view doc/docchecker @ 40978:42f59d3f714d

delta: exclude base candidate much smaller than the target

If a revision's full text is that much bigger than a base candidate full text,
we no longer consider that candidate.

This solves a pathological case we encountered on a very specify repository.
It contains a long series of changesets with a very small manifest (one file)
co-existing with others changesets using a very large manifest.

Without this filtering, we ended up considering a large number of tiny full
snapshots as a potential base. It resulted in very large delta (the size of
the full text) and mercurial spending 99% of its time compressing these
deltas.

The timing of a commit moved from about 400s to about 10s (still slow, but not
ridiculously slow).

#!/usr/bin/env python
#
# docchecker - look for problematic markup
#
# Copyright 2016 timeless <[e-mail]> and others
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

from __future__ import absolute_import, print_function

import re
import sys

leadingline = re.compile(r'(^\s*)(\S.*)$')

checks = [
  (r""":hg:`[^`]*'[^`]*`""",
    """warning: please avoid nesting ' in :hg:`...`"""),
  (r'\w:hg:`',
    'warning: please have a space before :hg:'),
  (r"""(?:[^a-z][^'.])hg ([^,;"`]*'(?!hg)){2}""",
    '''warning: please use " instead of ' for hg ... "..."'''),
]

def check(line):
    messages = []
    for match, msg in checks:
        if re.search(match, line):
            messages.append(msg)
    if messages:
        print(line)
        for msg in messages:
            print(msg)

def work(file):
    (llead, lline) = ('', '')

    for line in file:
        # this section unwraps lines
        match = leadingline.match(line)
        if not match:
            check(lline)
            (llead, lline) = ('', '')
            continue

        lead, line = match.group(1), match.group(2)
        if (lead == llead):
            if (lline != ''):
                lline += ' ' + line
            else:
                lline = line
        else:
            check(lline)
            (llead, lline) = (lead, line)
    check(lline)

def main():
    for f in sys.argv[1:]:
        try:
            with open(f) as file:
                work(file)
        except BaseException as e:
            print("failed to process %s: %s" % (f, e))

main()