view tests/sshprotoext.py @ 42406:f385ba70e4af

changelog: optionally store added and removed files in changeset extras

As mentioned in an earlier patch, copies._chain() is used a lot in the
changeset-centric version of pathcopies(). It is expensive because it
needs to look at the manifest in order to filter out copies whose
target file has since been removed. I want to store the sets of added
and removed files in the changeset in order to speed that up. This
patch does the writing part of that. It could easily be a separate
config, but it's currently tied to experimental.copies.write-to since
that's the only real use case (it will also make the {file_*} template
keywords faster, but I doubt that anyone cares enough about those to
write extra metadata for them).

The new information is stored in the changeset extras. Since they're
always subsets of the changeset's "files" list, they're stored as
indexes into that list. I've stored the indexes as stringified ints
separated by NUL bytes. The size of 00changelog.d for the hg repo
increased in size by 0.28% percent (compared to the size with only
copy information in the changesets, which in turn is 0.17% larger than
without copy information). We could store only the delta between the
indexes and we could store them in binary, but the chosen format is
more readable.

We could also have implemented this as a cache outside the
changelog. One advantage of doing it that way is that we would get the
speedups from the {file_*} template keywords also on old
repos. Another advantage is that it we can rewrite the cache if we
find a bug in how we calculate the set of files. A disadvantage is
that it would be more complex. Another is that it would surely use
more space. We already write the copy information to the changeset
extras, so it seems like a small step to also write these file sets.

Differential Revision: https://phab.mercurial-scm.org/D6416

# sshprotoext.py - Extension to test behavior of SSH protocol
#
# Copyright 2018 Gregory Szorc <[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.

# This extension replaces the SSH server started via `hg serve --stdio`.
# The server behaves differently depending on environment variables.

from __future__ import absolute_import

from mercurial import (
    error,
    extensions,
    registrar,
    sshpeer,
    wireprotoserver,
    wireprotov1server,
)

configtable = {}
configitem = registrar.configitem(configtable)

configitem(b'sshpeer', b'mode', default=None)
configitem(b'sshpeer', b'handshake-mode', default=None)

class bannerserver(wireprotoserver.sshserver):
    """Server that sends a banner to stdout."""
    def serve_forever(self):
        for i in range(10):
            self._fout.write(b'banner: line %d\n' % i)

        super(bannerserver, self).serve_forever()

class prehelloserver(wireprotoserver.sshserver):
    """Tests behavior when connecting to <0.9.1 servers.

    The ``hello`` wire protocol command was introduced in Mercurial
    0.9.1. Modern clients send the ``hello`` command when connecting
    to SSH servers. This mock server tests behavior of the handshake
    when ``hello`` is not supported.
    """
    def serve_forever(self):
        l = self._fin.readline()
        assert l == b'hello\n'
        # Respond to unknown commands with an empty reply.
        wireprotoserver._sshv1respondbytes(self._fout, b'')
        l = self._fin.readline()
        assert l == b'between\n'
        proto = wireprotoserver.sshv1protocolhandler(self._ui, self._fin,
                                                     self._fout)
        rsp = wireprotov1server.dispatch(self._repo, proto, b'between')
        wireprotoserver._sshv1respondbytes(self._fout, rsp.data)

        super(prehelloserver, self).serve_forever()

def performhandshake(orig, ui, stdin, stdout, stderr):
    """Wrapped version of sshpeer._performhandshake to send extra commands."""
    mode = ui.config(b'sshpeer', b'handshake-mode')
    if mode == b'pre-no-args':
        ui.debug(b'sending no-args command\n')
        stdin.write(b'no-args\n')
        stdin.flush()
        return orig(ui, stdin, stdout, stderr)
    elif mode == b'pre-multiple-no-args':
        ui.debug(b'sending unknown1 command\n')
        stdin.write(b'unknown1\n')
        ui.debug(b'sending unknown2 command\n')
        stdin.write(b'unknown2\n')
        ui.debug(b'sending unknown3 command\n')
        stdin.write(b'unknown3\n')
        stdin.flush()
        return orig(ui, stdin, stdout, stderr)
    else:
        raise error.ProgrammingError(b'unknown HANDSHAKECOMMANDMODE: %s' %
                                     mode)

def extsetup(ui):
    # It's easier for tests to define the server behavior via environment
    # variables than config options. This is because `hg serve --stdio`
    # has to be invoked with a certain form for security reasons and
    # `dummyssh` can't just add `--config` flags to the command line.
    servermode = ui.environ.get(b'SSHSERVERMODE')

    if servermode == b'banner':
        wireprotoserver.sshserver = bannerserver
    elif servermode == b'no-hello':
        wireprotoserver.sshserver = prehelloserver
    elif servermode:
        raise error.ProgrammingError(b'unknown server mode: %s' % servermode)

    peermode = ui.config(b'sshpeer', b'mode')

    if peermode == b'extra-handshake-commands':
        extensions.wrapfunction(sshpeer, '_performhandshake', performhandshake)
    elif peermode:
        raise error.ProgrammingError(b'unknown peer mode: %s' % peermode)