automatically ignore lines from flake8

noqaer.py

"""
Add `# noqa: FXXX` comments to all lines with violations from flake8
"""

# MIT License
# 
# Copyright (c) 2022 Alex Riina
# 
# Permission is hereby granted, free of charge, to any person obtaining a copy
# of this software and associated documentation files (the "Software"), to deal
# in the Software without restriction, including without limitation the rights
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
# copies of the Software, and to permit persons to whom the Software is
# furnished to do so, subject to the following conditions:
# 
# The above copyright notice and this permission notice shall be included in all
# copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
# SOFTWARE.

import sys
import argparse
import fileinput
from itertools import groupby
from collections import defaultdict

parser = argparse.ArgumentParser(
    description=__doc__,
    usage="flake8 $(git ls-files **/*.py) | noqaer.py - [--dry-run]",
    epilog="""
    Intended to be used once in lieu of manually fixing all flake8 violatios so
    flake8 passes 100% and can be added to a build.""",
)
parser.add_argument("errors", type=argparse.FileType("r"), help="errors from flake8")
parser.add_argument("--dry-run", action="store_true")
args = parser.parse_args()


def parse_flake8_errors(error_lines):
    for error_line in error_lines:
        filename, line_number, col, message = error_line.strip().split(":", 3)
        error_code, message = message.strip().split(" ", 1)
        yield filename, int(line_number), error_code


for filename, error_tuples in groupby(
    parse_flake8_errors(args.errors), key=lambda error_tuple: error_tuple[0]
):
    errors = defaultdict(set)
    for _, line_number, code in error_tuples:
        errors[line_number].add(code)

    with fileinput.input(files=[filename], inplace=not args.dry_run) as fp:
        for line_number, line in enumerate(fp, start=1):
            if line_number not in errors:
                # line already has a newline, so don't add an extra
                print(line, end="")
            elif "noqa" in line or line.strip().endswith("\\"):
                print("skipping {}:{}".format(filename, line_number), file=sys.stderr)
                print(line, end="")
            else:
                # note the fileinput inplace captures output and writes back to the file
                print(line.rstrip("\n") + "  # noqa: " + ", ".join(errors[line_number]))

@AlexRiina have you considered suggesting folks use flake8-json so you have structured data that you can parse more easily?

@sigmavirus24 I hadn't heard of that project but my inclination is to avoid adding any external dependencies so this can be audited and run very easily. I do like the idea of reducing the split and strips though and think the script could be rewritten to use an explicit flake8 --format ....

With something like flake8 --format '%(path)s:%(row)d:%(col)d:%(code)s' some of the strips can go away and this could even use csv.reader (if someone is dealing with a gnarly error message that breaks this script and reads this: '%(path)s:%(row)d:%(col)d:%(code)s x' looks like be good enough).

I'm not planning to change this gist since I've run the code on my repo and we're unlikely to declare a "jubilee" for any other flake8 errors but please feel free to fork this repo and make any changes you like (just added a license).