Add stricter Ruff linting (#79)

Author: william-billaud

dissect/hypervisor/__init__.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 from dissect.hypervisor.descriptor import hyperv, ovf, pvs, vbox, vmx
 from dissect.hypervisor.disk import asif, hdd, qcow2, vdi, vhd, vhdx, vmdk
 from dissect.hypervisor.util import envelope, vmtar

dissect/hypervisor/descriptor/vmx.py

@@ -101,7 +101,7 @@ def unlock_with_phrase(self, passphrase: str) -> None:
         self.attr.update(**_parse_dictionary(decrypted.decode()))
 
     def disks(self) -> list[str]:
-        """Return a list of paths to disk files"""
+        """Return a list of paths to disk files."""
         dev_classes = ("scsi", "sata", "ide", "nvme")
         devices = {}
 
@@ -179,7 +179,6 @@ def unseal_with_phrase(self, passphrase: str) -> bytes:
     @classmethod
     def from_text(cls, text: str) -> KeySafe:
         """Parse a ``KeySafe`` from a string."""
-
         # Key safes are a list of key locators. It's a key locator string with a specific prefix
         identifier, _, remainder = text.partition("/")
         if identifier != "vmware:key":
@@ -262,7 +261,6 @@ def _parse_key_locator(locator_string: str) -> Pair | Phrase | list[Pair | Phras
 
     Interally called ``KeyLocator``.
     """
-
     identifier, _, remainder = locator_string.partition("/")
 
     if identifier == "list":
@@ -303,7 +301,6 @@ def _split_list(value: str) -> list[str]:
     Lists are wrapped by braces and separated by comma. They can contain nested lists/pairs,
     so we need to separate at the correct nest level.
     """
-
     if not (match := re.match(r"\((.+)\)", value)):
         raise ValueError("Invalid list string")
 
@@ -337,7 +334,6 @@ def _parse_crypto_dict(dict_string: str) -> dict[str, str]:
 
     Internally called ``CryptoDict``.
     """
-
     crypto_dict = {}
     for part in dict_string.split(":"):
         key, _, value = part.partition("=")
@@ -351,7 +347,6 @@ def _decrypt_hmac(key: bytes, data: bytes, digest: str) -> bytes:
     First 16 bytes of the ciphertext are the IV and the last N bytes are the HMAC digest.
     The cleartext is padded using PKCS#7.
     """
-
     digest, digest_size = HMAC_MAP[digest]
 
     iv, encrypted, mac = data[:16], data[16:-digest_size], data[-digest_size:]
@@ -374,7 +369,6 @@ def _create_cipher(key: bytes, iv: bytes) -> AES.CbcMode:
 
     Dynamic based on the available crypto module.
     """
-
     if HAS_PYSTANDALONE:
         if len(key) == 32:
             cipher = "aes-256-cbc"

dissect/hypervisor/disk/vmdk.py

@@ -29,9 +29,7 @@
 
 class VMDK(AlignedStream):
     def __init__(self, fh: BinaryIO | Path | str | list[BinaryIO | Path | str]):
-        """
-        Input can be a file handle to a Disk Descriptor file or a list of file handles to multiple VMDK files.
-        """
+        """Input can be a file handle to a Disk Descriptor file or a list of file handles to multiple VMDK files."""
         fhs = [fh] if not isinstance(fh, list) else fh
 
         self.disks = []
@@ -462,7 +460,6 @@ def parse(cls, vmdk_config: str) -> DiskDescriptor:
         Resources:
             - https://github.com/libyal/libvmdk/blob/main/documentation/VMWare%20Virtual%20Disk%20Format%20(VMDK).asciidoc
         """
-
         descriptor_settings = {}
         extents: list[ExtentDescriptor] = []
         disk_db = {}

dissect/hypervisor/exceptions.py

@@ -1,3 +1,6 @@
+from __future__ import annotations
+
+
 class Error(Exception):
     pass
 

dissect/hypervisor/tools/vmtar.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 import tarfile
 
 from dissect.hypervisor.util import vmtar

dissect/hypervisor/util/vmtar.py

@@ -62,12 +62,12 @@ def visoropen(cls, name: str, mode: str = "r", fileobj: BinaryIO | None = None,
             raise tarfile.TarError("visor currently only supports read mode")
 
         try:
-            from gzip import GzipFile  # noqa: PLC0415
+            from gzip import GzipFile
         except ImportError:
             raise tarfile.CompressionError("gzip module is not available") from None
 
         try:
-            from lzma import LZMAError, LZMAFile  # noqa: PLC0415
+            from lzma import LZMAError, LZMAFile
         except ImportError:
             raise tarfile.CompressionError("lzma module is not available") from None
 

pyproject.toml

@@ -105,16 +105,33 @@ select = [
   "SLOT",
   "SIM",
   "TID",
-  "TCH",
+  "TC",
   "PTH",
   "PLC",
   "TRY",
   "FLY",
   "PERF",
   "FURB",
   "RUF",
+  "D"
 ]
-ignore = ["E203", "B904", "UP024", "ANN002", "ANN003", "ANN204", "ANN401", "SIM105", "TRY003"]
+ignore = [
+    "E203", "B904", "UP024", "ANN002", "ANN003", "ANN204", "ANN401", "SIM105", "TRY003", "PLC0415",
+    # Ignore some pydocstyle rules for now as they require a larger cleanup
+    "D1",
+    "D205",
+    "D301",
+    "D417",
+    # Seems bugged: https://github.com/astral-sh/ruff/issues/16824
+    "D402",
+]
+future-annotations = true
+
+[tool.ruff.lint.pydocstyle]
+convention = "google"
+
+[tool.ruff.lint.flake8-type-checking]
+strict = true
 
 [tool.ruff.lint.per-file-ignores]
 "tests/_docs/**" = ["INP001"]
@@ -123,6 +140,7 @@ ignore = ["E203", "B904", "UP024", "ANN002", "ANN003", "ANN204", "ANN401", "SIM1
 [tool.ruff.lint.isort]
 known-first-party = ["dissect.hypervisor"]
 known-third-party = ["dissect"]
+required-imports = ["from __future__ import annotations"]
 
 [tool.setuptools.packages.find]
 include = ["dissect.*"]

tests/_docs/conf.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 project = "dissect.hypervisor"
 
 extensions = [

tests/disk/test_vmdk.py

@@ -197,12 +197,11 @@ def test_vmdk_sesparse() -> None:
     ),
 )
 def test_vmdk_extent_description(extent_description: str, expected_extents: list[ExtentDescriptor]) -> None:
-    """test if we correctly parse VMDK sparse and flat extent descriptions.
+    """Test if we correctly parse VMDK sparse and flat extent descriptions.
 
     Resources:
         - https://github.com/libyal/libvmdk/blob/main/documentation/VMWare%20Virtual%20Disk%20Format%20(VMDK).asciidoc#22-extent-descriptions
     """
-
     descriptor = DiskDescriptor.parse(extent_description)
     assert descriptor.extents == expected_extents