ruff: enable ruff isort and other rules (#470)

* ruff: enable ruff isort and other rules

* Update pyproject.toml

.github/dependabot.yml

@@ -7,23 +7,10 @@ updates:
       interval: "weekly"
     labels:
       - "maintenance"
-    # Update via cruft
-    ignore:
-      - dependency-name: "mkdocs*"
-      - dependency-name: "pytest*"
-      - dependency-name: "pylint"
-      - dependency-name: "mypy"
 
   - directory: "/"
     package-ecosystem: "github-actions"
     schedule:
       interval: "weekly"
     labels:
       - "maintenance"
-    # Update via cruft
-    ignore:
-      - dependency-name: "actions/checkout"
-      - dependency-name: "actions/setup-python"
-      - dependency-name: "pypa/gh-action-pypi-publish"
-      - dependency-name: "codecov/codecov-action"
-      - dependency-name: "peter-evans/create-pull-request"

.github/workflows/benchmark.yml

@@ -21,18 +21,18 @@ jobs:
     env:
       PYTEST_BENCHMARK_STORAGE: file://${{ github.workspace }}/.benchmarks
     steps:
-    - name: Set up Python 3.10
-      uses: actions/setup-python@v4
+    - name: Set up Python 3.11
+      uses: actions/setup-python@v5
       with:
-        python-version: '3.10'
+        python-version: '3.11'
 
-    - uses: actions/checkout@v3
+    - uses: actions/checkout@v4
       with:
         ref: ${{ github.event.pull_request.base.sha }}
         fetch-depth: 0
         path: base
 
-    - uses: actions/checkout@v3
+    - uses: actions/checkout@v4
       with:
         fetch-depth: 0
         path: pr

.github/workflows/release.yml

@@ -21,10 +21,10 @@ jobs:
       with:
         fetch-depth: 0
 
-    - name: Set up Python 3.10
-      uses: actions/setup-python@v4
+    - name: Set up Python 3.11
+      uses: actions/setup-python@v5
       with:
-        python-version: '3.10'
+        python-version: '3.11'
 
     - name: Upgrade pip and nox
       run: |

.github/workflows/tests.yml

@@ -32,7 +32,7 @@ jobs:
         fetch-depth: 0
 
     - name: Set up Python ${{ matrix.pyv }}
-      uses: actions/setup-python@v4
+      uses: actions/setup-python@v5
       with:
         python-version: ${{ matrix.pyv }}
 
@@ -49,7 +49,7 @@ jobs:
       run: nox -s tests-${{ matrix.nox_pyv || matrix.pyv }} -- --cov-report=xml
 
     - name: Upload coverage report
-      uses: codecov/codecov-action@v3.1.4
+      uses: codecov/codecov-action@v3
 
     - name: Build package
       run: nox -s build

.pre-commit-config.yaml

@@ -2,7 +2,7 @@ default_language_version:
   python: python3
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.4.0
+    rev: v4.5.0
     hooks:
       - id: check-added-large-files
       - id: check-case-conflict
@@ -20,18 +20,18 @@ repos:
       - id: sort-simple-yaml
       - id: trailing-whitespace
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: 'v0.1.5'
+    rev: 'v0.1.7'
     hooks:
       - id: ruff
         args: [--fix, --exit-non-zero-on-fix]
       - id: ruff-format
   - repo: https://github.com/codespell-project/codespell
-    rev: v2.2.5
+    rev: v2.2.6
     hooks:
       - id: codespell
         additional_dependencies: ["tomli"]
   - repo: https://github.com/asottile/pyupgrade
-    rev: v3.10.1
+    rev: v3.15.0
     hooks:
       - id: pyupgrade
         args: [--py38-plus]

pyproject.toml

@@ -6,7 +6,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "dvc-data"
-description = "dvc data"
+description = "DVC's data management subsystem"
 readme = "README.rst"
 license = {text = "Apache-2.0"}
 authors = [{ name = "Iterative", email = "support@dvc.org" }]
@@ -44,12 +44,12 @@ all = [
     "dvc-data[cli]",
 ]
 tests = [
-    "pytest==7.2.0",
-    "pytest-sugar==0.9.6",
-    "pytest-cov==4.0.0",
-    "pytest-mock==3.10.0",
-    "pytest-benchmark==4.0.0",
-    "mypy==1.5.1",
+    "pytest<8,>=7",
+    "pytest-sugar",
+    "pytest-cov>=4.1.0",
+    "pytest-mock",
+    "pytest-benchmark",
+    "mypy==1.7.1",
     "pytest-servers[s3]==0.1.3",
 ]
 dev = [
@@ -62,7 +62,7 @@ dev = [
 dvc-data = "dvc_data.__main__:main"
 
 [tool.setuptools.package-data]
-dvc_objects = ["py.typed"]
+dvc_data = ["py.typed"]
 
 [tool.setuptools.packages.find]
 where = ["src"]
@@ -121,3 +121,81 @@ module = [
 
 [tool.codespell]
 ignore-words-list = "fo"
+
+[tool.ruff]
+ignore = [
+    "ISC001", # single-line-implicit-string-concatenation
+    "PLR2004", # magic-value-comparison
+    "PLW2901", # redefined-loop-name
+    "RET501", # unnecessary-return-none
+    "RET502", # implicit-return-value
+    "RET503", # implicit-return
+    "S101", # assert
+    "SIM105", # suppressible-exception
+    "SIM108", # if-else-block-instead-of-if-exp
+    "SIM117", # multiple-with-statements
+]
+select = [
+    "A", # flake8-buitlins
+    "ASYNC", # flake8-async
+    "B", # flake8-bugbear
+    "BLE", # flake8-blind-except
+    "C4", # flake8-comprehensions
+    "C90", # mccabe
+    "DTZ", # flake8-datetimez
+    "E", # pycodestyle - Error
+    "EXE", # flake8-executable
+    "F", # pyflakes
+    "FLY", # flynt-rules
+    "G", # flake8-logging-format
+    "I", # isort
+    "ICN", # flake8-import-conventions
+    "INP", # flake8-no-pep420
+    "ISC", # flake8-implicit-str-concat
+    "N", # pep8-naming
+    "PERF101", # perflint
+    "PGH", # pygrep-hooks
+    "PIE", # flake8-pie
+    "PL", # pylint
+    "PT", # flake8-pytest-style
+    "PYI", # flake8-pyi
+    "Q", # flae8-quotes
+    "RET", # flake8-return
+    "RSE", # flake8-raise
+    "RUF", # ruff
+    "S", # flake8-bandit
+    "SIM", # flake8-simplify
+    "SLOT", # flake8-slots
+    "T10", # flake8-debugger
+    "T20", # flake8-print
+    "TCH", # flake8-type-checking
+    "TCH", # flake8-type-checking
+    "TID", # flake8-tidy-imports
+    "UP", # pyupgrade
+    "W", # pycodestyle - Warning
+    "YTT", # flake8-2020
+]
+show-source = true
+show-fixes = true
+
+[tool.ruff.lint.flake8-pytest-style]
+fixture-parentheses = false
+mark-parentheses = false
+parametrize-names-type = "csv"
+
+[tool.ruff.lint.flake8-tidy-imports]
+[tool.ruff.lint.flake8-tidy-imports.banned-api]
+"funcy.cached_property" = {msg = "use `from dvc_data.utils import cached_property` instead."}
+"functools.cached_property" = {msg = "use `from dvc_data.utils import cached_property` instead."}
+
+[tool.ruff.lint.flake8-type-checking]
+strict = true
+
+[tool.ruff.lint.isort]
+known-first-party = ["dvc_data"]
+
+[tool.ruff.lint.pylint]
+max-args = 10
+
+[tool.ruff.per-file-ignores]
+"src/dvc_data/cli.py" = ["T201", "B008"]

src/dvc_data/__main__.py

@@ -5,7 +5,7 @@
     def main():  # type: ignore[misc]
         import sys
 
-        print(
+        print(  # noqa: T201
             "dvc-data could not run because the required "
             "dependencies are not installed.\n"
             "Please install it with: pip install 'dvc-data[cli]'"

src/dvc_data/cli.py

@@ -13,7 +13,7 @@
 from typing import List, cast
 
 import click
-import typer  # pylint: disable=import-error
+import typer
 from attrs import asdict
 from dvc_objects._tqdm import Tqdm
 from dvc_objects.errors import ObjectFormatError
@@ -34,10 +34,9 @@
 from dvc_data.hashfile.obj import HashFile
 from dvc_data.hashfile.state import State
 from dvc_data.hashfile.transfer import transfer as _transfer
-from dvc_data.hashfile.tree import Tree
+from dvc_data.hashfile.tree import Tree, merge
 from dvc_data.hashfile.tree import du as _du
-from dvc_data.hashfile.tree import merge
-from dvc_data.repo import NotARepo, Repo
+from dvc_data.repo import NotARepoError, Repo
 
 install(show_locals=True, suppress=[typer, click])
 
@@ -224,9 +223,9 @@ def from_shortoid(odb: HashFileDB, oid: str) -> str:
 def get_odb(**config):
     try:
         repo = Repo.discover()
-    except NotARepo as exc:
+    except NotARepoError as exc:
         typer.echo(exc, err=True)
-        raise typer.Abort(1)
+        raise typer.Abort(1)  # noqa: B904
 
     if "state" not in config:
         config.setdefault("state", State(root_dir=repo.root, tmp_dir=repo.tmp_dir))
@@ -324,7 +323,7 @@ def show(oid: str = typer.Argument(..., allow_dash=True)):
     obj = load(odb, odb.get(oid).hash_info)
     if isinstance(obj, Tree):
         return _ls_tree(obj)
-    elif isinstance(obj, HashFile):
+    if isinstance(obj, HashFile):
         return _cat_object(odb, obj.oid)
     raise AssertionError(f"unknown object of type {type(obj)}")
 
@@ -429,14 +428,15 @@ def merge_tree(oid1: str, oid2: str, force: bool = False):
     oid2 = from_shortoid(odb, oid2)
     obj1 = load(odb, odb.get(oid1).hash_info)
     obj2 = load(odb, odb.get(oid2).hash_info)
-    assert isinstance(obj1, Tree) and isinstance(obj2, Tree), "not a tree obj"
+    assert isinstance(obj1, Tree)
+    assert isinstance(obj2, Tree), "not a tree obj"
 
     if not force:
         # detect conflicts
         d = _diff(obj1, obj2, odb)
         modified = [
             posixpath.join(*change.old.key)
-            for change in d.modified  # pylint: disable=not-an-iterable
+            for change in d.modified
             if change.old.key != ROOT
         ]
         if modified:
@@ -478,7 +478,6 @@ def apply_op(odb, obj, application):
     op = application["op"]
     path = application["path"]
     keys = tuple(path.split("/"))
-    # pylint: disable=protected-access
     if op in ("add", "modify"):
         new = tuple(application["to"].split("/"))
         if op == "add" and new in obj._dict:
@@ -594,7 +593,7 @@ def checkout(
     path: Path = typer.Argument(..., resolve_path=True),
     relink: bool = False,
     force: bool = False,
-    type: List[LinkEnum] = typer.Option(["copy"]),  # pylint: disable=redefined-builtin
+    type: List[LinkEnum] = typer.Option(["copy"]),  # noqa: A002
 ):
     odb = get_odb(type=[t.value for t in type])
     oid = from_shortoid(odb, oid)

src/dvc_data/fs.py

@@ -9,15 +9,15 @@
 from dvc_objects.fs.callbacks import DEFAULT_CALLBACK
 from fsspec import AbstractFileSystem
 
-from dvc_data.hashfile.db import HashFileDB
-
 from .utils import cached_property
 
 if typing.TYPE_CHECKING:
     from dvc_objects.fs.base import AnyFSPath, FileSystem
     from dvc_objects.fs.callbacks import Callback
     from dvc_objects.fs.path import Path
 
+    from dvc_data.hashfile.db import HashFileDB
+
     from .hashfile.hash_info import HashInfo
     from .index import DataIndex, DataIndexEntry, ObjectStorage
 
@@ -33,7 +33,7 @@ class FileInfo(NamedTuple):
     fs_path: "AnyFSPath"
 
 
-class DataFileSystem(AbstractFileSystem):  # pylint:disable=abstract-method
+class DataFileSystem(AbstractFileSystem):
     root_marker = "/"
 
     def __init__(self, index: "DataIndex", **kwargs: Any):
@@ -55,7 +55,7 @@ def _get_key(self, path: str) -> Tuple[str, ...]:
             return ()
 
         key = self.path.relparts(path, self.root_marker)
-        if key == (".",) or key == ("",):
+        if key in ((".",), ("",)):
             key = ()
 
         return key
@@ -108,9 +108,7 @@ def _cache_remote_file(
         odb.add(path, fs, oid)
         return odb.fs, odb.oid_to_path(oid)
 
-    def _open(  # pylint: disable=arguments-differ
-        self, path: "AnyFSPath", **kwargs: Any
-    ) -> "BinaryIO":
+    def _open(self, path: "AnyFSPath", **kwargs: Any) -> "BinaryIO":
         typ, _, cache_storage, hi, fs, fspath = self._get_fs_path(path)
 
         if kwargs.get("cache", False) and typ == "remote" and cache_storage:
@@ -156,7 +154,7 @@ def info(self, path: "AnyFSPath", **kwargs: Any):
         info["name"] = path
         return info
 
-    def get_file(  # pylint: disable=arguments-differ
+    def get_file(
         self,
         rpath: "AnyFSPath",
         lpath: "AnyFSPath",

src/dvc_data/hashfile/_ignore.py

@@ -5,8 +5,6 @@
 if TYPE_CHECKING:
     from dvc_objects.fs.base import AnyFSPath, FileSystem
 
-# pylint: disable=unused-argument
-
 
 class Ignore(Protocol):
     def find(self, fs: "FileSystem", path: "AnyFSPath") -> Iterator["AnyFSPath"]: