flake8, bugbear, pyupgrade → ruff (#9147)

Co-authored-by: Jacob Tomlinson <[email protected]>

Author: DimitriPapadopoulos

.flake8

@@ -1,35 +1,22 @@
-# NOTE: autoupdate does not pick up flake8-bugbear since it is a transitive
-#  dependency. Make sure to update flake8-bugbear manually on a regular basis.
 repos:
   - repo: https://github.com/MarcoGorelli/absolufy-imports
     rev: v0.3.1
     hooks:
       - id: absolufy-imports
         name: absolufy-imports
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.14.5
+    hooks:
+      - id: ruff-check
   - repo: https://github.com/pycqa/isort
     rev: 5.13.2
     hooks:
       - id: isort
         language_version: python3
-  - repo: https://github.com/asottile/pyupgrade
-    rev: v3.17.0
-    hooks:
-      - id: pyupgrade
-        args:
-          - --py39-plus
   - repo: https://github.com/psf/black-pre-commit-mirror
     rev: 25.11.0
     hooks:
       - id: black
-  - repo: https://github.com/pycqa/flake8
-    rev: 7.1.1
-    hooks:
-      - id: flake8
-        language_version: python3
-        additional_dependencies:
-        # NOTE: autoupdate does not pick up flake8-bugbear since it is a transitive
-        #  dependency. Make sure to update flake8-bugbear manually on a regular basis.
-          - flake8-bugbear==24.8.19
   - repo: https://github.com/codespell-project/codespell
     rev: v2.3.0
     hooks:

.pre-commit-config.yaml

@@ -41,9 +41,9 @@ def _python_exit():
     global _shutdown
     _shutdown = True
     items = list(_threads_queues.items())
-    for t, q in items:
+    for _, q in items:
         q.put(None)
-    for t, q in items:
+    for t, _ in items:
         t.join()
 
 

distributed/_concurrent_futures_thread.py

@@ -436,8 +436,7 @@ class Suggestion(NamedTuple):
 
 
 if TYPE_CHECKING:
-    # TODO import from typing (requires Python >=3.10)
-    from typing_extensions import TypeAlias
+    from typing import TypeAlias
 
 SuggestionGenerator: TypeAlias = Generator[
     Suggestion, Union["scheduler_module.WorkerState", None], None

distributed/active_memory_manager.py

@@ -30,7 +30,7 @@ def _cascade_future(future, cf_future):
         try:
             typ, exc, tb = result
             raise exc.with_traceback(tb)
-        except BaseException as exc:  # noqa: B036
+        except BaseException as exc:
             cf_future.set_exception(exc)
 
 

distributed/cfexecutor.py

@@ -189,11 +189,7 @@ def main(
     import distributed
 
     print("\n---------------------------------------------------------------")
-    print(
-        "                 Dask.distributed v{version}\n".format(
-            version=distributed.__version__
-        )
-    )
+    print(f"                 Dask.distributed v{distributed.__version__}\n")
     print(f"Worker nodes: {len(hostnames)}")
     for i, host in enumerate(hostnames):
         print(f"  {i}: {host}")

distributed/cli/dask_ssh.py

@@ -17,7 +17,14 @@
 import warnings
 import weakref
 from collections import defaultdict
-from collections.abc import Collection, Coroutine, Iterable, Iterator, Sequence
+from collections.abc import (
+    Callable,
+    Collection,
+    Coroutine,
+    Iterable,
+    Iterator,
+    Sequence,
+)
 from concurrent.futures import ThreadPoolExecutor
 from concurrent.futures._base import DoneAndNotDoneFutures
 from contextlib import asynccontextmanager, contextmanager, suppress
@@ -29,7 +36,6 @@
 from typing import (
     TYPE_CHECKING,
     Any,
-    Callable,
     ClassVar,
     Generic,
     Literal,
@@ -125,7 +131,7 @@
 from distributed.worker import get_client, get_worker, secede
 
 if TYPE_CHECKING:
-    from typing_extensions import TypeAlias
+    from typing import TypeAlias
 
 logger = logging.getLogger(__name__)
 
@@ -1121,9 +1127,7 @@ def __init__(
                 security = getattr(self.cluster, "security", None)
         elif address is not None and not isinstance(address, str):
             raise TypeError(
-                "Scheduler address must be a string or a Cluster instance, got {}".format(
-                    type(address)
-                )
+                f"Scheduler address must be a string or a Cluster instance, got {type(address)}"
             )
 
         # If connecting to an address and no explicit security is configured, attempt
@@ -1375,10 +1379,7 @@ def __repr__(self):
             return text
 
         elif self.scheduler is not None:
-            return "<{}: scheduler={!r}>".format(
-                self.__class__.__name__,
-                self.scheduler.address,
-            )
+            return f"<{self.__class__.__name__}: scheduler={self.scheduler.address!r}>"
         else:
             return f"<{self.__class__.__name__}: No scheduler connected>"
 
@@ -2368,7 +2369,7 @@ async def _gather(self, futures, errors="raise", direct=None, local_worker=None)
                 "Cannot gather Futures created by another client. "
                 f"These are the {len(mismatched_futures)} (out of {len(futures)}) "
                 f"mismatched Futures and their client IDs (this client is {self.id}): "
-                f"{ {f: f.client.id for f in mismatched_futures} }"  # noqa: E201, E202
+                f"{ {f: f.client.id for f in mismatched_futures} }"
             )
         keys = [future.key for future in future_set]
         bad_data = dict()
@@ -5892,8 +5893,8 @@ def count(self):
             return len(self.futures) + len(self.queue.queue)
 
     def __repr__(self):
-        return "<as_completed: waiting={} done={}>".format(
-            len(self.futures), len(self.queue.queue)
+        return (
+            f"<as_completed: waiting={len(self.futures)} done={len(self.queue.queue)}>"
         )
 
     def __iter__(self):

distributed/client.py

@@ -151,9 +151,8 @@ def update(self):
             "escaped_worker": [url_escape(w) for w in worker],
         }
 
-        self.memory_figure.title.text = "GPU Memory: {} / {}".format(
-            format_bytes(sum(memory)),
-            format_bytes(memory_total),
+        self.memory_figure.title.text = (
+            f"GPU Memory: {format_bytes(sum(memory))} / {format_bytes(memory_total)}"
         )
         self.memory_figure.x_range.end = memory_max
 

distributed/dashboard/components/nvml.py

@@ -1,10 +1,10 @@
 from __future__ import annotations
 
 import logging
-from collections.abc import Hashable
+from collections.abc import Callable, Hashable
 from datetime import timedelta
 from inspect import isawaitable
-from typing import TYPE_CHECKING, Any, Callable, Literal, cast
+from typing import TYPE_CHECKING, Any, Literal, cast
 
 from tornado.ioloop import IOLoop
 
@@ -18,7 +18,7 @@
 from distributed.utils import log_errors
 
 if TYPE_CHECKING:
-    from typing_extensions import TypeAlias
+    from typing import TypeAlias
 
     import distributed
     from distributed.deploy.cluster import Cluster

distributed/deploy/adaptive.py

@@ -2,7 +2,6 @@
 
 import logging
 import os
-import socket
 import sys
 import traceback
 import warnings
@@ -136,7 +135,7 @@ def read_from_stdout():
                     )
                 )
                 line = stdout.readline()
-        except (PipeTimeout, socket.timeout):
+        except (TimeoutError, PipeTimeout):
             pass
 
     def read_from_stderr():
@@ -155,7 +154,7 @@ def read_from_stderr():
                     + bcolors.ENDC
                 )
                 line = stderr.readline()
-        except (PipeTimeout, socket.timeout):
+        except (TimeoutError, PipeTimeout):
             pass
 
     def communicate():
@@ -208,16 +207,12 @@ def communicate():
 def start_scheduler(
     logdir, addr, port, ssh_username, ssh_port, ssh_private_key, remote_python=None
 ):
-    cmd = "{python} -m distributed.cli.dask_scheduler --port {port}".format(
-        python=remote_python or sys.executable, port=port
-    )
+    cmd = f"{remote_python or sys.executable} -m distributed.cli.dask_scheduler --port {port}"
 
     # Optionally re-direct stdout and stderr to a logfile
     if logdir is not None:
         cmd = f"mkdir -p {logdir} && {cmd}"
-        cmd += "&> {logdir}/dask_scheduler_{addr}:{port}.log".format(
-            addr=addr, port=port, logdir=logdir
-        )
+        cmd += f"&> {logdir}/dask_scheduler_{addr}:{port}.log"
 
     # Format output labels we can prepend to each line of output, and create
     # a 'status' key to keep track of jobs that terminate prematurely.
@@ -297,16 +292,11 @@ def start_worker(
     )
 
     if local_directory is not None:
-        cmd += " --local-directory {local_directory}".format(
-            local_directory=local_directory
-        )
+        cmd += f" --local-directory {local_directory}"
 
     # Optionally redirect stdout and stderr to a logfile
     if logdir is not None:
-        cmd = f"mkdir -p {logdir} && {cmd}"
-        cmd += "&> {logdir}/dask_scheduler_{addr}.log".format(
-            addr=worker_addr, logdir=logdir
-        )
+        cmd = f"mkdir -p {logdir} && {cmd}&> {logdir}/dask_scheduler_{worker_addr}.log"
 
     label = f"worker {worker_addr}"
 
@@ -401,10 +391,8 @@ def __init__(
                 "dask-ssh_" + datetime.datetime.now().strftime("%Y-%m-%d_%H:%M:%S"),
             )
             print(
-                bcolors.WARNING + "Output will be redirected to logfiles "
-                'stored locally on individual worker nodes under "{logdir}".'.format(
-                    logdir=logdir
-                )
+                bcolors.WARNING
+                + f'Output will be redirected to logfiles stored locally on individual worker nodes under "{logdir}".'
                 + bcolors.ENDC
             )
         self.logdir = logdir