migrate to python-magic (#23)

Co-authored-by: Artur Shiriev <me@shiriev.ru>

Author: lesnik512

.dockerignore

@@ -0,0 +1,15 @@
+.env
+.coverage
+.gitignore
+.idea
+.mypy_cache
+.ruff_cache
+.vscode
+.git
+.pytest_cache
+.DS_Store
+*.yml
+Dockerfile
+**/__pycache__
+.hypothesis
+.venv

.github/workflows/ci.yml

@@ -0,0 +1,54 @@
+name: main
+
+on:
+  push:
+    branches:
+      - main
+  pull_request: {}
+
+concurrency:
+  group: ${{ github.head_ref || github.run_id }}
+  cancel-in-progress: true
+
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: extractions/setup-just@v2
+      - uses: astral-sh/setup-uv@v3
+        with:
+          enable-cache: true
+          cache-dependency-glob: "**/pyproject.toml"
+      - run: uv python install 3.10
+      - run: just install lint-ci
+
+  pytest:
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version:
+          - "3.10"
+          - "3.11"
+          - "3.12"
+          - "3.13"
+    steps:
+      - name: install libmagic
+        run: sudo apt install -y libmagic-dev
+      - uses: actions/checkout@v4
+      - uses: extractions/setup-just@v2
+      - uses: astral-sh/setup-uv@v3
+        with:
+          enable-cache: true
+          cache-dependency-glob: "**/pyproject.toml"
+      - run: uv python install ${{ matrix.python-version }}
+      - run: just install
+      - run: just test-ci . --cov=. --cov-report xml
+      - uses: codecov/codecov-action@v4.0.1
+        env:
+          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
+        with:
+          files: ./coverage.xml
+          flags: unittests
+          name: codecov-${{ matrix.python-version }}

.github/workflows/publish.yml

@@ -0,0 +1,17 @@
+name: Publish Package
+
+on:
+  release:
+    types:
+      - published
+
+jobs:
+  publish:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: extractions/setup-just@v2
+      - uses: astral-sh/setup-uv@v3
+      - run: just publish
+        env:
+          PYPI_TOKEN: ${{ secrets.PYPI_TOKEN }}

.github/workflows/workflow.yml

@@ -0,0 +1,27 @@
+FROM python:3.13-slim
+
+# required for python-magic
+RUN apt update \
+    && apt install -y --no-install-recommends \
+        libmagic-dev \
+    && apt clean \
+    && rm -rf /var/lib/apt/lists/*
+
+COPY --from=ghcr.io/astral-sh/uv:latest /uv /bin/uv
+RUN useradd --no-create-home --gid root runner
+
+ENV UV_PYTHON_PREFERENCE=only-system
+ENV UV_NO_CACHE=true
+
+WORKDIR /code
+
+COPY pyproject.toml .
+COPY uv.lock .
+
+RUN uv sync --all-extras --frozen --no-install-project
+
+COPY . .
+
+RUN chown -R runner:root /code && chmod -R g=u /code
+
+USER runner

Dockerfile

@@ -1,5 +1,17 @@
 default: install lint test
 
+down:
+    docker compose down --remove-orphans
+
+sh:
+    docker compose run --service-ports application bash
+
+test *args: down && down
+    docker compose run application uv run --no-sync pytest {{ args }}
+
+build:
+    docker compose build application
+
 install:
     uv lock --upgrade
     uv sync --frozen --all-groups
@@ -16,7 +28,7 @@ lint-ci:
     uv run --group lint ruff check --no-fix
     uv run --group lint mypy .
 
-test *args:
+test-ci *args:
     uv run pytest {{ args }}
 
 publish:

Justfile

@@ -1,6 +1,6 @@
 # safe-s3-storage
 
-S3 tools for uploading files to S3 safely (antivirus check, etc) as well as downloading and deleting files.
+S3 tools for uploading files to S3 safely (antivirus check, etc.) as well as downloading and deleting files.
 
 ## How To Use
 

README.md

@@ -0,0 +1,11 @@
+services:
+  application:
+    build:
+      context: .
+      dockerfile: ./Dockerfile
+    restart: always
+    volumes:
+      - .:/code
+      - /code/.venv
+    stdin_open: true
+    tty: true

docker-compose.yml

@@ -6,6 +6,7 @@ keywords = ["s3", "kaspersky", "antivirus", "upload"]
 classifiers = [
     "Natural Language :: English",
     "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
     "Programming Language :: Python :: 3.12",
     "Programming Language :: Python :: 3.13",
     "Topic :: Software Development :: Libraries",
@@ -22,12 +23,22 @@ dependencies = [
     "pydantic",
     "pyvips",
     "pyvips-binary",
-    "magika",
+    "python-magic",
 ]
 
 [dependency-groups]
-dev = ["anyio", "faker", "pytest", "pytest-cov"]
-lint = [{ include-group = "dev" }, "auto-typing-final", "mypy", "ruff"]
+dev = [
+    "anyio",
+    "faker",
+    "pytest",
+    "pytest-cov",
+]
+lint = [
+    { include-group = "dev" },
+    "auto-typing-final",
+    "mypy",
+    "ruff",
+]
 
 [build-system]
 requires = ["uv_build"]

pyproject.toml

@@ -2,8 +2,8 @@
 import enum
 import typing
 
+import magic
 import pyvips  # type: ignore[import-untyped]
-from magika import Magika
 
 from safe_s3_storage import exceptions
 from safe_s3_storage.kaspersky_scan_engine import KasperskyScanEngineClient
@@ -49,13 +49,7 @@ class FileValidator:
     excluded_conversion_formats: list[str] | None = None
 
     def _validate_mime_type(self, *, file_name: str, file_content: bytes) -> str:
-        mime_type_prediction: typing.Final = Magika().identify_bytes(file_content)
-        if mime_type_prediction.output.is_text and file_name.endswith(".txt"):
-            mime_type = "text/plain"
-        elif mime_type_prediction.dl.extensions:
-            mime_type = mime_type_prediction.dl.mime_type
-        else:
-            mime_type = mime_type_prediction.output.mime_type
+        mime_type: typing.Final = magic.from_buffer(file_content, mime=True)
         if self.allowed_mime_types is None or mime_type in self.allowed_mime_types:
             return mime_type