wireproto: correctly escape batched args and responses (issue4739)
This issue appears to be as old as wireproto batching itself: I can
reproduce the failure as far back as 08ef6b5f3715 trivially by
rebasing the test changes in this patch, which was back in the 1.9
era. I didn't test before that change, because prior to that the
testfile has a different name and I'm lazy.
Note that the test thought it was checking this case, but it actually
wasn't: it put a literal ; in the arg and response for its greet
command, but the mangle/unmangle step defined in the test meant that
instead of "Fo, =;o" going over the wire, "Gp-!><p" went instead,
which doesn't contain any special characters (those being [.=;]) and
thus not exercising the escaping. The test has been updated to use
pre-unmangled special characters, so the request is now "Fo+<:o",
which mangles to "Gp,=;p". I have confirmed that the test fails
without the adjustment to the escaping rules in wireproto.py.
No existing clients of RPC batching were depending on the old behavior
in any way. The only *actual* users of batchable RPCs in core were:
1) largefiles, wherein it batches up many statlfile calls. It sends
hexlified hashes over the wire and gets a 0, 1, or 2 back as a
response. No risk of special characters.
2) setdiscovery, which was using heads() and known(), both of which
communicate via hexlified nodes. Again, no risk of special characters.
Since the escaping functionality has been completely broken since it
was introduced, we know that it has no users. As such, we can change
the escaping mechanism without having to worry about backwards
compatibility issues.
For the curious, this was detected by chance: it happens that the
lz4-compressed text of a test file for remotefilelog compressed to
something containing a ;, which then caused the failure when I moved
remotefilelog to using batching for file content fetching.
# test-batching.py - tests for transparent command batching
#
# Copyright 2011 Peter Arrenbrecht <peter@arrenbrecht.ch>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
from mercurial.wireproto import localbatch, remotebatch, batchable, future
# equivalent of repo.repository
class thing(object):
def hello(self):
return "Ready."
# equivalent of localrepo.localrepository
class localthing(thing):
def foo(self, one, two=None):
if one:
return "%s and %s" % (one, two,)
return "Nope"
def bar(self, b, a):
return "%s und %s" % (b, a,)
def greet(self, name=None):
return "Hello, %s" % name
def batch(self):
'''Support for local batching.'''
return localbatch(self)
# usage of "thing" interface
def use(it):
# Direct call to base method shared between client and server.
print it.hello()
# Direct calls to proxied methods. They cause individual roundtrips.
print it.foo("Un", two="Deux")
print it.bar("Eins", "Zwei")
# Batched call to a couple of (possibly proxied) methods.
batch = it.batch()
# The calls return futures to eventually hold results.
foo = batch.foo(one="One", two="Two")
foo2 = batch.foo(None)
bar = batch.bar("Eins", "Zwei")
# We can call non-batchable proxy methods, but the break the current batch
# request and cause additional roundtrips.
greet = batch.greet(name="John Smith")
# We can also add local methods into the mix, but they break the batch too.
hello = batch.hello()
bar2 = batch.bar(b="Uno", a="Due")
# Only now are all the calls executed in sequence, with as few roundtrips
# as possible.
batch.submit()
# After the call to submit, the futures actually contain values.
print foo.value
print foo2.value
print bar.value
print greet.value
print hello.value
print bar2.value
# local usage
mylocal = localthing()
print
print "== Local"
use(mylocal)
# demo remoting; mimicks what wireproto and HTTP/SSH do
# shared
def escapearg(plain):
return (plain
.replace(':', '::')
.replace(',', ':,')
.replace(';', ':;')
.replace('=', ':='))
def unescapearg(escaped):
return (escaped
.replace(':=', '=')
.replace(':;', ';')
.replace(':,', ',')
.replace('::', ':'))
# server side
# equivalent of wireproto's global functions
class server(object):
def __init__(self, local):
self.local = local
def _call(self, name, args):
args = dict(arg.split('=', 1) for arg in args)
return getattr(self, name)(**args)
def perform(self, req):
print "REQ:", req
name, args = req.split('?', 1)
args = args.split('&')
vals = dict(arg.split('=', 1) for arg in args)
res = getattr(self, name)(**vals)
print " ->", res
return res
def batch(self, cmds):
res = []
for pair in cmds.split(';'):
name, args = pair.split(':', 1)
vals = {}
for a in args.split(','):
if a:
n, v = a.split('=')
vals[n] = unescapearg(v)
res.append(escapearg(getattr(self, name)(**vals)))
return ';'.join(res)
def foo(self, one, two):
return mangle(self.local.foo(unmangle(one), unmangle(two)))
def bar(self, b, a):
return mangle(self.local.bar(unmangle(b), unmangle(a)))
def greet(self, name):
return mangle(self.local.greet(unmangle(name)))
myserver = server(mylocal)
# local side
# equivalent of wireproto.encode/decodelist, that is, type-specific marshalling
# here we just transform the strings a bit to check we're properly en-/decoding
def mangle(s):
return ''.join(chr(ord(c) + 1) for c in s)
def unmangle(s):
return ''.join(chr(ord(c) - 1) for c in s)
# equivalent of wireproto.wirerepository and something like http's wire format
class remotething(thing):
def __init__(self, server):
self.server = server
def _submitone(self, name, args):
req = name + '?' + '&'.join(['%s=%s' % (n, v) for n, v in args])
return self.server.perform(req)
def _submitbatch(self, cmds):
req = []
for name, args in cmds:
args = ','.join(n + '=' + escapearg(v) for n, v in args)
req.append(name + ':' + args)
req = ';'.join(req)
res = self._submitone('batch', [('cmds', req,)])
return res.split(';')
def batch(self):
return remotebatch(self)
@batchable
def foo(self, one, two=None):
if not one:
yield "Nope", None
encargs = [('one', mangle(one),), ('two', mangle(two),)]
encresref = future()
yield encargs, encresref
yield unmangle(encresref.value)
@batchable
def bar(self, b, a):
encresref = future()
yield [('b', mangle(b),), ('a', mangle(a),)], encresref
yield unmangle(encresref.value)
# greet is coded directly. It therefore does not support batching. If it
# does appear in a batch, the batch is split around greet, and the call to
# greet is done in its own roundtrip.
def greet(self, name=None):
return unmangle(self._submitone('greet', [('name', mangle(name),)]))
# demo remote usage
myproxy = remotething(myserver)
print
print "== Remote"
use(myproxy)