Add stricter Ruff linting #291

acquire/acquire.py

@@ -49,7 +49,7 @@
 from acquire.log import get_file_handler, reconfigure_log_file, setup_logging
 from acquire.outputs import OUTPUTS
 from acquire.uploaders.minio import MinIO
-from acquire.uploaders.plugin import UploaderPlugin, upload_files_using_uploader
+from acquire.uploaders.plugin import upload_files_using_uploader
 from acquire.uploaders.plugin_registry import UploaderRegistry
 from acquire.utils import (
     check_and_set_acquire_args,
@@ -71,6 +71,8 @@
 
     from dissect.target.filesystem import Filesystem
 
+    from acquire.uploaders.plugin import UploaderPlugin
+
 try:
     from acquire.version import version
 except ImportError:
@@ -245,7 +247,7 @@ def wrapper(module_cls: type[Module]) -> type[Module]:
 
 
 def local_module(cls: type[object]) -> object:
-    """A decorator that sets property `__local__` on a module class to mark it for local target only"""
+    """A decorator that sets property `__local__` on a module class to mark it for local target only."""
     cls.__local__ = True
     return cls
 

acquire/collector.py

@@ -681,8 +681,7 @@ def write_bytes(self, destination_path: str, data: bytes) -> None:
 
 
 def get_report_summary(report: CollectionReport) -> str:
-    """Create a table-view report summary with success/failure/missing/empty counters per module"""
-
+    """Create a table-view report summary with success/failure/missing/empty counters per module."""
     record_counts = report.get_counts_per_module_per_outcome()
 
     if not record_counts:
@@ -748,11 +747,9 @@ def get_report_summary(report: CollectionReport) -> str:
 
 
 def get_full_formatted_report(report: CollectionReport, record_indent: int = 4) -> str:
-    """
-    Create a full list of successful / failed / missing / empty artifacts collected,
+    """Create a full list of successful / failed / missing / empty artifacts collected,
     broken down by module.
     """
-
     record_line_template = "{record.outcome}: {record.artifact_type}:{record.artifact_value}"
     blocks = []
 

acquire/dynamic/windows/collect.py

@@ -4,8 +4,8 @@
 from typing import TYPE_CHECKING
 
 from acquire.dynamic.windows.exceptions import AccessDeniedError
-from acquire.dynamic.windows.handles import Handle, get_handles
-from acquire.dynamic.windows.named_objects import NamedObject, NamedObjectType
+from acquire.dynamic.windows.handles import get_handles
+from acquire.dynamic.windows.named_objects import NamedObjectType
 from acquire.dynamic.windows.ntdll import (
     close_handle,
     open_directory_object,
@@ -15,6 +15,9 @@
 if TYPE_CHECKING:
     from collections.abc import Iterator
 
+    from acquire.dynamic.windows.handles import Handle
+    from acquire.dynamic.windows.named_objects import NamedObject
+
 log = getLogger(__name__)
 
 
@@ -24,7 +27,6 @@ def collect_named_objects(path: str = "\\") -> list[NamedObject]:
     Parameters:
         path: point to start searching from
     """
-
     try:
         dir_handle = open_directory_object(dir_name=path, root_handle=None)
     except AccessDeniedError:
@@ -45,7 +47,7 @@ def collect_named_objects(path: str = "\\") -> list[NamedObject]:
 
 
 def collect_open_handles(handle_types: list[NamedObject] | None = None) -> Iterator[Handle]:
-    """Collect open handles
+    """Collect open handles.
 
     Collect open handles and optionally provide a list to explicitly collect specific types of handles.
 

acquire/dynamic/windows/exceptions.py

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

acquire/dynamic/windows/handles.py

@@ -5,7 +5,7 @@
 import gzip
 import io
 import threading
-from logging import Filter, LogRecord, getLogger
+from logging import Filter, getLogger
 from queue import Empty, Queue
 from typing import TYPE_CHECKING
 
@@ -39,6 +39,7 @@
 
 if TYPE_CHECKING:
     from collections.abc import Iterator
+    from logging import LogRecord
 
 log = getLogger(__name__)
 
@@ -164,7 +165,6 @@ def _get_file_name_thread(h_file: HANDLE, queue: Queue) -> None:
 
 def get_handle_name(pid: int, handle: SYSTEM_HANDLE_TABLE_ENTRY_INFO_EX) -> str | None:
     """Return handle name."""
-
     remote = pid != GetCurrentProcessId()
 
     if remote:
@@ -268,7 +268,6 @@ def serialize_handles_into_csv(rows: Iterator[Handle], compress: bool = True) ->
     Serialize provided rows into normal or gzip-compressed CSV, and return a tuple
     containing the result bytes.
     """
-
     raw_buffer = io.BytesIO()
 
     buffer = gzip.GzipFile(fileobj=raw_buffer, mode="wb") if compress else raw_buffer

acquire/dynamic/windows/ntdll.py

@@ -93,9 +93,11 @@ class ACCESS_MASK(IntFlag):
 
 
 class OBJ_ATTR(IntFlag):
-    """
-    https://github.com/tpn/winsdk-10/blob/master/Include/10.0.10240.0/shared/ntdef.h
-    https://docs.microsoft.com/en-us/windows-hardware/drivers/kernel/object-handles
+    """Drivers object handles values.
+
+    References:
+        - https://github.com/tpn/winsdk-10/blob/master/Include/10.0.10240.0/shared/ntdef.h
+        - https://docs.microsoft.com/en-us/windows-hardware/drivers/kernel/object-handles
     """
 
     OBJ_INHERIT = 0x00000002
@@ -169,7 +171,7 @@ def close_handle(handle: HANDLE) -> None:
 
 
 def validate_ntstatus(status: NTSTATUS) -> None:
-    """Validates the result status of a Nt call
+    """Validates the result status of a Nt call.
 
     Parameters:
         status: the return value of a ntcall
@@ -189,7 +191,6 @@ def open_directory_object(dir_name: str, root_handle: HANDLE = None) -> HANDLE:
         dir_name: Specific directory we want to try and open.
         root_handle: From which point we want to start querying the object.
     """
-
     object_name = UNICODE_STRING.from_str(dir_name)
     p_name = ctypes.pointer(object_name)
 

acquire/dynamic/windows/types.py

@@ -167,7 +167,7 @@ class TOKEN_PRIVILEGES(ctypes.Structure):
 
 
 class Handle:
-    """Handle object"""
+    """Handle object."""
 
     def __init__(self, handle: SYSTEM_HANDLE_TABLE_ENTRY_INFO_EX, handle_type: str, handle_name: str) -> None:
         self.name = handle_name

acquire/gui/__init__.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 from acquire.gui.base import GUI, GUIError
 
 __all__ = ["GUI", "GUIError"]

acquire/hashes.py

@@ -46,8 +46,7 @@ def get_paths_from_dir(
     glob: str,
     extensions: set[str] | None = None,
 ) -> Iterator[Path]:
-    """Yield paths that match provided `glob` pattern and `extensions` values"""
-
+    """Yield paths that match provided `glob` pattern and `extensions` values."""
     extension_suffixes = {f".{ext}" for ext in extensions} if extensions else None
 
     for path in target.fs.path("/").glob(glob):
@@ -57,13 +56,11 @@ def get_paths_from_dir(
 
 
 def get_path_details(path: TargetPath, hash_funcs: Iterator[HashFunc] | None = None) -> tuple:
-    """
-    Calculate and return the details for specified path.
+    """Calculate and return the details for specified path.
 
     The details include file size and hashes, calculated for
     hash functions provided in `hash_funcs`.
     """
-
     hash_funcs = hash_funcs or []
     if hash_funcs:
         provided_hash_funcs_sorted = sorted(set(hash_funcs))
@@ -84,7 +81,7 @@ def get_path_details(path: TargetPath, hash_funcs: Iterator[HashFunc] | None = N
 
 
 def filter_out_nonfiles(paths: Iterator[Path]) -> Iterator[Path]:
-    """Filter out paths that are not files"""
+    """Filter out paths that are not files."""
     for path in paths:
         try:
             is_file = path.is_file()
@@ -99,7 +96,7 @@ def filter_out_nonfiles(paths: Iterator[Path]) -> Iterator[Path]:
 
 
 def filter_out_huge_files(paths: Iterator[Path], *, max_size_bytes: int) -> Iterator[Path]:
-    """Filter out paths that are larger than `max_size_bytes` value"""
+    """Filter out paths that are larger than `max_size_bytes` value."""
     for path in paths:
         try:
             file_size = path.stat().st_size
@@ -119,8 +116,7 @@ def filter_out_by_value_match(
     value: bytes,
     offsets: Iterator[int] = (0,),
 ) -> Iterator[Path]:
-    """Filter out paths where file data matches the provided `value` at the specified offsets"""
-
+    """Filter out paths where file data matches the provided `value` at the specified offsets."""
     if not offsets:
         raise ValueError("No offsets provided")
 
@@ -148,7 +144,7 @@ def filter_out_by_path_match(
     re_pattern: str,
     re_flags: re.RegexFlag = re.IGNORECASE,
 ) -> Iterator[Path]:
-    """Filter out paths that match provided regex pattern"""
+    """Filter out paths that match provided regex pattern."""
     pattern = re.compile(re_pattern, flags=re_flags)
     return filter(lambda p: not pattern.match(str(p)), paths)
 
@@ -158,8 +154,7 @@ def collect_hashes(
     specs: Iterator[Iterator[tuple]],
     path_filters: Iterator[Callable[[Iterator[Path]], Iterator[Path]]] | None = None,
 ) -> Iterator[tuple]:
-    """
-    Walk through the paths, calculate hashes and return details per path.
+    """Walk through the paths, calculate hashes and return details per path.
 
     Spec contains a path selector and a list of hash functions to compute against the paths.
     For example::
@@ -169,7 +164,6 @@ def collect_hashes(
             (HashFunc.MD5, HashFunc.SHA1),
         ]
     """
-
     log.info("Starting to collect hashes for spec: %s", specs)
 
     stream_hash_func_pairs = []
@@ -225,11 +219,9 @@ def collect_hashes(
 
 
 def serialize_into_csv(rows: Iterator[list], compress: bool = True) -> tuple[int, bytes]:
-    """
-    Serialize provided rows into normal or gzip-compressed CSV, and return a tuple
+    """Serialize provided rows into normal or gzip-compressed CSV, and return a tuple
     containing the number of rows processed and the result bytes.
     """
-
     raw_buffer = io.BytesIO()
 
     counter = 0

acquire/outputs/__init__.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 from acquire.outputs.dir import DirectoryOutput
 from acquire.outputs.tar import TAR_COMPRESSION_METHODS, TarOutput
 from acquire.outputs.zip import ZIP_COMPRESSION_METHODS, ZipOutput

acquire/outputs/base.py

@@ -70,7 +70,6 @@ def write_bytes(
             entry: The optional filesystem entry to write.
             size: The optional file size in bytes of the entry to write.
         """
-
         stream = io.BytesIO(data)
         self.write(output_path, stream, entry=entry, size=size)
 

acquire/outputs/zip.py

@@ -111,7 +111,6 @@ def close(self) -> None:
 
     def _get_external_attr(self, entry: FilesystemEntry) -> int:
         """Return the appropriate external attributes of the entry."""
-
         # The Python zipfile module accepts the 16-bit "Mode" field (that stores st_mode field from
         # struct stat, containing user/group/other permissions, setuid/setgid and symlink info, etc) of the
         # ASi extra block for Unix as bits 16-31 of the external_attr

acquire/tools/decrypter.py

@@ -16,7 +16,6 @@
 from datetime import datetime, timezone
 from pathlib import Path
 from queue import Empty as QueueEmptyError
-from queue import Queue
 from typing import TYPE_CHECKING, BinaryIO
 from urllib import request
 from urllib.error import HTTPError
@@ -62,6 +61,7 @@
 
 if TYPE_CHECKING:
     from collections.abc import Iterator
+    from queue import Queue
     from threading import Event
 
 log = logging.getLogger(__name__)

acquire/uploaders/minio.py

@@ -18,7 +18,6 @@ def __init__(self, upload: dict[str, str], **kwargs: dict[str, Any]) -> None:
         Raises:
             ValueError: When the configuration is invalid.
         """
-
         self.endpoint = upload.get("endpoint")
         self.access_id = upload.get("access_id")
         self.access_key = upload.get("access_key")

acquire/uploaders/plugin_registry.py

@@ -53,7 +53,7 @@ def remove(self, name: str) -> None:
         self.plugins.pop(name)
 
     def items(self) -> ItemsView[str, T]:
-        """Returns all the items inside the ``plugins`` dictionary"""
+        """Returns all the items inside the ``plugins`` dictionary."""
         return self.plugins.items()
 
     def get(self, name: str) -> T:

acquire/utils.py

@@ -31,7 +31,7 @@
 
 
 class StrEnum(str, Enum):
-    """Sortable and serializible string-based enum"""
+    """Sortable and serializible string-based enum."""
 
 
 def _create_profile_information(profiles: dict) -> str:

pyproject.toml

@@ -78,6 +78,9 @@ acquire-decrypt = "acquire.tools.decrypter:main"
 line-length = 120
 required-version = ">=0.13.1"
 
+# Exclude setuptools_scm autogenerated file from linting
+extend-exclude = ["acquire/version.py"]
+
 [tool.ruff.format]
 docstring-code-format = true
 
@@ -107,22 +110,40 @@ 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 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",
 ]
-ignore = ["E203", "B904", "UP024", "ANN002", "ANN003", "ANN204", "ANN401", "SIM105", "TRY003"]
+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"]
 
 [tool.ruff.lint.isort]
 known-first-party = ["acquire"]
+required-imports = ["from __future__ import annotations"]
 
 [tool.setuptools.packages.find]
 include = ["acquire", "acquire.*"]

tests/_docs/conf.py

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