feat: initial microservices project structure

Services:
- api: FastAPI gateway with JWT auth, async endpoints, WebSocket
- worker-gpu: CUDA sentence-transformers, FAISS IVFFlat, Ollama LLM
- worker-indexer: Winnowing+MinHash plagiarism detection, PDF/DOCX extraction
- worker-notifier: SMTP email notifications
- worker-gost: GOST 7.1-2003 and GOST R 7.0.5-2008 formatting

Infrastructure:
- docker-compose.yml (production) + docker-compose.dev.yml (hot reload)
- Nginx reverse proxy + WebSocket support
- PostgreSQL 16 with Alembic migrations
- Elasticsearch 8 with Russian/English analyzers
- MinIO, RabbitMQ, Redis, Ollama

Frontend:
- React 18 + Vite + TypeScript + TailwindCSS + Zustand + React Query v5
- 9 pages: Home, Search, Cabinet, Task, Check, Bibliography, Pricing, Login, Register

Scripts:
- Parser stubs: OpenAlex, КиберЛенинка, arXiv (Phase 0 - to be filled)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
jze9
2026-05-24 19:42:39 +05:00
commit 7758315632
120 changed files with 9500 additions and 0 deletions

View File

@@ -0,0 +1,75 @@
{
"settings": {
"number_of_shards": 1,
"number_of_replicas": 0,
"analysis": {
"analyzer": {
"russian_analyzer": {
"type": "custom",
"tokenizer": "standard",
"filter": ["lowercase", "russian_stop", "russian_stemmer"]
},
"english_analyzer": {
"type": "custom",
"tokenizer": "standard",
"filter": ["lowercase", "english_stop", "english_stemmer"]
},
"multilingual_analyzer": {
"type": "custom",
"tokenizer": "standard",
"filter": ["lowercase", "russian_stop", "russian_stemmer", "english_stop"]
}
},
"filter": {
"russian_stop": {
"type": "stop",
"stopwords": "_russian_"
},
"russian_stemmer": {
"type": "stemmer",
"language": "russian"
},
"english_stop": {
"type": "stop",
"stopwords": "_english_"
},
"english_stemmer": {
"type": "stemmer",
"language": "english"
}
}
}
},
"mappings": {
"properties": {
"doc_id": {"type": "long"},
"source": {"type": "keyword"},
"title": {
"type": "text",
"analyzer": "multilingual_analyzer",
"fields": {
"keyword": {"type": "keyword", "ignore_above": 512},
"ru": {"type": "text", "analyzer": "russian_analyzer"},
"en": {"type": "text", "analyzer": "english_analyzer"}
}
},
"abstract": {
"type": "text",
"analyzer": "multilingual_analyzer",
"fields": {
"ru": {"type": "text", "analyzer": "russian_analyzer"},
"en": {"type": "text", "analyzer": "english_analyzer"}
}
},
"authors": {
"type": "text",
"analyzer": "multilingual_analyzer"
},
"year": {"type": "integer"},
"lang": {"type": "keyword"},
"journal": {"type": "keyword", "ignore_above": 512},
"doi": {"type": "keyword"},
"url": {"type": "keyword", "index": false}
}
}
}

36
infra/elasticsearch/setup.sh Executable file
View File

@@ -0,0 +1,36 @@
#!/bin/bash
# Создание ES индекса с маппингом для документов
# Запускать после старта контейнера Elasticsearch
set -e
ES_URL="${ELASTICSEARCH_URL:-http://localhost:9200}"
INDEX_NAME="documents"
MAPPINGS_FILE="$(dirname "$0")/mappings.json"
echo "Ожидание готовности Elasticsearch..."
until curl -s "$ES_URL/_cluster/health" | grep -qv '"status":"red"'; do
sleep 2
done
echo "Elasticsearch готов."
# Проверить существование индекса
if curl -s -o /dev/null -w "%{http_code}" "$ES_URL/$INDEX_NAME" | grep -q "200"; then
echo "Индекс '$INDEX_NAME' уже существует."
read -p "Пересоздать? (y/N): " confirm
if [[ $confirm != "y" ]]; then
echo "Пропускаем."
exit 0
fi
echo "Удаление старого индекса..."
curl -s -X DELETE "$ES_URL/$INDEX_NAME"
echo ""
fi
echo "Создание индекса '$INDEX_NAME'..."
curl -s -X PUT "$ES_URL/$INDEX_NAME" \
-H "Content-Type: application/json" \
-d @"$MAPPINGS_FILE" | python3 -m json.tool
echo ""
echo "Индекс '$INDEX_NAME' создан."

113
infra/nginx/nginx.conf Normal file
View File

@@ -0,0 +1,113 @@
# Nginx конфиг для academic.jze9.ru
# Продакшн: SSL + proxy to FastAPI + React static
user nginx;
worker_processes auto;
error_log /var/log/nginx/error.log warn;
pid /var/run/nginx.pid;
events {
worker_connections 1024;
}
http {
include /etc/nginx/mime.types;
default_type application/octet-stream;
# Логи
log_format main '$remote_addr - $remote_user [$time_local] "$request" '
'$status $body_bytes_sent "$http_referer" '
'"$http_user_agent"';
access_log /var/log/nginx/access.log main;
sendfile on;
tcp_nopush on;
keepalive_timeout 65;
# Gzip
gzip on;
gzip_types text/plain text/css application/json application/javascript text/xml application/xml;
gzip_min_length 1024;
gzip_vary on;
# Лимиты
client_max_body_size 100M;
proxy_read_timeout 300s;
proxy_connect_timeout 30s;
proxy_send_timeout 300s;
# Upstream
upstream api {
server api:8000;
keepalive 32;
}
# HTTP → HTTPS редирект
server {
listen 80;
server_name academic.jze9.ru;
return 301 https://$server_name$request_uri;
}
# HTTPS основной сервер
server {
listen 443 ssl http2;
server_name academic.jze9.ru;
# SSL (Let's Encrypt)
ssl_certificate /etc/letsencrypt/live/academic.jze9.ru/fullchain.pem;
ssl_certificate_key /etc/letsencrypt/live/academic.jze9.ru/privkey.pem;
ssl_protocols TLSv1.2 TLSv1.3;
ssl_ciphers ECDHE-ECDSA-AES128-GCM-SHA256:ECDHE-RSA-AES128-GCM-SHA256:ECDHE-ECDSA-AES256-GCM-SHA384:ECDHE-RSA-AES256-GCM-SHA384;
ssl_prefer_server_ciphers off;
ssl_session_cache shared:SSL:10m;
ssl_session_timeout 1d;
# HSTS
add_header Strict-Transport-Security "max-age=63072000" always;
# Security headers
add_header X-Content-Type-Options nosniff;
add_header X-Frame-Options DENY;
add_header X-XSS-Protection "1; mode=block";
# ── API proxy ──────────────────────────────────────────────────────────
location /api/ {
proxy_pass http://api/api/;
proxy_http_version 1.1;
proxy_set_header Host $host;
proxy_set_header X-Real-IP $remote_addr;
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
proxy_set_header X-Forwarded-Proto $scheme;
proxy_set_header Connection "";
}
# ── WebSocket ──────────────────────────────────────────────────────────
location /ws/ {
proxy_pass http://api/ws/;
proxy_http_version 1.1;
proxy_set_header Upgrade $http_upgrade;
proxy_set_header Connection "upgrade";
proxy_set_header Host $host;
proxy_set_header X-Real-IP $remote_addr;
proxy_read_timeout 86400;
}
# ── React SPA (статика) ────────────────────────────────────────────────
root /var/www/academic;
index index.html;
location / {
try_files $uri $uri/ /index.html;
expires 1d;
add_header Cache-Control "public, no-transform";
}
# Кэшировать статические ресурсы
location ~* \.(js|css|png|jpg|jpeg|gif|ico|svg|woff2|woff)$ {
expires 30d;
add_header Cache-Control "public, immutable";
}
}
}

14
infra/postgres/init.sql Normal file
View File

@@ -0,0 +1,14 @@
-- Инициализация PostgreSQL для Академического помощника
-- Выполняется при первом старте контейнера
-- Расширения
CREATE EXTENSION IF NOT EXISTS "uuid-ossp";
CREATE EXTENSION IF NOT EXISTS "pg_trgm"; -- Для нечёткого поиска по тексту
-- Настройки подключения (уже создан через POSTGRES_USER/POSTGRES_DB env)
-- Дополнительные гранты
GRANT ALL PRIVILEGES ON DATABASE antiplagiator TO antiplagiator;
GRANT ALL PRIVILEGES ON ALL TABLES IN SCHEMA public TO antiplagiator;
GRANT ALL PRIVILEGES ON ALL SEQUENCES IN SCHEMA public TO antiplagiator;
ALTER DEFAULT PRIVILEGES IN SCHEMA public GRANT ALL ON TABLES TO antiplagiator;
ALTER DEFAULT PRIVILEGES IN SCHEMA public GRANT ALL ON SEQUENCES TO antiplagiator;