contrib/hg-ssh

clone: properly exclude rev-branch-cache from post clone cache warming

When adding "CACHE_REV_BRANCH" to "CACHES_ALL" in e51161b12c7e, I did not
expected it to impact the clone steps. However the "CACHES_POST_CLONE" set is
created rather creatively. (we should fix that, but not on stable)

The benchmark caught a quite significant slowdown one hardlink and ssh-stream
clones. Such slow down can be reduced to around ~5% by fully warming the cache
before the clone. However keeping this expensive step away from the clone
operation fully fix the slowdown and preserve the initial intend.


Example slowdow for hardlink clone

### benchmark.name                               = hg.command.clone
  # bin-env-vars.hg.flavor                       = default
  # bin-env-vars.hg.py-re2-module                = default
  # benchmark.variants.explicit-rev              = none
  # benchmark.variants.issue6528                 = default
  # benchmark.variants.protocol                  = local-hardlink
  # benchmark.variants.pulled-delta-reuse-policy = default
  # benchmark.variants.resource-usage            = default
  # benchmark.variants.validate                  = default
 ## data-env-vars.name = netbeans-2018-08-01-zstd-sparse-revlog
6.8.2:  19.799752
6.9rc0: 29.017493  (+46.55%, +9.22)
after:  19.929341

 ## data-env-vars.name = mercurial-public-2018-08-01-zstd-sparse-revlog
6.8.2:  0.468020
6.9rc0: 1.701294 (+263.51%, +1.23)
after:  0.471934

 ## data-env-vars.name = pypy-2024-03-22-zstd-sparse-revlog
6.8.2:  2.397564
6.9rc0: 5.666641 (+137.41%, +3.28)
after:  2.428085

#!/usr/bin/env python3
#
# Copyright 2005-2007 by Intevation GmbH <[e-mail]>
#
# Author(s):
# Thomas Arendsen Hein <[e-mail]>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

"""
hg-ssh - a wrapper for ssh access to a limited set of mercurial repos

To be used in ~/.ssh/authorized_keys with the "command" option, see sshd(8):
command="hg-ssh path/to/repo1 /path/to/repo2 ~/repo3 ~user/repo4" ssh-dss ...
(probably together with these other useful options:
 no-port-forwarding,no-X11-forwarding,no-agent-forwarding)

This allows pull/push over ssh from/to the repositories given as arguments.

If all your repositories are subdirectories of a common directory, you can
allow shorter paths with:
command="cd path/to/my/repositories && hg-ssh repo1 subdir/repo2"

You can use pattern matching of your normal shell, e.g.:
command="cd repos && hg-ssh user/thomas/* projects/{mercurial,foo}"

You can also add a --read-only flag to allow read-only access to a key, e.g.:
command="hg-ssh --read-only repos/*"
"""

import os
import re
import shlex
import sys

# enable importing on demand to reduce startup time
import hgdemandimport

hgdemandimport.enable()

from mercurial import (
    dispatch,
    pycompat,
    ui as uimod,
)


def main():
    # Prevent insertion/deletion of CRs
    dispatch.initstdio()

    cwd = os.getcwd()
    if os.name == 'nt':
        # os.getcwd() is inconsistent on the capitalization of the drive
        # letter, so adjust it. see https://bugs.python.org/issue40368
        if re.match('^[a-z]:', cwd):
            cwd = cwd[0:1].upper() + cwd[1:]

    readonly = False
    args = sys.argv[1:]
    while len(args):
        if args[0] == '--read-only':
            readonly = True
            args.pop(0)
        else:
            break
    allowed_paths = [
        os.path.normpath(os.path.join(cwd, os.path.expanduser(path)))
        for path in args
    ]
    orig_cmd = os.getenv('SSH_ORIGINAL_COMMAND', '?')
    try:
        cmdargv = shlex.split(orig_cmd)
    except ValueError as e:
        sys.stderr.write('Illegal command "%s": %s\n' % (orig_cmd, e))
        sys.exit(255)

    if cmdargv[:2] == ['hg', '-R'] and cmdargv[3:] == ['serve', '--stdio']:
        path = cmdargv[2]
        repo = os.path.normpath(os.path.join(cwd, os.path.expanduser(path)))
        if repo in allowed_paths:
            cmd = [b'-R', pycompat.fsencode(repo), b'serve', b'--stdio']
            req = dispatch.request(cmd)
            if readonly:
                if not req.ui:
                    req.ui = uimod.ui.load()
                req.ui.setconfig(
                    b'hooks',
                    b'pretxnopen.hg-ssh',
                    b'python:__main__.rejectpush',
                    b'hg-ssh',
                )
                req.ui.setconfig(
                    b'hooks',
                    b'prepushkey.hg-ssh',
                    b'python:__main__.rejectpush',
                    b'hg-ssh',
                )
            dispatch.dispatch(req)
        else:
            sys.stderr.write('Illegal repository "%s"\n' % repo)
            sys.exit(255)
    else:
        sys.stderr.write('Illegal command "%s"\n' % orig_cmd)
        sys.exit(255)


def rejectpush(ui, **kwargs):
    ui.warn((b"Permission denied\n"))
    # mercurial hooks use unix process conventions for hook return values
    # so a truthy return means failure
    return True


if __name__ == '__main__':
    main()