annotate mercurial/httpconnection.py @ 37047:fddcb51b5084

wireproto: define permissions-based routing of HTTPv2 wire protocol

Now that we have a scaffolding for serving version 2 of the HTTP
protocol, let's start implementing it.

A good place to start is URL routing and basic request processing
semantics. We can focus on content types, capabilities detect, etc
later.

Version 2 of the HTTP wire protocol encodes the needed permissions
of the request in the URL path. The reasons for this are documented
in the added documentation. In short, a) it makes it really easy and
fail proof for server administrators to implement path-based
authentication and b) it will enable clients to realize very early in
a server exchange that authentication will be required to complete
the operation. This latter point avoids all kinds of complexity and
problems, like dealing with Expect: 100-continue and clients finding
out later during `hg push` that they need to provide authentication.
This will avoid the current badness where clients send a full bundle,
get an HTTP 403, provide authentication, then retransmit the bundle.

In order to implement command checking, we needed to implement a
protocol handler for the new wire protocol. Our handler is just
small enough to run the code we've implemented.

Tests for the defined functionality have been added.

I very much want to refactor the permissions checking code and define
a better response format. But this can be done later. Nothing is
covered by backwards compatibility at this point.

Differential Revision: https://phab.mercurial-scm.org/D2836

# httpconnection.py - urllib2 handler for new http support
#
# Copyright 2005, 2006, 2007, 2008 Matt Mackall <[e-mail]>
# Copyright 2006, 2007 Alexis S. L. Carvalho <[e-mail]>
# Copyright 2006 Vadim Gelfer <[e-mail]>
# Copyright 2011 Google, Inc.
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

from __future__ import absolute_import

import os

from .i18n import _
from . import (
    pycompat,
    util,
)

urlerr = util.urlerr
urlreq = util.urlreq

# moved here from url.py to avoid a cycle
class httpsendfile(object):
    """This is a wrapper around the objects returned by python's "open".

    Its purpose is to send file-like objects via HTTP.
    It do however not define a __len__ attribute because the length
    might be more than Py_ssize_t can handle.
    """

    def __init__(self, ui, *args, **kwargs):
        self.ui = ui
        self._data = open(*args, **kwargs)
        self.seek = self._data.seek
        self.close = self._data.close
        self.write = self._data.write
        self.length = os.fstat(self._data.fileno()).st_size
        self._pos = 0
        self._total = self.length // 1024 * 2

    def read(self, *args, **kwargs):
        ret = self._data.read(*args, **kwargs)
        if not ret:
            self.ui.progress(_('sending'), None)
            return ret
        self._pos += len(ret)
        # We pass double the max for total because we currently have
        # to send the bundle twice in the case of a server that
        # requires authentication. Since we can't know until we try
        # once whether authentication will be required, just lie to
        # the user and maybe the push succeeds suddenly at 50%.
        self.ui.progress(_('sending'), self._pos // 1024,
                         unit=_('kb'), total=self._total)
        return ret

    def __enter__(self):
        return self

    def __exit__(self, exc_type, exc_val, exc_tb):
        self.close()

# moved here from url.py to avoid a cycle
def readauthforuri(ui, uri, user):
    uri = pycompat.bytesurl(uri)
    # Read configuration
    groups = {}
    for key, val in ui.configitems('auth'):
        if key in ('cookiefile',):
            continue

        if '.' not in key:
            ui.warn(_("ignoring invalid [auth] key '%s'\n") % key)
            continue
        group, setting = key.rsplit('.', 1)
        gdict = groups.setdefault(group, {})
        if setting in ('username', 'cert', 'key'):
            val = util.expandpath(val)
        gdict[setting] = val

    # Find the best match
    scheme, hostpath = uri.split('://', 1)
    bestuser = None
    bestlen = 0
    bestauth = None
    for group, auth in groups.iteritems():
        if user and user != auth.get('username', user):
            # If a username was set in the URI, the entry username
            # must either match it or be unset
            continue
        prefix = auth.get('prefix')
        if not prefix:
            continue
        p = prefix.split('://', 1)
        if len(p) > 1:
            schemes, prefix = [p[0]], p[1]
        else:
            schemes = (auth.get('schemes') or 'https').split()
        if (prefix == '*' or hostpath.startswith(prefix)) and \
            (len(prefix) > bestlen or (len(prefix) == bestlen and \
                not bestuser and 'username' in auth)) \
             and scheme in schemes:
            bestlen = len(prefix)
            bestauth = group, auth
            bestuser = auth.get('username')
            if user and not bestuser:
                auth['username'] = user
    return bestauth