view contrib/check-commit @ 38573:050fbd9d103a

test-convert: demonstrate an unstable hash issue for bzr -> hg -> hg It looks like the manifest value changing is the only difference, but I'm not sure why it's happening. I've got a similar divergence in a production repo that was also converted from bzr and has an octopus merge[1]. Unlike here, the manifest values for the destination merge commits reflect the initial merge only, instead of all four merges agreeing like this test. $ hg -R src_repo manifest -r 310 --debug | grep file # octopus fixup merge 2d8775bc2481bd28ac87038ecdf33e1dbddc80e9 644 file1 6adb9353a55bb8be76e71382efc724ec3ccf7ed5 644 file2 $ hg -R src_repo manifest -r 309 --debug | grep file # first merge 362e7cb5163153c4989daad1a834871ae849f205 644 file1 2c65d947191938c3ea616b7ceb7648ff3843261f 644 file2 $ hg -R dst_repo manifest -r 273 --debug | grep file # octopus fixup merge 362e7cb5163153c4989daad1a834871ae849f205 644 file1 2c65d947191938c3ea616b7ceb7648ff3843261f 644 file2 $ hg -R dst_repo manifest -r 272 --debug | grep file # first merge 362e7cb5163153c4989daad1a834871ae849f205 644 file1 2c65d947191938c3ea616b7ceb7648ff3843261f 644 file2 This divergence is espcially annoying because unlike changelog differences, I haven't figured out a way to fix this in code. The only way I found to work around it is to convert up to the point of divergence, `hg bundle` the bad revision in the source, apply it to the destination, add a line to the shamap, and fire off the conversion again. But I suspect that there's more to it than just the octopus merge because I also have a commit in the same repo, done in Mercurial (well after the conversion) that is exhibiting a similar issue (and it's not a merge commit). I'm almost positive that it was created with 4.4 or later. Any ideas? [1] https://www.mercurial-scm.org/pipermail/mercurial/2018-June/050924.html
author Matt Harbison <matt_harbison@yahoo.com>
date Thu, 05 Jul 2018 15:07:29 -0400
parents 2fb3ae89e4e1
children 47084b5ffd80
line wrap: on
line source

#!/usr/bin/env python
#
# Copyright 2014 Matt Mackall <mpm@selenic.com>
#
# 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

from __future__ import absolute_import, print_function

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"[^\n]*: *[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)"),
    (r"\n\+\n( |\+)\n", "adds double empty line"),
    (r"\n \n\+\n", "adds double empty line"),
    # Forbid "_" in function name.
    #
    # We skip the check for cffi related functions. They use names mapping the
    # name of the C function. C function names may contain "_".
    (r"\n\+[ \t]+def (?!cffi)[a-z]+_[a-z]",
     "adds a function with foo_bar naming"),
]

word = re.compile('\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)