Merge pull request #5 from ArcanaFramework/mypy-ci

Updated to use Binary|UnicodeFile types and validated_property

.pre-commit-config.yaml

@@ -1,28 +1,35 @@
 # See https://pre-commit.com for more information
 # See https://pre-commit.com/hooks.html for more hooks
 repos:
--   repo: https://github.com/pre-commit/pre-commit-hooks
+  - repo: https://github.com/pre-commit/pre-commit-hooks
     rev: v4.3.0
     hooks:
-    -   id: trailing-whitespace
-    -   id: end-of-file-fixer
-    -   id: check-yaml
-    -   id: check-added-large-files
--   repo: https://github.com/psf/black
+      - id: trailing-whitespace
+      - id: end-of-file-fixer
+      - id: check-yaml
+      - id: check-added-large-files
+  - repo: https://github.com/psf/black
     rev: 22.3.0
     hooks:
-    -   id: black
+      - id: black
         exclude: ^(arcana/_version\.py|versioneer\.py)$
         args:
           - -l 88
--   repo: https://github.com/codespell-project/codespell
+  - repo: https://github.com/codespell-project/codespell
     rev: v2.1.0
     hooks:
-    -   id: codespell
+      - id: codespell
         exclude: ^(xnat_checks/_version\.py|versioneer\.py)$
         args:
-        -   --ignore-words=.codespell-ignorewords
--   repo: https://github.com/PyCQA/flake8
+          - --ignore-words=.codespell-ignorewords
+  - repo: https://github.com/PyCQA/flake8
     rev: 4.0.1
     hooks:
-    -   id: flake8
+      - id: flake8
+  - repo: https://github.com/pre-commit/mirrors-mypy
+    rev: v1.11.2
+    hooks:
+      - id: mypy
+        args: [--strict, --install-types, --non-interactive]
+        exclude: tests
+        additional_dependencies: [pytest, fileformats>=0.13.0]

conftest.py

@@ -1,6 +1,7 @@
 import os
 import logging
 from pathlib import Path
+import typing as ty
 import tempfile
 import pytest
 
@@ -23,15 +24,16 @@
 if os.getenv("_PYTEST_RAISE", "0") != "0":
 
     @pytest.hookimpl(tryfirst=True)
-    def pytest_exception_interact(call):
-        raise call.excinfo.value
+    def pytest_exception_interact(call: pytest.CallInfo[ty.Any]) -> None:
+        if call.excinfo is not None:
+            raise call.excinfo.value
 
     @pytest.hookimpl(tryfirst=True)
-    def pytest_internalerror(excinfo):
+    def pytest_internalerror(excinfo: pytest.ExceptionInfo[BaseException]) -> None:
         raise excinfo.value
 
 
 @pytest.fixture
-def work_dir():
+def work_dir() -> Path:
     work_dir = tempfile.mkdtemp()
     return Path(work_dir)

fileformats/datascience/__init__.py

@@ -4,12 +4,22 @@
     MatFile,
     RData,
     DatFile,
-    Hdf5,   
-)
-from .scripts import (
-    RFile
+    Hdf5,
 )
+from .scripts import RFile
 from .object_serialization import (
     Pickle,
     Pickle__Gzip,
-)
+)
+
+__all__ = [
+    "__version__",
+    "TextMatrix",
+    "MatFile",
+    "RData",
+    "DatFile",
+    "Hdf5",
+    "RFile",
+    "Pickle",
+    "Pickle__Gzip",
+]

fileformats/datascience/data.py

@@ -1,61 +1,61 @@
 from fileformats.core.mixin import WithMagicNumber
-from fileformats.generic import File
+from fileformats.generic import UnicodeFile, BinaryFile
 
 
-class Data(File):
-    iana_mime = None
-    binary = True
+class Data:
+    ...
 
 
-class TextVector(Data):
+class TextVector(Data, UnicodeFile):
     """space-delimited text file containing a single vector of values"""
-    binary = False
+
+    ...
 
 
-class TextArray(Data):
+class TextArray(Data, UnicodeFile):
     """space-delimited text file containing a 2-d array of values"""
-    binary = False
+
+    ...
 
 
-class TextMatrix(Data):
+class TextMatrix(Data, UnicodeFile):
     ext = ".mat"
-    binary = False
 
 
-class RData(WithMagicNumber, Data):
+class RData(WithMagicNumber, Data, BinaryFile):
     """Data-file created by the R statistical package"""
+
     ext = ".rData"
     binary = True
     magic_number = "1f8b0800"
 
 
-class MatFile(WithMagicNumber, Data):
+class MatFile(WithMagicNumber, Data, BinaryFile):
     """MATLAB Mat-File (https://au.mathworks.com/help/matlab/import_export/mat-file-versions.html)"""
+
     ext = ".mat"
     magic_number = "4D41544C"
-    binary = True
 
 
 class DatFile(Data):
     """Generic binary data file"""
-    binary = True
+
     ext = ".dat"
 
 
-class Hdf5(WithMagicNumber, Data):
+class Hdf5(WithMagicNumber, Data, BinaryFile):
     """Hierarchical Data Format (HDF) Version 5
 
     An open source file format that supports large, complex, heterogeneous data.
     HDF5 uses a "file directory" like structure that allows you to organize data within
-    the file in many different structured ways, as you might do with files on your computer."""
+    the file in many different structured ways, as you might do with files on your computer.
+    """
 
-    binary = True
     ext = ".h5"
     magic_number = "894844460d0a1a0a"
 
 
-class VtkDataFile(WithMagicNumber, Data):
+class VtkDataFile(WithMagicNumber, Data, BinaryFile):
 
-    binary = True
     ext = ".vtk"
     magic_number = b"#vtk DataFile Version"

fileformats/datascience/object_serialization.py

@@ -1,21 +1,22 @@
-from fileformats.generic import File
+from fileformats.generic import BinaryFile
 from fileformats.core.mixin import WithMagicNumber
 from fileformats.application import Gzip
 
 
-class ObjectSerialisation(File):
-    iana_mime = None
-    binary = True
+class ObjectSerialisation(BinaryFile):
+    ...
 
 
 class Pickle(WithMagicNumber, ObjectSerialisation):
     """Python's native byte-encoded serialization format"""
+
     ext = ".pkl"
     magic_number = "8004"
 
 
-class Pickle__Gzip(Gzip[Pickle]):
+class Pickle__Gzip(Gzip[Pickle]):  # type: ignore[type-arg]
     """Python pickle file that has been gzipped"""
+
     ext = "pkl.gz"
     alternate_exts = (".pklz",)
     iana_mime = "application/x-pickle+gzip"

fileformats/datascience/scripts.py

@@ -2,9 +2,10 @@
 
 
 class Script(Plain):
-    iana_mime = None
+    iana_mime = None  # type: ignore[assignment]
 
 
 class RFile(Script):
     """R statistical package script file"""
+
     ext = ".r"

pyproject.toml

@@ -74,7 +74,7 @@ doctests = true
 per-file-ignores = ["__init__.py:F401"]
 max-line-length = 88
 select = "C,E,F,W,B,B950"
-extend-ignore = ['E203', 'E501', 'E129']
+extend-ignore = ['E203', 'E501', 'E129', 'E701', 'W503']
 
 
 [tool.mypy]