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>

services/api/alembic/env.py

@@ -0,0 +1,90 @@
+"""Alembic env.py — настройка среды для миграций (async режим)."""
+
+import asyncio
+import os
+from logging.config import fileConfig
+
+from alembic import context
+from sqlalchemy import pool
+from sqlalchemy.engine import Connection
+from sqlalchemy.ext.asyncio import async_engine_from_config
+
+# Импорт всех моделей для автоопределения изменений
+from app.database import Base
+import app.models  # noqa: F401 — регистрирует все модели
+
+# Alembic Config
+config = context.config
+
+# Настройка логирования
+if config.config_file_name is not None:
+    fileConfig(config.config_file_name)
+
+# Целевые метаданные для автогенерации
+target_metadata = Base.metadata
+
+# Читаем DATABASE URL из переменной окружения (синхронный psycopg2 для Alembic)
+def get_url() -> str:
+    host = os.getenv("POSTGRES_HOST", "postgres")
+    port = os.getenv("POSTGRES_PORT", "5432")
+    db = os.getenv("POSTGRES_DB", "antiplagiator")
+    user = os.getenv("POSTGRES_USER", "antiplagiator")
+    password = os.getenv("POSTGRES_PASSWORD", "changeme")
+    return f"postgresql+psycopg2://{user}:{password}@{host}:{port}/{db}"
+
+
+def run_migrations_offline() -> None:
+    """Запустить миграции в 'offline' режиме (без реального соединения с БД)."""
+    url = get_url()
+    context.configure(
+        url=url,
+        target_metadata=target_metadata,
+        literal_binds=True,
+        dialect_opts={"paramstyle": "named"},
+        compare_type=True,
+        compare_server_default=True,
+    )
+
+    with context.begin_transaction():
+        context.run_migrations()
+
+
+def do_run_migrations(connection: Connection) -> None:
+    """Выполнить миграции с реальным соединением."""
+    context.configure(
+        connection=connection,
+        target_metadata=target_metadata,
+        compare_type=True,
+        compare_server_default=True,
+    )
+
+    with context.begin_transaction():
+        context.run_migrations()
+
+
+async def run_async_migrations() -> None:
+    """Запустить миграции в async режиме."""
+    configuration = config.get_section(config.config_ini_section) or {}
+    configuration["sqlalchemy.url"] = get_url()
+
+    connectable = async_engine_from_config(
+        configuration,
+        prefix="sqlalchemy.",
+        poolclass=pool.NullPool,
+    )
+
+    async with connectable.connect() as connection:
+        await connection.run_sync(do_run_migrations)
+
+    await connectable.dispose()
+
+
+def run_migrations_online() -> None:
+    """Запустить миграции в 'online' режиме."""
+    asyncio.run(run_async_migrations())
+
+
+if context.is_offline_mode():
+    run_migrations_offline()
+else:
+    run_migrations_online()

services/api/alembic/script.py.mako

@@ -0,0 +1,24 @@
+"""${message}
+
+Revision ID: ${up_revision}
+Revises: ${down_revision | comma,n}
+Create Date: ${create_date}
+
+"""
+from alembic import op
+import sqlalchemy as sa
+${imports if imports else ""}
+
+# revision identifiers, used by Alembic.
+revision = ${repr(up_revision)}
+down_revision = ${repr(down_revision)}
+branch_labels = ${repr(branch_labels)}
+depends_on = ${repr(depends_on)}
+
+
+def upgrade() -> None:
+    ${upgrades if upgrades else "pass"}
+
+
+def downgrade() -> None:
+    ${downgrades if downgrades else "pass"}

services/api/alembic/versions/001_initial_schema.py

@@ -0,0 +1,113 @@
+"""Начальная схема базы данных.
+
+Revision ID: 001
+Revises:
+Create Date: 2024-01-01 00:00:00.000000
+
+Создаёт таблицы: users, tasks, documents, fingerprints, usage_logs
+"""
+
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers
+revision = "001"
+down_revision = None
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    """Создать все таблицы."""
+
+    # ── users ──────────────────────────────────────────────────────────────────
+    op.create_table(
+        "users",
+        sa.Column("id", sa.Integer(), primary_key=True, autoincrement=True),
+        sa.Column("email", sa.String(255), nullable=False),
+        sa.Column("hashed_password", sa.String(255), nullable=False),
+        sa.Column("name", sa.String(255), nullable=False),
+        sa.Column("is_verified", sa.Boolean(), nullable=False, server_default="false"),
+        sa.Column("plan", sa.String(20), nullable=False, server_default="free"),
+        sa.Column("verification_token", sa.String(255), nullable=True),
+        sa.Column("created_at", sa.DateTime(timezone=True), server_default=sa.func.now()),
+        sa.Column("updated_at", sa.DateTime(timezone=True), server_default=sa.func.now()),
+    )
+    op.create_index("ix_users_email", "users", ["email"], unique=True)
+
+    # ── tasks ──────────────────────────────────────────────────────────────────
+    op.create_table(
+        "tasks",
+        sa.Column("id", sa.String(36), primary_key=True),
+        sa.Column("user_id", sa.Integer(), sa.ForeignKey("users.id", ondelete="CASCADE")),
+        sa.Column("type", sa.String(20), nullable=False),
+        sa.Column("status", sa.String(20), nullable=False, server_default="queued"),
+        sa.Column("celery_task_id", sa.String(255), nullable=True),
+        sa.Column("input_data", sa.JSON(), nullable=False, server_default="{}"),
+        sa.Column("result", sa.JSON(), nullable=True),
+        sa.Column("error", sa.Text(), nullable=True),
+        sa.Column("queue_position", sa.Integer(), nullable=True),
+        sa.Column("created_at", sa.DateTime(timezone=True), server_default=sa.func.now()),
+        sa.Column("updated_at", sa.DateTime(timezone=True), nullable=True),
+    )
+    op.create_index("ix_tasks_user_id", "tasks", ["user_id"])
+    op.create_index("ix_tasks_status", "tasks", ["status"])
+
+    # ── documents ──────────────────────────────────────────────────────────────
+    op.create_table(
+        "documents",
+        sa.Column("id", sa.Integer(), primary_key=True, autoincrement=True),
+        sa.Column("source", sa.String(50), nullable=False),
+        sa.Column("ext_id", sa.String(255), nullable=False),
+        sa.Column("doi", sa.String(255), nullable=True),
+        sa.Column("title", sa.Text(), nullable=False),
+        sa.Column("authors", sa.JSON(), nullable=False, server_default="[]"),
+        sa.Column("year", sa.Integer(), nullable=True),
+        sa.Column("lang", sa.String(10), nullable=True),
+        sa.Column("journal", sa.Text(), nullable=True),
+        sa.Column("volume", sa.String(50), nullable=True),
+        sa.Column("issue", sa.String(50), nullable=True),
+        sa.Column("pages", sa.String(50), nullable=True),
+        sa.Column("abstract", sa.Text(), nullable=True),
+        sa.Column("url", sa.Text(), nullable=True),
+        sa.Column("minio_key", sa.Text(), nullable=True),
+        sa.Column("faiss_id", sa.Integer(), nullable=True),
+        sa.Column("indexed_at", sa.DateTime(timezone=True), server_default=sa.func.now()),
+    )
+    op.create_index("ix_documents_ext_id", "documents", ["ext_id"], unique=True)
+    op.create_index("ix_documents_doi", "documents", ["doi"])
+    op.create_index("ix_documents_source", "documents", ["source"])
+    op.create_index("ix_documents_year", "documents", ["year"])
+    op.create_index("ix_documents_lang", "documents", ["lang"])
+    op.create_index("ix_documents_faiss_id", "documents", ["faiss_id"])
+
+    # ── fingerprints ───────────────────────────────────────────────────────────
+    op.create_table(
+        "fingerprints",
+        sa.Column("id", sa.Integer(), primary_key=True, autoincrement=True),
+        sa.Column("doc_id", sa.Integer(), sa.ForeignKey("documents.id", ondelete="CASCADE")),
+        sa.Column("hash_value", sa.BigInteger(), nullable=False),
+        sa.Column("position", sa.Integer(), nullable=False),
+    )
+    op.create_index("ix_fingerprints_doc_id", "fingerprints", ["doc_id"])
+    op.create_index("ix_fingerprints_hash_value", "fingerprints", ["hash_value"])
+
+    # ── usage_logs ─────────────────────────────────────────────────────────────
+    op.create_table(
+        "usage_logs",
+        sa.Column("id", sa.Integer(), primary_key=True, autoincrement=True),
+        sa.Column("user_id", sa.Integer(), sa.ForeignKey("users.id", ondelete="CASCADE")),
+        sa.Column("action", sa.String(50), nullable=False),
+        sa.Column("created_at", sa.DateTime(timezone=True), server_default=sa.func.now()),
+    )
+    op.create_index("ix_usage_logs_user_id", "usage_logs", ["user_id"])
+    op.create_index("ix_usage_logs_created_at", "usage_logs", ["created_at"])
+
+
+def downgrade() -> None:
+    """Удалить все таблицы."""
+    op.drop_table("usage_logs")
+    op.drop_table("fingerprints")
+    op.drop_table("documents")
+    op.drop_table("tasks")
+    op.drop_table("users")