Run pyupgrade 2.31.0. (#10141)

This PR runs [pyupgrade](https://github.com/asottile/pyupgrade) to modernize some syntax in the Python code base. (I am preparing a "better code" talk for our team that will reference this PR.)

The kinds of modernizing changes that pyupgrade makes are similar in purpose to those made by clang-tidy (#9860), but for Python. These include things like:
- Using literals for empty dicts `{}` and lists `[]`, because they are a bit faster and more readable than `dict()` or `list()`
- Removing extra parentheses or braces wrapping generator expressions if not needed
- Preferring format strings
- Using canonical error names, e.g. `IOError` became an alias for `OSError` in Python 3.3.
- Replacing the "new-style" class definitions like `class A(object):` with the simpler syntax `class A:`
- Removing unnecessary `__future__` imports that were needed for Python 2 compatibility, like `print_function` and `division`
- Using raw strings for regular expressions, to clarify intent and avoid extra escaping

The [pyupgrade README](https://github.com/asottile/pyupgrade) has a long showcase of other rules.

Notes for reviewers:
- pyupgrade has a lot of opinions on how to use type annotations, and I'm not sure if I like all of them (some may have compatibility issues?). I have skipped over the type annotations for now, to set a more reasonable scope for this PR. See commit 54b16b9 (since reverted) for examples. Please let me know what you think about these changes and I may investigate them further in a follow-up PR!
- I have not added this tool to our CI style checks via a pre-commit hook yet. That can be done in a follow-up PR if we agree that we would like these types of changes to be required in the future.
- I used the argument `--py37-plus` to only perform changes that are compatible with Python 3.7+.
- I can revert the changes to the vendored code in `versioneer.py` if desired. (It's pretty outdated anyway, it looks like we're using versioneer 0.18, released on January 1, 2017.)

Authors:
  - Bradley Dice (https://github.com/bdice)

Approvers:
  - Vyas Ramasubramani (https://github.com/vyasr)
  - Charles Blackmon-Luca (https://github.com/charlesbluca)
  - AJ Schmidt (https://github.com/ajschmidt8)

URL: #10141

Author: bdice

ci/utils/nbtestlog2junitxml.py

@@ -7,11 +7,11 @@
 from enum import Enum
 
 
-startingPatt = re.compile("^STARTING: ([\w\.\-]+)$")
-skippingPatt = re.compile("^SKIPPING: ([\w\.\-]+)\s*(\(([\w\.\-\ \,]+)\))?\s*$")
-exitCodePatt = re.compile("^EXIT CODE: (\d+)$")
-folderPatt = re.compile("^FOLDER: ([\w\.\-]+)$")
-timePatt = re.compile("^real\s+([\d\.ms]+)$")
+startingPatt = re.compile(r"^STARTING: ([\w\.\-]+)$")
+skippingPatt = re.compile(r"^SKIPPING: ([\w\.\-]+)\s*(\(([\w\.\-\ \,]+)\))?\s*$")
+exitCodePatt = re.compile(r"^EXIT CODE: (\d+)$")
+folderPatt = re.compile(r"^FOLDER: ([\w\.\-]+)$")
+timePatt = re.compile(r"^real\s+([\d\.ms]+)$")
 linePatt = re.compile("^" + ("-" * 80) + "$")
 
 

cpp/scripts/run-clang-format.py

@@ -13,7 +13,6 @@
 # limitations under the License.
 #
 
-from __future__ import print_function
 
 import argparse
 import os
@@ -124,19 +123,19 @@ def run_clang_format(src, dst, exe, verbose, inplace):
         os.makedirs(dstdir)
     # run the clang format command itself
     if src == dst:
-        cmd = "%s -i %s" % (exe, src)
+        cmd = f"{exe} -i {src}"
     else:
-        cmd = "%s %s > %s" % (exe, src, dst)
+        cmd = f"{exe} {src} > {dst}"
     try:
         subprocess.check_call(cmd, shell=True)
     except subprocess.CalledProcessError:
         print("Failed to run clang-format! Maybe your env is not proper?")
         raise
     # run the diff to check if there are any formatting issues
     if inplace:
-        cmd = "diff -q %s %s >/dev/null" % (src, dst)
+        cmd = f"diff -q {src} {dst} >/dev/null"
     else:
-        cmd = "diff %s %s" % (src, dst)
+        cmd = f"diff {src} {dst}"
 
     try:
         subprocess.check_call(cmd, shell=True)

cpp/scripts/run-clang-tidy.py

@@ -13,7 +13,6 @@
 # limitations under the License.
 #
 
-from __future__ import print_function
 import re
 import os
 import subprocess
@@ -67,7 +66,7 @@ def parse_args():
 
 
 def get_all_commands(cdb):
-    with open(cdb, "r") as fp:
+    with open(cdb) as fp:
         return json.load(fp)
 
 
@@ -195,10 +194,10 @@ def collect_result(result):
 
 def print_result(passed, stdout, file):
     status_str = "PASSED" if passed else "FAILED"
-    print("%s File:%s %s %s" % (SEPARATOR, file, status_str, SEPARATOR))
+    print(f"{SEPARATOR} File:{file} {status_str} {SEPARATOR}")
     if stdout:
         print(stdout)
-        print("%s File:%s ENDS %s" % (SEPARATOR, file, SEPARATOR))
+        print(f"{SEPARATOR} File:{file} ENDS {SEPARATOR}")
 
 
 def print_results():

cpp/scripts/sort_ninja_log.py

@@ -33,7 +33,7 @@
 
 # build a map of the log entries
 entries = {}
-with open(log_file, "r") as log:
+with open(log_file) as log:
     last = 0
     files = {}
     for line in log:

docs/cudf/source/conf.py

@@ -1,6 +1,4 @@
 #!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-#
 # Copyright (c) 2018-2021, NVIDIA CORPORATION.
 #
 # cudf documentation build configuration file, created by

python/cudf/cudf/_fuzz_testing/fuzzer.py

@@ -14,7 +14,7 @@
 )
 
 
-class Fuzzer(object):
+class Fuzzer:
     def __init__(
         self,
         target,

python/cudf/cudf/_fuzz_testing/io.py

@@ -16,7 +16,7 @@
 )
 
 
-class IOFuzz(object):
+class IOFuzz:
     def __init__(
         self,
         dirs=None,
@@ -59,7 +59,7 @@ def __init__(
         self._current_buffer = None
 
     def _load_params(self, path):
-        with open(path, "r") as f:
+        with open(path) as f:
             params = json.load(f)
         self._inputs.append(params)
 

python/cudf/cudf/_fuzz_testing/main.py

@@ -3,7 +3,7 @@
 from cudf._fuzz_testing import fuzzer
 
 
-class PythonFuzz(object):
+class PythonFuzz:
     def __init__(self, func, params=None, data_handle=None, **kwargs):
         self.function = func
         self.data_handler_class = data_handle

python/cudf/cudf/_version.py

@@ -86,7 +86,7 @@ def run_command(
                 stderr=(subprocess.PIPE if hide_stderr else None),
             )
             break
-        except EnvironmentError:
+        except OSError:
             e = sys.exc_info()[1]
             if e.errno == errno.ENOENT:
                 continue
@@ -96,7 +96,7 @@ def run_command(
             return None, None
     else:
         if verbose:
-            print("unable to find command, tried %s" % (commands,))
+            print(f"unable to find command, tried {commands}")
         return None, None
     stdout = p.communicate()[0].strip()
     if sys.version_info[0] >= 3:
@@ -149,7 +149,7 @@ def git_get_keywords(versionfile_abs):
     # _version.py.
     keywords = {}
     try:
-        f = open(versionfile_abs, "r")
+        f = open(versionfile_abs)
         for line in f.readlines():
             if line.strip().startswith("git_refnames ="):
                 mo = re.search(r'=\s*"(.*)"', line)
@@ -164,7 +164,7 @@ def git_get_keywords(versionfile_abs):
                 if mo:
                     keywords["date"] = mo.group(1)
         f.close()
-    except EnvironmentError:
+    except OSError:
         pass
     return keywords
 
@@ -188,11 +188,11 @@ def git_versions_from_keywords(keywords, tag_prefix, verbose):
         if verbose:
             print("keywords are unexpanded, not using")
         raise NotThisMethod("unexpanded keywords, not a git-archive tarball")
-    refs = set([r.strip() for r in refnames.strip("()").split(",")])
+    refs = {r.strip() for r in refnames.strip("()").split(",")}
     # starting in git-1.8.3, tags are listed as "tag: foo-1.0" instead of
     # just "foo-1.0". If we see a "tag: " prefix, prefer those.
     TAG = "tag: "
-    tags = set([r[len(TAG) :] for r in refs if r.startswith(TAG)])
+    tags = {r[len(TAG) :] for r in refs if r.startswith(TAG)}
     if not tags:
         # Either we're using git < 1.8.3, or there really are no tags. We use
         # a heuristic: assume all version tags have a digit. The old git %d
@@ -201,7 +201,7 @@ def git_versions_from_keywords(keywords, tag_prefix, verbose):
         # between branches and tags. By ignoring refnames without digits, we
         # filter out many common branch names like "release" and
         # "stabilization", as well as "HEAD" and "master".
-        tags = set([r for r in refs if re.search(r"\d", r)])
+        tags = {r for r in refs if re.search(r"\d", r)}
         if verbose:
             print("discarding '%s', no digits" % ",".join(refs - tags))
     if verbose:
@@ -308,10 +308,9 @@ def git_pieces_from_vcs(tag_prefix, root, verbose, run_command=run_command):
             if verbose:
                 fmt = "tag '%s' doesn't start with prefix '%s'"
                 print(fmt % (full_tag, tag_prefix))
-            pieces["error"] = "tag '%s' doesn't start with prefix '%s'" % (
-                full_tag,
-                tag_prefix,
-            )
+            pieces[
+                "error"
+            ] = f"tag '{full_tag}' doesn't start with prefix '{tag_prefix}'"
             return pieces
         pieces["closest-tag"] = full_tag[len(tag_prefix) :]
 

python/cudf/cudf/comm/gpuarrow.py

@@ -58,7 +58,7 @@ def to_dict(self):
         return dc
 
 
-class GpuArrowNodeReader(object):
+class GpuArrowNodeReader:
     def __init__(self, table, index):
         self._table = table
         self._field = table.schema[index]