view tests/filterpyflakes.py @ 20713:6a1a4c212d50

revset: improve head revset performance

Previously the head() revset would iterate over every item in the subset and
check if it was a head.  Since the subset is often the entire repo, this was
slow on large repos. Now we iterate over each item in the head list and check if
it's in the subset, which results in much less work.

hg log -r 'head()' on a large repo:
Before: 0.95s
After: 0.28s

#!/usr/bin/env python

# Filter output by pyflakes to control which warnings we check

import sys, re, os

def makekey(typeandline):
    """
    for sorting lines by: msgtype, path/to/file, lineno, message

    typeandline is a sequence of a message type and the entire message line
    the message line format is path/to/file:line: message

    >>> makekey((3, 'example.py:36: any message'))
    (3, 'example.py', 36, ' any message')
    >>> makekey((7, 'path/to/file.py:68: dummy message'))
    (7, 'path/to/file.py', 68, ' dummy message')
    >>> makekey((2, 'fn:88: m')) > makekey((2, 'fn:9: m'))
    True
    """

    msgtype, line = typeandline
    fname, line, message = line.split(":", 2)
    # line as int for ordering 9 before 88
    return msgtype, fname, int(line), message


lines = []
for line in sys.stdin:
    # We whitelist tests (see more messages in pyflakes.messages)
    pats = [
            r"imported but unused",
            r"local variable '.*' is assigned to but never used",
            r"unable to detect undefined names",
           ]
    for msgtype, pat in enumerate(pats):
        if re.search(pat, line):
            break # pattern matches
    else:
        continue # no pattern matched, next line
    fn = line.split(':', 1)[0]
    f = open(os.path.join(os.path.dirname(os.path.dirname(__file__)), fn))
    data = f.read()
    f.close()
    if 'no-' 'check-code' in data:
        continue
    lines.append((msgtype, line))

for msgtype, line in sorted(lines, key=makekey):
    sys.stdout.write(line)
print