outgoing: rework the handling of the `missingroots` case to be faster
The previous implementation was slow, to the point it was taking a significant
amount of `hg bundle --type none-streamv2` call. We rework the code to compute
the same value much faster, making the operation disappear from the `hg bundle
--type none-streamv2` profile. Someone would remark that producing a streamclone
does not requires an `outgoing` object. However that is a matter for another
day. There is other user of `missingroots` (non stream `hg bundle` call for
example), and they will also benefit from this rework.
We implement an old TODO in the process, directly computing the missing and
common attribute as we have most element at hand already.
### benchmark.name = hg.command.bundle
# bin-env-vars.hg.flavor = default
# bin-env-vars.hg.py-re2-module = default
# benchmark.variants.revs = all
# benchmark.variants.type = none-streamv2
## data-env-vars.name = heptapod-public-2024-03-25-zstd-sparse-revlog
before: 7.750458
after: 6.665565 (-14.00%, -1.08)
## data-env-vars.name = mercurial-public-2024-03-22-zstd-sparse-revlog
before: 0.700229
after: 0.496050 (-29.16%, -0.20)
## data-env-vars.name = mozilla-try-2023-03-22-zstd-sparse-revlog
before: 346.508952
after: 316.749699 (-8.59%, -29.76)
## data-env-vars.name = pypy-2024-03-22-zstd-sparse-revlog
before: 3.401700
after: 2.915810 (-14.28%, -0.49)
## data-env-vars.name = tryton-public-2024-03-22-zstd-sparse-revlog
before: 1.870798
after: 1.461583 (-21.87%, -0.41)
note: this whole `missingroots` of outgoing has a limited number of callers and
could likely be replace by something simpler (like taking an explicit
"missing_revs" set for example). However this is a wider change and we focus on
a small impact, quick rework that does not change the API for now.
#!/usr/bin/env python3
#
# Copyright 2014 Olivia Mackall <olivia@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
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)