Init

.github/workflows/build_docker_image.yml

@@ -0,0 +1,49 @@
+name: Build docker image
+
+on:
+  push:
+    branches:
+      - 'main'
+
+jobs:
+  Build-Docker-Image:
+    runs-on: ubuntu-latest
+    steps:
+      -
+        name: Checkout
+        uses: actions/checkout@v2
+      
+      -
+        name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v1
+
+      - id: repository_name
+        uses: ASzc/change-string-case-action@v1
+        with:
+          string: ${{ github.repository }}
+
+      -
+        name: Login to ghcr.io
+        uses: docker/login-action@v1 
+        with:
+          registry: ghcr.io
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      -
+        name: Build and push
+        id: docker_build
+        uses: docker/build-push-action@v2
+        env:
+          IMAGE: ${{ steps.repository_name.outputs.lowercase }}
+        with:
+          push: true
+          tags: ghcr.io/${{ env.IMAGE }}:latest
+          context: .
+          file: ./docker/production.dockerfile
+
+      - 
+        name: Invoke deployment hook
+        uses: joelwmale/webhook-action@master
+        with:
+          url: ${{ secrets.WEBHOOK_URL }}

.gitignore

@@ -0,0 +1,5 @@
+.vscode
+
+__pycache__
+
+venv

docker/production.dockerfile

@@ -0,0 +1,35 @@
+FROM python:3.10-slim as build-image
+
+RUN apt-get update \
+    && apt-get install --no-install-recommends -y gcc build-essential python3-dev libpq-dev libffi-dev \
+    && rm -rf /var/lib/apt/lists/*
+
+WORKDIR /root/venv
+COPY ./requirements.txt /root/venv/
+
+ENV VENV_PATH=/opt/venv
+
+RUN python -m venv $VENV_PATH \
+    && . /opt/venv/bin/activate \
+    && pip install -r requirements.txt --no-cache-dir
+
+
+FROM python:3.10-slim as runtime-image
+
+RUN apt-get update \
+    && apt-get install --no-install-recommends -y python3-dev libpq-dev libffi-dev \
+    && rm -rf /var/lib/apt/lists/*
+
+WORKDIR /app
+
+COPY ./src/ /app/
+
+ENV VENV_PATH=/opt/venv
+COPY --from=build-image $VENV_PATH $VENV_PATH
+ENV PATH="$VENV_PATH/bin:$PATH"
+
+COPY ./scripts/start_production.sh /root/
+
+EXPOSE 8080
+
+CMD bash /root/start_production.sh

requirements.txt

@@ -0,0 +1,8 @@
+fastapi
+pydantic
+asyncpg
+psycopg2
+httpx
+ormar
+alembic
+uvicorn[standart]

scripts/start_production.sh

@@ -0,0 +1,3 @@
+cd /app
+alembic -c ./app/alembic.ini upgrade head
+uvicorn main:app --host="0.0.0.0" --port="8080"

src/app/alembic.ini

@@ -0,0 +1,98 @@
+# A generic, single database configuration.
+
+[alembic]
+# path to migration scripts
+script_location = ./app/alembic
+
+# template used to generate migration files
+# file_template = %%(rev)s_%%(slug)s
+
+# sys.path path, will be prepended to sys.path if present.
+# defaults to the current working directory.
+prepend_sys_path = .
+
+# timezone to use when rendering the date within the migration file
+# as well as the filename.
+# If specified, requires the python-dateutil library that can be
+# installed by adding `alembic[tz]` to the pip requirements
+# string value is passed to dateutil.tz.gettz()
+# leave blank for localtime
+# timezone =
+
+# max length of characters to apply to the
+# "slug" field
+# truncate_slug_length = 40
+
+# set to 'true' to run the environment during
+# the 'revision' command, regardless of autogenerate
+# revision_environment = false
+
+# set to 'true' to allow .pyc and .pyo files without
+# a source .py file to be detected as revisions in the
+# versions/ directory
+# sourceless = false
+
+# version location specification; This defaults
+# to alembic/versions.  When using multiple version
+# directories, initial revisions must be specified with --version-path.
+# The path separator used here should be the separator specified by "version_path_separator"
+# version_locations = %(here)s/bar:%(here)s/bat:alembic/versions
+
+# version path separator; As mentioned above, this is the character used to split
+# version_locations. Valid values are:
+#
+# version_path_separator = :
+# version_path_separator = ;
+# version_path_separator = space
+version_path_separator = os  # default: use os.pathsep
+
+# the output encoding used when revision files
+# are written from script.py.mako
+# output_encoding = utf-8
+
+
+[post_write_hooks]
+# post_write_hooks defines scripts or Python functions that are run
+# on newly generated revision scripts.  See the documentation for further
+# detail and examples
+
+# format using "black" - use the console_scripts runner, against the "black" entrypoint
+# hooks = black
+# black.type = console_scripts
+# black.entrypoint = black
+# black.options = -l 79 REVISION_SCRIPT_FILENAME
+
+# Logging configuration
+[loggers]
+keys = root,sqlalchemy,alembic
+
+[handlers]
+keys = console
+
+[formatters]
+keys = generic
+
+[logger_root]
+level = WARN
+handlers = console
+qualname =
+
+[logger_sqlalchemy]
+level = WARN
+handlers =
+qualname = sqlalchemy.engine
+
+[logger_alembic]
+level = INFO
+handlers =
+qualname = alembic
+
+[handler_console]
+class = StreamHandler
+args = (sys.stderr,)
+level = NOTSET
+formatter = generic
+
+[formatter_generic]
+format = %(levelname)-5.5s [%(name)s] %(message)s
+datefmt = %H:%M:%S

src/app/alembic/README

@@ -0,0 +1 @@
+Generic single-database configuration.

src/app/alembic/env.py

@@ -0,0 +1,64 @@
+from alembic import context
+import sys, os
+
+from sqlalchemy.engine import create_engine
+
+from core.db import DATABASE_URL
+
+
+myPath = os.path.dirname(os.path.abspath(__file__))
+sys.path.insert(0, myPath + '/../../')
+
+config = context.config
+
+
+from app.models import BaseMeta
+target_metadata = BaseMeta.metadata
+
+
+def run_migrations_offline():
+    """Run migrations in 'offline' mode.
+
+    This configures the context with just a URL
+    and not an Engine, though an Engine is acceptable
+    here as well.  By skipping the Engine creation
+    we don't even need a DBAPI to be available.
+
+    Calls to context.execute() here emit the given string to the
+    script output.
+
+    """
+    url = config.get_main_option("sqlalchemy.url")
+    context.configure(
+        url=url,
+        target_metadata=target_metadata,
+        literal_binds=True,
+        dialect_opts={"paramstyle": "named"},
+    )
+
+    with context.begin_transaction():
+        context.run_migrations()
+
+
+def run_migrations_online():
+    """Run migrations in 'online' mode.
+
+    In this scenario we need to create an Engine
+    and associate a connection with the context.
+
+    """
+    connectable = create_engine(DATABASE_URL)
+
+    with connectable.connect() as connection:
+        context.configure(
+            connection=connection, target_metadata=target_metadata, compare_type=True
+        )
+
+        with context.begin_transaction():
+            context.run_migrations()
+
+
+if context.is_offline_mode():
+    run_migrations_offline()
+else:
+    run_migrations_online()

src/app/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():
+    ${upgrades if upgrades else "pass"}
+
+
+def downgrade():
+    ${downgrades if downgrades else "pass"}

src/app/alembic/versions/9b7cfb422191_.py

@@ -0,0 +1,35 @@
+"""empty message
+
+Revision ID: 9b7cfb422191
+Revises: 
+Create Date: 2021-11-21 14:09:17.478532
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = '9b7cfb422191'
+down_revision = None
+branch_labels = None
+depends_on = None
+
+
+def upgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.create_table('cached_files',
+    sa.Column('id', sa.Integer(), nullable=False),
+    sa.Column('object_id', sa.Integer(), nullable=False),
+    sa.Column('object_type', sa.String(length=8), nullable=False),
+    sa.Column('data', sa.JSON(), nullable=False),
+    sa.PrimaryKeyConstraint('id'),
+    sa.UniqueConstraint('object_id', 'object_type', name='uc_cached_files_object_id_object_type')
+    )
+    # ### end Alembic commands ###
+
+
+def downgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.drop_table('cached_files')
+    # ### end Alembic commands ###

src/app/depends.py

@@ -0,0 +1,9 @@
+from fastapi import Security, HTTPException, status
+
+from core.auth import default_security
+from core.config import env_config
+
+
+async def check_token(api_key: str = Security(default_security)):
+    if api_key != env_config.API_KEY:
+        raise HTTPException(status_code=status.HTTP_403_FORBIDDEN, detail="Wrong api key!")

src/app/models.py

@@ -0,0 +1,21 @@
+import ormar
+
+from core.db import metadata, database
+
+
+class BaseMeta(ormar.ModelMeta):
+    metadata = metadata
+    database = database
+
+
+class CachedFile(ormar.Model):
+    class Meta(BaseMeta):
+        tablename = "cached_files"
+        constraints = [
+            ormar.UniqueColumns('object_id','object_type')
+        ]
+    
+    id: int = ormar.Integer(primary_key=True)  # type: ignore
+    object_id: int = ormar.Integer()  # type: ignore
+    object_type: str = ormar.String(max_length=8)  # type: ignore
+    data = ormar.JSON()

src/app/serializers.py

@@ -0,0 +1,14 @@
+from pydantic import BaseModel, constr
+
+
+class CachedFile(BaseModel):
+    id: int
+    object_id: int
+    object_type: str
+    data: dict
+
+
+class CreateCachedFile(BaseModel):
+    object_id: int
+    object_type: constr(max_length=8)  # type: ignore
+    data: dict

src/app/services/cache_updater.py

@@ -0,0 +1,76 @@
+import asyncio
+
+from app.services.library_client import get_books, Book
+from app.services.downloader import download
+from app.services.files_uploader import upload_file
+from app.models import CachedFile
+
+
+PAGE_SIZE = 50
+
+
+class CacheUpdater:
+    def __init__(self):
+        self.queue = asyncio.Queue(maxsize=10)
+        self.all_books_checked = False
+
+    async def _check_book(self, book: Book):
+        for file_type in book.available_types:
+            cached_file = await CachedFile.objects.get_or_none(
+                object_id=book.id, object_type=file_type
+            )
+
+            if cached_file is None:
+                await self.queue.put((book, file_type))
+
+    async def _start_producer(self):
+        books_page = await get_books(1, 1)
+
+        page_count = books_page.total // PAGE_SIZE
+        if books_page.total % PAGE_SIZE != 0:
+            page_count += 1
+
+        for page_number in range(1, page_count + 1):
+            page = await get_books(page_number, PAGE_SIZE)
+
+            for book in page.items:
+                await self._check_book(book)
+        
+        self.all_books_checked = True
+
+    async def _start_worker(self):
+        while not self.all_books_checked or not self.queue.empty():
+            try:
+                task = self.queue.get_nowait()
+                book: Book = task[0]
+                file_type: str = task[1]
+            except asyncio.QueueEmpty:
+                await asyncio.sleep(0.1)
+                continue
+            
+            data = await download(book.source.id, book.remote_id, file_type)
+
+            if data is None:
+                return
+
+            content, filename = data
+
+            upload_data = await upload_file(content, filename, 'Test')
+
+            await CachedFile.objects.create(
+                object_id=book.id,
+                object_type=file_type,
+                data=upload_data.data
+            )
+
+    async def _update(self):
+        await asyncio.gather(
+            self._start_producer(),
+            self._start_worker(),
+            self._start_worker()
+        )
+
+    @classmethod
+    async def update(cls):
+        updater = cls()
+        return await updater._update()

src/app/services/downloader.py

@@ -0,0 +1,21 @@
+from typing import Optional
+
+import httpx
+
+from core.config import env_config
+
+
+async def download(source_id: int, remote_id: int, file_type: str) -> Optional[tuple[bytes, str]]:
+    headers = {"Authorization": env_config.DOWNLOADER_API_KEY}
+
+    async with httpx.AsyncClient() as client:
+        response = await client.get(f"{env_config.DOWNLOADER_URL}/download/{source_id}/{remote_id}/{file_type}", headers=headers, timeout=5 * 60)
+
+        if response.status_code != 200:
+            return None
+
+        content_disposition = response.headers['Content-Disposition']
+
+        name = content_disposition.replace('attachment; filename=', '')
+
+        return response.content, name

src/app/services/files_uploader.py

@@ -0,0 +1,25 @@
+from datetime import datetime
+
+import httpx
+from pydantic import BaseModel
+
+from core.config import env_config
+
+
+class UploadedFile(BaseModel):
+    id: int
+    backend: str
+    data: dict
+    upload_time: datetime
+
+
+async def upload_file(content: bytes, filename: str, caption: str) -> UploadedFile:
+    headers = {"Authorization": env_config.FILES_SERVER_API_KEY}
+
+    async with httpx.AsyncClient() as client:
+        form = {'caption': caption}
+        files = {'file': (filename, content)}
+
+        response = await client.post(f"{env_config.FILES_SERVER_URL}/api/v1/files/upload/", data=form, files=files, headers=headers, timeout=5 * 60)
+
+        return UploadedFile.parse_obj(response.json())

src/app/services/library_client.py

@@ -0,0 +1,54 @@
+from typing import Generic, TypeVar
+from pydantic import BaseModel
+from datetime import date
+
+from core.config import env_config
+
+import httpx
+
+
+T = TypeVar('T')
+
+
+class Page(BaseModel, Generic[T]):
+    items: list[T]
+    total: int
+    page: int
+    size: int
+
+
+class BookAuthor(BaseModel):
+    id: int
+    first_name: str
+    last_name: str
+    middle_name: str
+
+
+class BookSource(BaseModel):
+    id: int
+    name: str
+
+
+class Book(BaseModel):
+    id: int
+    title: str
+    file_type: str
+    available_types: list[str]
+    source: BookSource
+    remote_id: int
+    uploaded: date
+    authors: list[BookAuthor]
+
+
+async def get_books(page: int, page_size: int) -> Page[Book]:
+    headers = {"Authorization": env_config.LIBRARY_API_KEY}
+
+    async with httpx.AsyncClient() as client:
+        response = await client.get(f"{env_config.LIBRARY_URL}/api/v1/books/?page={page}&size={page_size}&is_deleted=false", headers=headers)
+
+        data = response.json()
+
+        page_data = Page[Book].parse_obj(data)
+        page_data.items = [Book.parse_obj(item) for item in page_data.items]
+
+        return page_data

src/app/views.py

@@ -0,0 +1,53 @@
+from fastapi import APIRouter, Depends, HTTPException, status
+
+from app.depends import check_token
+from app.models import CachedFile as CachedFileDB
+from app.serializers import CachedFile, CreateCachedFile
+from app.services.cache_updater import CacheUpdater
+
+
+router = APIRouter(
+    prefix="/api/v1",
+    tags=["files"],
+    dependencies=[Depends(check_token)]
+)
+
+
+@router.get("/{object_id}/{object_type}", response_model=CachedFile)
+async def get_cached_file(object_id: int, object_type: str):
+    cached_file = await CachedFileDB.objects.get(
+        object_id=object_id,
+        object_type=object_type
+    )
+
+    if not cached_file:
+        raise HTTPException(status_code=status.HTTP_404_NOT_FOUND)
+    
+    return cached_file
+
+
+@router.delete("/{object_id}/{object_type}", response_model=CachedFile)
+async def delete_cached_file(object_id: int, object_type: str):
+    cached_file = await CachedFileDB.objects.get(
+        object_id=object_id,
+        object_type=object_type
+    )
+
+    if not cached_file:
+        raise HTTPException(status_code=status.HTTP_404_NOT_FOUND)
+
+    await cached_file.delete()
+    
+    return cached_file
+
+
+@router.post("/", response_model=CachedFile)
+async def create_cached_file(data: CreateCachedFile):
+    return await CachedFileDB.objects.create(
+        *data.dict()
+    )
+
+
+@router.post("/update_cache")
+async def update_cache():
+    await CacheUpdater.update()

src/core/app.py

@@ -0,0 +1,26 @@
+from fastapi import FastAPI
+
+from core.db import database
+from app.views import router
+
+
+def start_app() -> FastAPI:
+    app = FastAPI()
+
+    app.state.database = database
+
+    app.include_router(router)
+
+    @app.on_event('startup')
+    async def startup() -> None:
+        database_ = app.state.database
+        if not database_.is_connected:
+            await database_.connect()
+
+    @app.on_event('shutdown')
+    async def shutdown() -> None:
+        database_ = app.state.database
+        if database_.is_connected:
+            await database_.disconnect()
+
+    return app

src/core/auth.py

@@ -0,0 +1,4 @@
+from fastapi.security import APIKeyHeader
+
+
+default_security = APIKeyHeader(name="Authorization")

src/core/config.py

@@ -0,0 +1,23 @@
+from pydantic import BaseSettings
+
+
+class EnvConfig(BaseSettings):
+    API_KEY: str
+
+    POSTGRES_USER: str
+    POSTGRES_PASSWORD: str
+    POSTGRES_HOST: str
+    POSTGRES_PORT: int
+    POSTGRES_DB: str
+
+    DOWNLOADER_API_KEY: str
+    DOWNLOADER_URL: str
+
+    LIBRARY_API_KEY: str
+    LIBRARY_URL: str
+
+    FILES_SERVER_API_KEY: str
+    FILES_SERVER_URL: str
+
+
+env_config = EnvConfig()

src/core/db.py

@@ -0,0 +1,15 @@
+from urllib.parse import quote
+from databases import Database
+
+from sqlalchemy import MetaData
+
+from core.config import env_config
+
+
+DATABASE_URL = (
+    f"postgresql://{env_config.POSTGRES_USER}:{quote(env_config.POSTGRES_PASSWORD)}@"
+    f"{env_config.POSTGRES_HOST}:{env_config.POSTGRES_PORT}/{env_config.POSTGRES_DB}"
+)
+
+metadata = MetaData()
+database = Database(DATABASE_URL)

src/main.py

@@ -0,0 +1,4 @@
+from core.app import start_app
+
+
+app = start_app()