Merge branch 'staging' of https://dev.dscrs.site/discours.io/core into feature/auth-internal

.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
@@ -162,5 +165,6 @@ views.json
 *.crt
 *cache.json
 .cursor
+.devcontainer/
 
-node_modules/
+node_modules/

Dockerfile

@@ -3,6 +3,7 @@ FROM python:slim
 RUN apt-get update && apt-get install -y \
     postgresql-client \
     curl \
+    build-essential \
     && rm -rf /var/lib/apt/lists/*
 
 WORKDIR /app

main.py

@@ -21,7 +21,7 @@ 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, initialize_search_index
 
 from utils.logger import root_logger as logger
 from auth.internal import InternalAuthentication
@@ -46,6 +46,15 @@ DIST_DIR = join(os.path.dirname(__file__), "dist")  # Директория дл
 INDEX_HTML = join(os.path.dirname(__file__), "index.html")
 
 
+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}")
+        
+
 async def index_handler(request: Request):
     """
     Раздача основного HTML файла

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"

requirements.txt

@@ -12,6 +12,10 @@ starlette
 gql
 ariadne
 granian
+
+# NLP and search
+httpx
+
 orjson
 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
@@ -97,6 +98,7 @@ __all__ = [
     "get_author_follows_authors",
     "get_authors_all",
     "load_authors_by",
+    "load_authors_search",
     "update_author",
     # "search_authors",
     

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]
@@ -358,6 +359,46 @@ async def load_authors_by(_, info, by, limit, offset):
     return await get_authors_with_stats(limit, offset, by, current_user_id, is_admin)
 
 
+@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

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
 
   # Auth queries
   logout: AuthResult!
@@ -41,6 +41,7 @@ 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

schema/type.graphql

@@ -214,6 +214,7 @@ type CommonResult {
 }
 
 type SearchResult {
+    id: Int!
     slug: String!
     title: String!
     cover: String
@@ -317,3 +318,7 @@ type RolesInfo {
   permissions: [Permission!]!
 }
 
+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
@@ -298,3 +298,32 @@ 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()