contrib/hg-ssh

hgweb: parse WSGI request into a data structure

Currently, our WSGI applications (hgweb_mod and hgwebdir_mod) process
the raw WSGI request instance themselves. This means they have to
talk in terms of system strings. And they need to know details
about what's in the WSGI request. And in the case of hgweb_mod, it
is doing some very funky things with URL parsing to impact
dispatching. The code is difficult to read and maintain.

This commit introduces parsing of the WSGI request into a higher-level
and easier-to-reason-about data structure.

To prove it works, we hook it up to hgweb_mod and use it for populating
the relative URL on the request instance.

We hold off on using it in more places because the logic in hgweb_mod
is crazy and I don't want to involve those changes with review of
the parsing code.

The URL construction code has variations that use the HTTP: Host header
(the canonical WSGI way of reconstructing the URL) and with the use
of SERVER_NAME. We need to differentiate because hgweb is currently
using SERVER_NAME for URL construction.

Differential Revision: https://phab.mercurial-scm.org/D2734

#!/usr/bin/env python
#
# 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/*"
"""
from __future__ import absolute_import

import os
import shlex
import sys

# enable importing on demand to reduce startup time
import hgdemandimport ; hgdemandimport.enable()

from mercurial import (
    dispatch,
    ui as uimod,
)

def main():
    cwd = os.getcwd()
    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 = ['-R', repo, 'serve', '--stdio']
            req = dispatch.request(cmd)
            if readonly:
                if not req.ui:
                    req.ui = uimod.ui.load()
                req.ui.setconfig('hooks', 'pretxnopen.hg-ssh',
                                 'python:__main__.rejectpush', 'hg-ssh')
                req.ui.setconfig('hooks', 'prepushkey.hg-ssh',
                                 'python:__main__.rejectpush', '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(("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()