view contrib/hg-ssh @ 52284:f4aede0f01af

rust-manifest: use `memchr` crate for all byte-finding needs

While writing a very dumb manifest diffing algorithm for a proof-of-concept
I saw that `Manifest::find_by_path` was much slower than I was expecting.

It turns out that the Rust stdlib uses slow (all is relative) code when
searching for byte positions for reasons ranging from portability, SIMD
API stability, nobody doing the work, etc. `memch` is much faster for these
purposes, so let's use it.

I was measuring ~670ms of profile time in `find_by_path`, after this patch
it went down to ~230ms.

#!/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()