ci: update linter to ruff and minor refactor

.github/workflows/python-app.yml

@@ -15,7 +15,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: ["3.7", "3.8", "3.9", "3.10"]
+        python-version: ["3.9", "3.10", "3.11"]
 
     steps:
       - uses: actions/checkout@v3
@@ -26,14 +26,15 @@ jobs:
       - name: Install dependencies
         run: |
           python -m pip install --upgrade pip
-          pip install flake8 pytest
+          pip install coverage pytest
           if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
-      - name: Lint with flake8
-        run: |
-          # stop the build if there are Python syntax errors or undefined names
-          flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
-          # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
-          flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
+      - name: Lint with ruff
+        uses: astral-sh/ruff-action@v3
+        with:
+          args: check
       - name: Test with pytest
         run: |
-          pytest
+          coverage run -m pytest
+      - name: Show coverage report
+        run: |
+          coverage report -mi --fail-under=${{ vars.COVERAGE_FAIL_UNDER}}

.pre-commit-config.yaml

@@ -5,19 +5,12 @@ repos:
     -   id: check-yaml
     -   id: end-of-file-fixer
     -   id: trailing-whitespace
--   repo: https://github.com/psf/black
-    rev: 22.8.0
+
+-   repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.11.5
     hooks:
-    -   id: black
--   repo: https://github.com/pycqa/isort
-    rev: 5.12.0
-    hooks:
-    -   id: isort
-        name: isort (python)
-        args: ["--profile", "black"]
--   repo: https://github.com/pycqa/flake8
-    rev: 5.0.4
-    hooks:
-    -   id: flake8
-        args: [--max-line-length=100, "-j8", "--ignore=E203,E501,P103,F403,F405,W503"]
-        additional_dependencies: [flake8-isort]
+    -   id: ruff
+        types_or: [ python, pyi ]
+        args: [ --fix ]
+    -   id: ruff-format
+        types_or: [ python, pyi ]

.vscode/settings.json

@@ -0,0 +1,7 @@
+{
+    "python.testing.pytestArgs": [
+        "tests"
+    ],
+    "python.testing.unittestEnabled": false,
+    "python.testing.pytestEnabled": true
+}

filext/__init__.py

@@ -1,67 +1,7 @@
-from typing import Union
+from filext.functions import whatdoc, whatimage, whatfile
 
-from filext.classifiers import *
-from filext.utils import lookup_file_type
-
-
-def whatfile(file: Union[str, bytes]) -> Union[str, None]:
-    """
-    Identifies the file type by calling each classifier
-
-    Args:
-        file (Union[str, bytes]): path to file or bytes of file
-
-    Returns:
-        str: found file type or None
-    """
-    classifiers = (
-        whatdoc,
-        whatimage,
-    )
-    for classifier in classifiers:
-        result = classifier(file)
-        if result:
-            return result
-
-
-def whatdoc(file: Union[str, bytes]) -> Union[str, None]:
-    """
-    Identifies the file type by calling each document classifier
-
-    Args:
-        file (Union[str, bytes]): path to file or bytes of file
-
-    Returns:
-        Union[str,None]: found file type or None
-    """
-    file_types = {
-        "docx": is_docx,
-        "pptx": is_pptx,
-        "xlsx": is_xlsx,
-        "pdf": is_pdf,
-        "doc": is_doc,
-        "xls": is_xls,
-        "ppt": is_ppt,
-    }
-    return lookup_file_type(file, file_types)
-
-
-def whatimage(file: Union[str, bytes]) -> Union[str, None]:
-    """
-    Identifies the file type by calling each image classifier
-
-    Args:
-        file (Union[str, bytes]): path to file or bytes of file
-
-    Returns:
-        Union[str,None]: found file type or None
-    """
-    file_types = {
-        "bmp": is_bmp,
-        "gif": is_gif,
-        "heic": is_heic,
-        "jpg": is_jpg,
-        "png": is_png,
-        "tif": is_tif,
-    }
-    return lookup_file_type(file, file_types)
+__all__ = [
+    "whatdoc",
+    "whatimage",
+    "whatfile",
+]

filext/functions.py

@@ -0,0 +1,81 @@
+from typing import Union
+
+from filext.classifiers import (
+    is_bmp,
+    is_doc,
+    is_docx,
+    is_gif,
+    is_heic,
+    is_jpg,
+    is_pdf,
+    is_png,
+    is_ppt,
+    is_pptx,
+    is_tif,
+    is_xls,
+    is_xlsx,
+)
+from filext.utils import lookup_file_type
+
+
+def whatfile(file: Union[str, bytes]) -> Union[str, None]:
+    """
+    Identifies the file type by calling each classifier
+
+    Args:
+        file (Union[str, bytes]): path to file or bytes of file
+
+    Returns:
+        str: found file type or None
+    """
+    classifiers = (
+        whatdoc,
+        whatimage,
+    )
+    for classifier in classifiers:
+        result = classifier(file)
+        if result:
+            return result
+
+
+def whatdoc(file: Union[str, bytes]) -> Union[str, None]:
+    """
+    Identifies the file type by calling each document classifier
+
+    Args:
+        file (Union[str, bytes]): path to file or bytes of file
+
+    Returns:
+        Union[str,None]: found file type or None
+    """
+    file_types = {
+        "docx": is_docx,
+        "pptx": is_pptx,
+        "xlsx": is_xlsx,
+        "pdf": is_pdf,
+        "doc": is_doc,
+        "xls": is_xls,
+        "ppt": is_ppt,
+    }
+    return lookup_file_type(file, file_types)
+
+
+def whatimage(file: Union[str, bytes]) -> Union[str, None]:
+    """
+    Identifies the file type by calling each image classifier
+
+    Args:
+        file (Union[str, bytes]): path to file or bytes of file
+
+    Returns:
+        Union[str,None]: found file type or None
+    """
+    file_types = {
+        "bmp": is_bmp,
+        "gif": is_gif,
+        "heic": is_heic,
+        "jpg": is_jpg,
+        "png": is_png,
+        "tif": is_tif,
+    }
+    return lookup_file_type(file, file_types)

filext/utils.py

@@ -1,8 +1,9 @@
 from concurrent.futures import ThreadPoolExecutor, as_completed
+from pathlib import Path
 from typing import Callable, Dict, Union
 
 
-def get_bytes(file: Union[str, bytes]) -> bytes:
+def get_bytes(file: Union[str, bytes, Path]) -> bytes:
     """
     Returns the raw bytes of a given file.
 
@@ -20,6 +21,8 @@ def get_bytes(file: Union[str, bytes]) -> bytes:
             file_bytes = fh.read()
     elif isinstance(file, bytes):
         file_bytes = file
+    elif isinstance(file, Path):
+        file_bytes = file.read_bytes()
     else:
         raise TypeError
     return file_bytes

requirements-dev.txt

@@ -0,0 +1,6 @@
+-r requirements.txt
+commitizen
+coverage
+pre-commit
+pytest
+ruff

tests/test_utils.py

@@ -1,9 +1,14 @@
+from pathlib import Path
+
 import pytest
 
 from filext.utils import get_bytes
 
 
-@pytest.mark.parametrize("file", ["tests/files/image.png"])
+@pytest.mark.parametrize(
+    "file",
+    ["tests/files/image.png", Path("tests/files/image.png")],
+)
 def test_get_bytes_valid(file):
     assert isinstance(get_bytes(file), bytes)