view doc/docchecker @ 28386:1c658391b22f

parsers: optimize filtered headrevs logic

The old native head revs logic would iterate over every node, starting from 0,
and check if every node was filtered (by testing it against the filteredrevs
python set). On large repos with hundreds of thousands of commits, this could
take 150ms.

This new logic iterates over the nodes in reverse order, and skips the filtered
check if we've seen an unfiltered child of the node. This saves approximately a
bagillion filteredrevs set checks, which shaves the time down from 150ms to
20ms during every branch cache write.

#!/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.
import sys
import re

leadingline = re.compile(r'(^\s*)(\S.*)$')
hg_backtick = re.compile(r""":hg:`[^`]*'[^`]*`""")
hg_cramped = re.compile(r'\w:hg:`')

def check(line):
    if hg_backtick.search(line):
        print(line)
        print("""warning: please avoid nesting ' in :hg:`...`""")
    if hg_cramped.search(line):
        print(line)
        print('warning: please have a space before :hg:')

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()