view mercurial/sshpeer.py @ 22506:6e1fbcb18a75 stable

hgweb: fail if an invalid command was supplied in url path (issue4071)

Traditionally, the way to specify a command for hgweb was to use url query
arguments (e.g. "?cmd=batch"). If the command is unknown to hgweb, it gives an
error (e.g. "400 no such method: badcmd").

But there's also another way to specify a command: as a url path fragment (e.g.
"/graph"). Before, hgweb was made forgiving (looks like it was made in
44c5157474e7) and user could put any unknown command in the url. If hgweb
couldn't understand it, it would just silently fall back to the default
command, which depends on the actual style (e.g. for paper it's shortlog, for
monoblue it's summary). This was inconsistent and was breaking some tools that
rely on http status codes (as noted in the issue4071). So this patch changes
that behavior to the more consistent one, i.e. hgweb will now return "400 no
such method: badcmd".

So if some tool was relying on having an invalid command return http status
code 200 and also have some information, then it will stop working. That is, if
somebody typed foobar when they really meant shortlog (and the user was lucky
enough to choose a style where the default command is shortlog too), that fact
will now be revealed.

Code-wise, the changed if block is only relevant when there's no "?cmd" query
parameter (i.e. only when command is specified as a url path fragment), and
looks like the removed else branch was there only for falling back to default
command. With that removed, the rest of the code works as expected: it looks at
the command, and if it's not known, raises a proper ErrorResponse exception
with an appropriate message.

Evidently, there were no tests that required the old behavior. But, frankly, I
don't know any way to tell if anyone actually exploited such forgiving behavior
in some in-house tool.

# sshpeer.py - ssh repository proxy class for mercurial
#
# Copyright 2005, 2006 Matt Mackall <[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.

import re
from i18n import _
import util, error, wireproto

class remotelock(object):
    def __init__(self, repo):
        self.repo = repo
    def release(self):
        self.repo.unlock()
        self.repo = None
    def __del__(self):
        if self.repo:
            self.release()

def _serverquote(s):
    '''quote a string for the remote shell ... which we assume is sh'''
    if re.match('[a-zA-Z0-9@%_+=:,./-]*$', s):
        return s
    return "'%s'" % s.replace("'", "'\\''")

class sshpeer(wireproto.wirepeer):
    def __init__(self, ui, path, create=False):
        self._url = path
        self.ui = ui
        self.pipeo = self.pipei = self.pipee = None

        u = util.url(path, parsequery=False, parsefragment=False)
        if u.scheme != 'ssh' or not u.host or u.path is None:
            self._abort(error.RepoError(_("couldn't parse location %s") % path))

        self.user = u.user
        if u.passwd is not None:
            self._abort(error.RepoError(_("password in URL not supported")))
        self.host = u.host
        self.port = u.port
        self.path = u.path or "."

        sshcmd = self.ui.config("ui", "ssh", "ssh")
        remotecmd = self.ui.config("ui", "remotecmd", "hg")

        args = util.sshargs(sshcmd, self.host, self.user, self.port)

        if create:
            cmd = '%s %s %s' % (sshcmd, args,
                util.shellquote("%s init %s" %
                    (_serverquote(remotecmd), _serverquote(self.path))))
            ui.debug('running %s\n' % cmd)
            res = util.system(cmd)
            if res != 0:
                self._abort(error.RepoError(_("could not create remote repo")))

        self._validaterepo(sshcmd, args, remotecmd)

    def url(self):
        return self._url

    def _validaterepo(self, sshcmd, args, remotecmd):
        # cleanup up previous run
        self.cleanup()

        cmd = '%s %s %s' % (sshcmd, args,
            util.shellquote("%s -R %s serve --stdio" %
                (_serverquote(remotecmd), _serverquote(self.path))))
        self.ui.debug('running %s\n' % cmd)
        cmd = util.quotecommand(cmd)

        # while self.subprocess isn't used, having it allows the subprocess to
        # to clean up correctly later
        self.pipeo, self.pipei, self.pipee, self.subprocess = util.popen4(cmd)

        # skip any noise generated by remote shell
        self._callstream("hello")
        r = self._callstream("between", pairs=("%s-%s" % ("0"*40, "0"*40)))
        lines = ["", "dummy"]
        max_noise = 500
        while lines[-1] and max_noise:
            l = r.readline()
            self.readerr()
            if lines[-1] == "1\n" and l == "\n":
                break
            if l:
                self.ui.debug("remote: ", l)
            lines.append(l)
            max_noise -= 1
        else:
            self._abort(error.RepoError(_('no suitable response from '
                                          'remote hg')))

        self._caps = set()
        for l in reversed(lines):
            if l.startswith("capabilities:"):
                self._caps.update(l[:-1].split(":")[1].split())
                break

    def _capabilities(self):
        return self._caps

    def readerr(self):
        while True:
            size = util.fstat(self.pipee).st_size
            if size == 0:
                break
            s = self.pipee.read(size)
            if not s:
                break
            for l in s.splitlines():
                self.ui.status(_("remote: "), l, '\n')

    def _abort(self, exception):
        self.cleanup()
        raise exception

    def cleanup(self):
        if self.pipeo is None:
            return
        self.pipeo.close()
        self.pipei.close()
        try:
            # read the error descriptor until EOF
            for l in self.pipee:
                self.ui.status(_("remote: "), l)
        except (IOError, ValueError):
            pass
        self.pipee.close()

    __del__ = cleanup

    def _callstream(self, cmd, **args):
        self.ui.debug("sending %s command\n" % cmd)
        self.pipeo.write("%s\n" % cmd)
        _func, names = wireproto.commands[cmd]
        keys = names.split()
        wireargs = {}
        for k in keys:
            if k == '*':
                wireargs['*'] = args
                break
            else:
                wireargs[k] = args[k]
                del args[k]
        for k, v in sorted(wireargs.iteritems()):
            self.pipeo.write("%s %d\n" % (k, len(v)))
            if isinstance(v, dict):
                for dk, dv in v.iteritems():
                    self.pipeo.write("%s %d\n" % (dk, len(dv)))
                    self.pipeo.write(dv)
            else:
                self.pipeo.write(v)
        self.pipeo.flush()

        return self.pipei

    def _callcompressable(self, cmd, **args):
        return self._callstream(cmd, **args)

    def _call(self, cmd, **args):
        self._callstream(cmd, **args)
        return self._recv()

    def _callpush(self, cmd, fp, **args):
        r = self._call(cmd, **args)
        if r:
            return '', r
        while True:
            d = fp.read(4096)
            if not d:
                break
            self._send(d)
        self._send("", flush=True)
        r = self._recv()
        if r:
            return '', r
        return self._recv(), ''

    def _calltwowaystream(self, cmd, fp, **args):
        r = self._call(cmd, **args)
        if r:
            # XXX needs to be made better
            raise util.Abort('unexpected remote reply: %s' % r)
        while True:
            d = fp.read(4096)
            if not d:
                break
            self._send(d)
        self._send("", flush=True)
        return self.pipei

    def _recv(self):
        l = self.pipei.readline()
        if l == '\n':
            err = []
            while True:
                line = self.pipee.readline()
                if line == '-\n':
                    break
                err.extend([line])
            if len(err) > 0:
                # strip the trailing newline added to the last line server-side
                err[-1] = err[-1][:-1]
            self._abort(error.OutOfBandError(*err))
        self.readerr()
        try:
            l = int(l)
        except ValueError:
            self._abort(error.ResponseError(_("unexpected response:"), l))
        return self.pipei.read(l)

    def _send(self, data, flush=False):
        self.pipeo.write("%d\n" % len(data))
        if data:
            self.pipeo.write(data)
        if flush:
            self.pipeo.flush()
        self.readerr()

    def lock(self):
        self._call("lock")
        return remotelock(self)

    def unlock(self):
        self._call("unlock")

    def addchangegroup(self, cg, source, url, lock=None):
        '''Send a changegroup to the remote server.  Return an integer
        similar to unbundle(). DEPRECATED, since it requires locking the
        remote.'''
        d = self._call("addchangegroup")
        if d:
            self._abort(error.RepoError(_("push refused: %s") % d))
        while True:
            d = cg.read(4096)
            if not d:
                break
            self.pipeo.write(d)
            self.readerr()

        self.pipeo.flush()

        self.readerr()
        r = self._recv()
        if not r:
            return 1
        try:
            return int(r)
        except ValueError:
            self._abort(error.ResponseError(_("unexpected response:"), r))

instance = sshpeer