Mercurial > hg
view contrib/check-commit @ 33927:853574db5b12
encoding: add fast path of from/tolocal() for ASCII strings
This is micro optimization, but seems not bad since to/fromlocal() is called
lots of times and isasciistr() is cheap and simple.
We boldly assume that any non-ASCII characters have at least one 8-bit byte.
This isn't true for some email character sets (e.g. ISO-2022-JP and UTF-7),
but I believe no such encodings are used as a platform default. Shift_JIS,
a major crap, is okay as it should have a leading byte in 0x80-0xff range.
(with mercurial repo)
$ export HGRCPATH=/dev/null HGPLAIN=
$ hg log --time --config experimental.stabilization=all > /dev/null
(original)
time: real 7.460 secs (user 7.420+0.000 sys 0.030+0.000)
time: real 7.670 secs (user 7.590+0.000 sys 0.080+0.000)
time: real 7.560 secs (user 7.510+0.000 sys 0.040+0.000)
(this patch)
time: real 7.340 secs (user 7.260+0.000 sys 0.060+0.000)
time: real 7.260 secs (user 7.210+0.000 sys 0.030+0.000)
time: real 7.310 secs (user 7.260+0.000 sys 0.060+0.000)
author | Yuya Nishihara <yuya@tcha.org> |
---|---|
date | Sun, 23 Apr 2017 13:06:23 +0900 |
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)