contrib/check-commit

check-commit: try to fix multiline handling

The old code did not understand the difference between the first line of the summary,
and a random line in the summary that happened to include a #, or a
random line in the changes that happened to include it.

965788d9ae09 is an example where it fails

#!/usr/bin/env python
#
# Copyright 2014 Matt 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 re, sys, os

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"),
    (r"\n\+[ \t]+def [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
    for exp, msg in errors:
        m = re.search(exp, commit)
        if m:
            pos = 0
            end = m.end()
            trailing = re.search(r'(\\n)+$', exp)
            if trailing:
                end -= len(trailing.group()) / 2
            last = ''
            for n, l in enumerate(commit.splitlines(True)):
                pos += len(l)
                if pos < end:
                    last = nonempty(l, last)
                else:
                    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
                    break
    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)