main_topic, str) else row.main_topic
                                 )
-                                # logger.debug(f"Parsed main_topic for shout#{shout_id}: {main_topic}")
 
                             if not main_topic and topics and len(topics) > 0:
-                                # logger.info(f"No main_topic found for shout#{shout_id}, using first topic from list")
                                 main_topic = {
                                     "id": topics[0]["id"],
                                     "title": topics[0]["title"],
@@ -252,10 +245,8 @@ def get_shouts_with_links(info, q, limit=20, offset=0):
                                     "is_main": True,
                                 }
                             elif not main_topic:
-                                logger.warning(f"No main_topic and no topics found for shout#{shout_id}")
                                 main_topic = {"id": 0, "title": "no topic", "slug": "notopic", "is_main": True}
                             shout_dict["main_topic"] = main_topic
-                            # logger.debug(f"Final main_topic for shout#{shout_id}: {main_topic}")
 
                         if has_field(info, "authors") and hasattr(row, "authors"):
                             shout_dict["authors"] = (
@@ -282,7 +273,6 @@ def get_shouts_with_links(info, q, limit=20, offset=0):
         logger.error(f"Fatal error in get_shouts_with_links: {e}", exc_info=True)
         raise
     finally:
-        logger.info(f"Returning {len(shouts)} shouts from get_shouts_with_links")
         return shouts
 
 
@@ -401,33 +391,49 @@ async def load_shouts_search(_, info, text, options):
     """
     limit = options.get("limit", 10)
     offset = options.get("offset", 0)
+    
     if isinstance(text, str) and len(text) > 2:
+        # Get search results with pagination
         results = await search_text(text, limit, offset)
-        scores = {}
-        hits_ids = []
-        for sr in results:
-            shout_id = sr.get("id")
-            if shout_id:
-                shout_id = str(shout_id)
-                scores[shout_id] = sr.get("score")
-                hits_ids.append(shout_id)
+        
+        if not results:
+            logger.info(f"No search results found for '{text}'")
+            return []
+        
+        # Extract IDs in the order from the search engine
+        hits_ids = [str(sr.get("id")) for sr in results if sr.get("id")]
 
-        q = (
-            query_with_stat(info)
-            if has_field(info, "stat")
-            else select(Shout).filter(and_(Shout.published_at.is_not(None), Shout.deleted_at.is_(None)))
-        )
+        # Query DB for only the IDs in the current page
+        q = query_with_stat(info)
         q = q.filter(Shout.id.in_(hits_ids))
-        q = apply_filters(q, options)
-        q = apply_sorting(q, options)
-        shouts = get_shouts_with_links(info, q, limit, offset)
-        for shout in shouts:
-            shout.score = scores[f"{shout.id}"]
-        shouts.sort(key=lambda x: x.score, reverse=True)
-        return shouts
+        q = apply_filters(q, options.get("filters", {}))
+
+        shouts = get_shouts_with_links(info, q, len(hits_ids), 0)
+
+        # Reorder shouts to match the order from hits_ids
+        shouts_dict = {str(shout['id']): shout for shout in shouts}
+        ordered_shouts = [shouts_dict[shout_id] for shout_id in hits_ids if shout_id in shouts_dict]
+
+        return ordered_shouts
     return []
 
 
+@query.field("get_search_results_count")
+async def get_search_results_count(_, info, text):
+    """
+    Returns the total count of search results for a search query.
+    
+    :param _: Root query object (unused)
+    :param info: GraphQL context information
+    :param text: Search query text
+    :return: Total count of results
+    """
+    if isinstance(text, str) and len(text) > 2:
+        count = await get_search_count(text)
+        return {"count": count}
+    return {"count": 0}
+
+
 @query.field("load_shouts_unrated")
 async def load_shouts_unrated(_, info, options):
     """

resolvers/topic.py

@@ -127,6 +127,28 @@ async def get_topics_with_stats(limit=100, offset=0, community_id=None, by=None)
             """
             followers_stats = {row[0]: row[1] for row in session.execute(text(followers_stats_query))}
 
+            # Запрос на получение статистики авторов для выбранных тем
+            authors_stats_query = f"""
+            SELECT st.topic, COUNT(DISTINCT sa.author) as authors_count
+            FROM shout_topic st
+            JOIN shout s ON st.shout = s.id AND s.deleted_at IS NULL AND s.published_at IS NOT NULL
+            JOIN shout_author sa ON sa.shout = s.id
+            WHERE st.topic IN ({",".join(map(str, topic_ids))})
+            GROUP BY st.topic
+            """
+            authors_stats = {row[0]: row[1] for row in session.execute(text(authors_stats_query))}
+
+            # Запрос на получение статистики комментариев для выбранных тем
+            comments_stats_query = f"""
+            SELECT st.topic, COUNT(DISTINCT r.id) as comments_count
+            FROM shout_topic st
+            JOIN shout s ON st.shout = s.id AND s.deleted_at IS NULL AND s.published_at IS NOT NULL
+            JOIN reaction r ON r.shout = s.id
+            WHERE st.topic IN ({",".join(map(str, topic_ids))})
+            GROUP BY st.topic
+            """
+            comments_stats = {row[0]: row[1] for row in session.execute(text(comments_stats_query))}
+
             # Формируем результат с добавлением статистики
             result = []
             for topic in topics:
@@ -134,6 +156,8 @@ async def get_topics_with_stats(limit=100, offset=0, community_id=None, by=None)
                 topic_dict["stat"] = {
                     "shouts": shouts_stats.get(topic.id, 0),
                     "followers": followers_stats.get(topic.id, 0),
+                    "authors": authors_stats.get(topic.id, 0),
+                    "comments": comments_stats.get(topic.id, 0),
                 }
                 result.append(topic_dict)
 
@@ -202,23 +226,6 @@ async def get_topics_all(_, _info):
     return await get_all_topics()
 
 
-# Запрос на получение тем с пагинацией и статистикой
-@query.field("get_topics_paginated")
-async def get_topics_paginated(_, _info, limit=100, offset=0, by=None):
-    """
-    Получает список тем с пагинацией и статистикой.
-
-    Args:
-        limit: Максимальное количество возвращаемых тем
-        offset: Смещение для пагинации
-        by: Опциональные параметры сортировки
-
-    Returns:
-        list: Список тем с их статистикой
-    """
-    return await get_topics_with_stats(limit, offset, None, by)
-
-
 # Запрос на получение тем по сообществу
 @query.field("get_topics_by_community")
 async def get_topics_by_community(_, _info, community_id: int, limit=100, offset=0, by=None):

schema/input.graphql

@@ -33,7 +33,6 @@ input DraftInput {
   main_topic_id: Int  # Changed from main_topic: Topic
   media: [MediaItemInput]  # Changed to use MediaItemInput
   lead: String
-  description: String
   subtitle: String
   lang: String
   seo: String

schema/query.graphql

@@ -4,7 +4,7 @@ type Query {
   get_author_id(user: String!): Author
   get_authors_all: [Author]
   load_authors_by(by: AuthorsBy!, limit: Int, offset: Int): [Author]
-  # search_authors(what: String!): [Author]
+  load_authors_search(text: String!, limit: Int, offset: Int): [Author!] # Search for authors by name or bio
 
   # community
   get_community: Community
@@ -33,6 +33,7 @@ type Query {
   get_shout(slug: String, shout_id: Int): Shout
   load_shouts_by(options: LoadShoutsOptions): [Shout]
   load_shouts_search(text: String!, options: LoadShoutsOptions): [SearchResult]
+  get_search_results_count(text: String!): CountResult!
   load_shouts_bookmarked(options: LoadShoutsOptions): [Shout]
 
   # rating
@@ -60,7 +61,7 @@ type Query {
   get_topic(slug: String!): Topic
   get_topics_all: [Topic]
   get_topics_by_author(slug: String, user: String, author_id: Int): [Topic]
-  get_topics_by_community(slug: String, community_id: Int): [Topic]
+  get_topics_by_community(community_id: Int!, limit: Int, offset: Int): [Topic]
 
   # notifier
   load_notifications(after: Int!, limit: Int, offset: Int): NotificationsResult!

schema/type.graphql

@@ -80,7 +80,6 @@ type Shout {
   layout: String!
 
   lead: String
-  description: String
   subtitle: String
   lang: String
   cover: String
@@ -100,6 +99,7 @@ type Shout {
   featured_at: Int
   deleted_at: Int
 
+  seo: String # generated if not set
   version_of: Shout  # TODO: use version_of somewhere
   draft: Draft
   media: [MediaItem]
@@ -111,13 +111,12 @@ type Draft {
   id: Int!
   created_at: Int!
   created_by: Author!
-
+  community: Community!
   layout: String
   slug: String
   title: String
   subtitle: String
   lead: String
-  description: String
   body: String
   media: [MediaItem]
   cover: String
@@ -137,7 +136,7 @@ type Draft {
 
 type Stat {
   rating: Int
-  commented: Int
+  comments_count: Int
   viewed: Int
   last_commented_at: Int
 }
@@ -208,6 +207,7 @@ type CommonResult {
 }
 
 type SearchResult {
+    id: Int!
     slug: String!
     title: String!
     cover: String
@@ -275,3 +275,7 @@ type MyRateComment {
   my_rate: ReactionKind
 }
 
+type CountResult {
+  count: Int!
+}
+

services/db.py

@@ -19,7 +19,7 @@ from sqlalchemy import (
     inspect,
     text,
 )
-from sqlalchemy.orm import Session, configure_mappers, declarative_base
+from sqlalchemy.orm import Session, configure_mappers, declarative_base, joinedload
 from sqlalchemy.sql.schema import Table
 
 from settings import DB_URL
@@ -259,3 +259,32 @@ def get_json_builder():
 
 # Используем их в коде
 json_builder, json_array_builder, json_cast = get_json_builder()
+
+# Fetch all shouts, with authors preloaded
+# This function is used for search indexing
+
+async def fetch_all_shouts(session=None):
+    """Fetch all published shouts for search indexing with authors preloaded"""
+    from orm.shout import Shout
+    
+    close_session = False
+    if session is None:
+        session = local_session()
+        close_session = True
+    
+    try:
+        # Fetch only published and non-deleted shouts with authors preloaded
+        query = session.query(Shout).options(
+            joinedload(Shout.authors)
+        ).filter(
+            Shout.published_at.is_not(None),
+            Shout.deleted_at.is_(None)
+        )
+        shouts = query.all()
+        return shouts
+    except Exception as e:
+        logger.error(f"Error fetching shouts for search indexing: {e}")
+        return []
+    finally:
+        if close_session:
+            session.close()

services/viewed.py

@@ -2,9 +2,7 @@ import asyncio
 import os
 import time
 from datetime import datetime, timedelta, timezone
-from typing import Dict
-
-import orjson
+from typing import Dict, Optional
 
 # ga
 from google.analytics.data_v1beta import BetaAnalyticsDataClient
@@ -20,33 +18,39 @@ from orm.author import Author
 from orm.shout import Shout, ShoutAuthor, ShoutTopic
 from orm.topic import Topic
 from services.db import local_session
+from services.redis import redis
 from utils.logger import root_logger as logger
 
 GOOGLE_KEYFILE_PATH = os.environ.get("GOOGLE_KEYFILE_PATH", "/dump/google-service.json")
 GOOGLE_PROPERTY_ID = os.environ.get("GOOGLE_PROPERTY_ID", "")
-VIEWS_FILEPATH = "/dump/views.json"
 
 
 class ViewedStorage:
+    """
+    Класс для хранения и доступа к данным о просмотрах.
+    Использует Redis в качестве основного хранилища и Google Analytics для сбора новых данных.
+    """
+
     lock = asyncio.Lock()
-    precounted_by_slug = {}
     views_by_shout = {}
     shouts_by_topic = {}
     shouts_by_author = {}
     views = None
     period = 60 * 60  # каждый час
-    analytics_client: BetaAnalyticsDataClient | None = None
+    analytics_client: Optional[BetaAnalyticsDataClient] = None
     auth_result = None
     running = False
+    redis_views_key = None
+    last_update_timestamp = 0
     start_date = datetime.now().strftime("%Y-%m-%d")
 
     @staticmethod
     async def init():
-        """Подключение к клиенту Google Analytics с использованием аутентификации"""
+        """Подключение к клиенту Google Analytics и загрузка данных о просмотрах из Redis"""
         self = ViewedStorage
         async with self.lock:
-            # Загрузка предварительно подсчитанных просмотров из файла JSON
-            self.load_precounted_views()
+            # Загрузка предварительно подсчитанных просмотров из Redis
+            await self.load_views_from_redis()
 
             os.environ.setdefault("GOOGLE_APPLICATION_CREDENTIALS", GOOGLE_KEYFILE_PATH)
             if GOOGLE_KEYFILE_PATH and os.path.isfile(GOOGLE_KEYFILE_PATH):
@@ -62,40 +66,54 @@ class ViewedStorage:
                 self.running = False
 
     @staticmethod
-    def load_precounted_views():
-        """Загрузка предварительно подсчитанных просмотров из файла JSON"""
+    async def load_views_from_redis():
+        """Загрузка предварительно подсчитанных просмотров из Redis"""
         self = ViewedStorage
-        viewfile_path = VIEWS_FILEPATH
-        if not os.path.exists(viewfile_path):
-            viewfile_path = os.path.join(os.path.curdir, "views.json")
-            if not os.path.exists(viewfile_path):
-                logger.warning(" * views.json not found")
-                return
 
-        logger.info(f" * loading views from {viewfile_path}")
-        try:
-            start_date_int = os.path.getmtime(viewfile_path)
-            start_date_str = datetime.fromtimestamp(start_date_int).strftime("%Y-%m-%d")
-            self.start_date = start_date_str
+        # Подключаемся к Redis если соединение не установлено
+        if not redis._client:
+            await redis.connect()
+
+        # Получаем список всех ключей migrated_views_* и находим самый последний
+        keys = await redis.execute("KEYS", "migrated_views_*")
+        if not keys:
+            logger.warning(" * No migrated_views keys found in Redis")
+            return
+
+        # Фильтруем только ключи timestamp формата (исключаем migrated_views_slugs)
+        timestamp_keys = [k for k in keys if k != "migrated_views_slugs"]
+        if not timestamp_keys:
+            logger.warning(" * No migrated_views timestamp keys found in Redis")
+            return
+
+        # Сортируем по времени создания (в названии ключа) и берем последний
+        timestamp_keys.sort()
+        latest_key = timestamp_keys[-1]
+        self.redis_views_key = latest_key
+
+        # Получаем метку времени создания для установки start_date
+        timestamp = await redis.execute("HGET", latest_key, "_timestamp")
+        if timestamp:
+            self.last_update_timestamp = int(timestamp)
+            timestamp_dt = datetime.fromtimestamp(int(timestamp))
+            self.start_date = timestamp_dt.strftime("%Y-%m-%d")
+
+            # Если данные сегодняшние, считаем их актуальными
             now_date = datetime.now().strftime("%Y-%m-%d")
-
             if now_date == self.start_date:
-                logger.info(" * views data is up to date!")
+                logger.info(" * Views data is up to date!")
             else:
-                logger.warn(f" * {viewfile_path} is too old: {self.start_date}")
+                logger.warning(f" * Views data is from {self.start_date}, may need update")
 
-            with open(viewfile_path, "r") as file:
-                precounted_views = orjson.loads(file.read())
-                self.precounted_by_slug.update(precounted_views)
-                logger.info(f" * {len(precounted_views)} shouts with views was loaded.")
-
-        except Exception as e:
-            logger.error(f"precounted views loading error: {e}")
+        # Выводим информацию о количестве загруженных записей
+        total_entries = await redis.execute("HGET", latest_key, "_total")
+        if total_entries:
+            logger.info(f" * {total_entries} shouts with views loaded from Redis key: {latest_key}")
 
     # noinspection PyTypeChecker
     @staticmethod
     async def update_pages():
-        """Запрос всех страниц от Google Analytics, отсортрованных по количеству просмотров"""
+        """Запрос всех страниц от Google Analytics, отсортированных по количеству просмотров"""
         self = ViewedStorage
         logger.info(" ⎧ views update from Google Analytics ---")
         if self.running:
@@ -140,15 +158,40 @@ class ViewedStorage:
                 self.running = False
 
     @staticmethod
-    def get_shout(shout_slug="", shout_id=0) -> int:
-        """Получение метрики просмотров shout по slug или id."""
+    async def get_shout(shout_slug="", shout_id=0) -> int:
+        """
+        Получение метрики просмотров shout по slug или id.
+
+        Args:
+            shout_slug: Slug публикации
+            shout_id: ID публикации
+
+        Returns:
+            int: Количество просмотров
+        """
         self = ViewedStorage
+
+        # Получаем данные из Redis для новой схемы хранения
+        if not redis._client:
+            await redis.connect()
+
         fresh_views = self.views_by_shout.get(shout_slug, 0)
-        precounted_views = self.precounted_by_slug.get(shout_slug, 0)
-        return fresh_views + precounted_views
+
+        # Если есть id, пытаемся получить данные из Redis по ключу migrated_views_<timestamp>
+        if shout_id and self.redis_views_key:
+            precounted_views = await redis.execute("HGET", self.redis_views_key, str(shout_id))
+            if precounted_views:
+                return fresh_views + int(precounted_views)
+
+        # Если нет id или данных, пытаемся получить по slug из отдельного хеша
+        precounted_views = await redis.execute("HGET", "migrated_views_slugs", shout_slug)
+        if precounted_views:
+            return fresh_views + int(precounted_views)
+
+        return fresh_views
 
     @staticmethod
-    def get_shout_media(shout_slug) -> Dict[str, int]:
+    async def get_shout_media(shout_slug) -> Dict[str, int]:
         """Получение метрики воспроизведения shout по slug."""
         self = ViewedStorage
 
@@ -157,23 +200,29 @@ class ViewedStorage:
         return self.views_by_shout.get(shout_slug, 0)
 
     @staticmethod
-    def get_topic(topic_slug) -> int:
+    async def get_topic(topic_slug) -> int:
         """Получение суммарного значения просмотров темы."""
         self = ViewedStorage
-        return sum(self.views_by_shout.get(shout_slug, 0) for shout_slug in self.shouts_by_topic.get(topic_slug, []))
+        views_count = 0
+        for shout_slug in self.shouts_by_topic.get(topic_slug, []):
+            views_count += await self.get_shout(shout_slug=shout_slug)
+        return views_count
 
     @staticmethod
-    def get_author(author_slug) -> int:
+    async def get_author(author_slug) -> int:
         """Получение суммарного значения просмотров автора."""
         self = ViewedStorage
-        return sum(self.views_by_shout.get(shout_slug, 0) for shout_slug in self.shouts_by_author.get(author_slug, []))
+        views_count = 0
+        for shout_slug in self.shouts_by_author.get(author_slug, []):
+            views_count += await self.get_shout(shout_slug=shout_slug)
+        return views_count
 
     @staticmethod
     def update_topics(shout_slug):
         """Обновление счетчиков темы по slug shout"""
         self = ViewedStorage
         with local_session() as session:
-            # Определение вспомогательной функции для избежа<EFBFBD><EFBFBD>ия повторения кода
+            # Определение вспомогательной функции для избежания повторения кода
             def update_groups(dictionary, key, value):
                 dictionary[key] = list(set(dictionary.get(key, []) + [value]))