view contrib/check-commit @ 39270:37e56607cbb9

lfs: add a progress bar when searching for blobs to upload The search itself can take an extreme amount of time if there are a lot of revisions involved. I've got a local repo that took 6 minutes to push 1850 commits, and 60% of that time was spent here (there are ~70K files): \ 58.1% wrapper.py: extractpointers line 297: pointers = extractpointers(... | 57.7% wrapper.py: pointersfromctx line 352: for p in pointersfromctx(ct... | 57.4% wrapper.py: pointerfromctx line 397: p = pointerfromctx(ctx, f, ... \ 38.7% context.py: __contains__ line 368: if f not in ctx: | 38.7% util.py: __get__ line 82: return key in self._manifest | 38.7% context.py: _manifest line 1416: result = self.func(obj) | 38.7% manifest.py: read line 472: return self._manifestctx.re... \ 25.6% revlog.py: revision line 1562: text = rl.revision(self._node) \ 12.8% revlog.py: _chunks line 2217: bins = self._chunks(chain, ... | 12.0% revlog.py: decompressline 2112: ladd(decomp(buffer(data, ch... \ 7.8% revlog.py: checkhash line 2232: self.checkhash(text, node, ... | 7.8% revlog.py: hash line 2315: if node != self.hash(text, ... | 7.8% revlog.py: hash line 2242: return hash(text, p1, p2) \ 12.0% manifest.py: __init__ line 1565: self._data = manifestdict(t... \ 16.8% context.py: filenode line 378: if not _islfs(fctx.filelog(... | 15.7% util.py: __get__ line 706: return self._filelog | 14.8% context.py: _filelog line 1416: result = self.func(obj) | 14.8% localrepo.py: file line 629: return self._repo.file(self... | 14.8% filelog.py: __init__ line 1134: return filelog.filelog(self... | 14.5% revlog.py: __init__ line 24: censorable=True)
author Matt Harbison <matt_harbison@yahoo.com>
date Fri, 24 Aug 2018 17:45:46 -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)