view contrib/check-commit @ 49491:c6a1beba27e9

bisect: avoid copying ancestor list for non-merge commits

During a bisection, hg needs to compute a list of all ancestors for every
candidate commit. This is accomplished via a bottom-up traversal of the set of
candidates, during which each revision's ancestor list is populated using the
ancestor list of its parent(s). Previously, this involved copying the entire
list, which could be very long in if the bisection range was large.

To help improve this, we can observe that each candidate commit is visited
exactly once, at which point its ancestor list is copied into its children's
lists and then dropped. In the case of non-merge commits, a commit's ancestor
list consists exactly of its parent's list plus itself. This means that we can
trivially reuse the parent's existing list for one of its non-merge children,
which avoids copying entirely if that commit is the parent's only child. This
makes bisections over linear ranges of commits much faster.

During some informal testing in the large publicly-available `mozilla-central`
repository, this noticeably sped up bisections over large ranges of history:

Setup:
  $ cd mozilla-central
  $ hg bisect --reset
  $ hg bisect --good 0
  $ hg log -r tip -T '{rev}\n'
  628417

Test:
  $ time hg bisect --bad tip --noupdate

Before:
  real    3m35.927s
  user    3m35.553s
  sys     0m0.319s

After:
  real    1m41.142s
  user    1m40.810s
  sys     0m0.285s

#!/usr/bin/env python3
#
# Copyright 2014 Olivia Mackall <[e-mail]>
#
# A tool/hook to run basic sanity checks on commits/patches for
# submission to Mercurial. Install by adding the following to your
# .hg/hgrc:
#
# [hooks]
# pretxncommit = contrib/check-commit
#
# The hook can be temporarily bypassed with:
#
# $ BYPASS= hg commit
#
# See also: https://mercurial-scm.org/wiki/ContributingChanges


import os
import re
import sys

commitheader = r"^(?:# [^\n]*\n)*"
afterheader = commitheader + r"(?!#)"
beforepatch = afterheader + r"(?!\n(?!@@))"

errors = [
    (beforepatch + r".*[(]bc[)]", "(BC) needs to be uppercase"),
    (
        beforepatch + r".*[(]issue \d\d\d",
        "no space allowed between issue and number",
    ),
    (beforepatch + r".*[(]bug(\d|\s)", "use (issueDDDD) instead of bug"),
    (commitheader + r"# User [^@\n]+\n", "username is not an email address"),
    (
        commitheader + r"(?!merge with )[^#]\S+[^:] ",
        "summary line doesn't start with 'topic: '",
    ),
    (afterheader + r"[A-Z][a-z]\S+", "don't capitalize summary lines"),
    (afterheader + r"^\S+: *[A-Z][a-z]\S+", "don't capitalize summary lines"),
    (
        afterheader + r"\S*[^A-Za-z0-9-_]\S*: ",
        "summary keyword should be most user-relevant one-word command or topic",
    ),
    (afterheader + r".*\.\s*\n", "don't add trailing period on summary line"),
    (afterheader + r".{79,}", "summary line too long (limit is 78)"),
]

word = re.compile(r'\S')


def nonempty(first, second):
    if word.search(first):
        return first
    return second


def checkcommit(commit, node=None):
    exitcode = 0
    printed = node is None
    hits = []
    signtag = (
        afterheader + r'Added (tag [^ ]+|signature) for changeset [a-f0-9]{12}'
    )
    if re.search(signtag, commit):
        return 0
    for exp, msg in errors:
        for m in re.finditer(exp, commit):
            end = m.end()
            trailing = re.search(r'(\\n)+$', exp)
            if trailing:
                end -= len(trailing.group()) / 2
            hits.append((end, exp, msg))
    if hits:
        hits.sort()
        pos = 0
        last = ''
        for n, l in enumerate(commit.splitlines(True)):
            pos += len(l)
            while len(hits):
                end, exp, msg = hits[0]
                if pos < end:
                    break
                if not printed:
                    printed = True
                    print("node: %s" % node)
                print("%d: %s" % (n, msg))
                print(" %s" % nonempty(l, last)[:-1])
                if "BYPASS" not in os.environ:
                    exitcode = 1
                del hits[0]
            last = nonempty(l, last)

    return exitcode


def readcommit(node):
    return os.popen("hg export %s" % node).read()


if __name__ == "__main__":
    exitcode = 0
    node = os.environ.get("HG_NODE")

    if node:
        commit = readcommit(node)
        exitcode = checkcommit(commit)
    elif sys.argv[1:]:
        for node in sys.argv[1:]:
            exitcode |= checkcommit(readcommit(node), node)
    else:
        commit = sys.stdin.read()
        exitcode = checkcommit(commit)
    sys.exit(exitcode)