view tests/filterpyflakes.py @ 36444:44c4a38bf563

diff: do not split function name if character encoding is unknown

Only ASCII characters can be split reliably at any byte positions, so let's
just leave long multi-byte sequence long. It's probably less bad than putting
an invalid byte sequence into a diff.

This doesn't try to split the first ASCII slice from multi-byte sequence
because a combining character may follow.

#!/usr/bin/env python

# Filter output by pyflakes to control which warnings we check

from __future__ import absolute_import, print_function

import re
import sys

lines = []
for line in sys.stdin:
    # We blacklist tests that are too noisy for us
    pats = [
        r"undefined name 'WindowsError'",
        r"redefinition of unused '[^']+' from line",
        # for cffi, allow re-exports from pure.*
        r"cffi/[^:]*:.*\bimport \*' used",
        r"cffi/[^:]*:.*\*' imported but unused",
    ]

    keep = True
    for pat in pats:
        if re.search(pat, line):
            keep = False
            break # pattern matches
    if keep:
        fn = line.split(':', 1)[0]
        f = open(fn)
        data = f.read()
        f.close()
        if 'no-' 'check-code' in data:
            continue
        lines.append(line)

for line in lines:
    sys.stdout.write(line)
print()