view mercurial/statichttprepo.py @ 25708:d3d32643c060

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.

# statichttprepo.py - simple http repository class for mercurial
#
# This provides read-only repo access to repositories exported via static http
#
# Copyright 2005-2007 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.

from i18n import _
import changelog, byterange, url, error, namespaces
import localrepo, manifest, util, scmutil, store
import urllib, urllib2, errno, os

class httprangereader(object):
    def __init__(self, url, opener):
        # we assume opener has HTTPRangeHandler
        self.url = url
        self.pos = 0
        self.opener = opener
        self.name = url
    def seek(self, pos):
        self.pos = pos
    def read(self, bytes=None):
        req = urllib2.Request(self.url)
        end = ''
        if bytes:
            end = self.pos + bytes - 1
        if self.pos or end:
            req.add_header('Range', 'bytes=%d-%s' % (self.pos, end))

        try:
            f = self.opener.open(req)
            data = f.read()
            code = f.code
        except urllib2.HTTPError as inst:
            num = inst.code == 404 and errno.ENOENT or None
            raise IOError(num, inst)
        except urllib2.URLError as inst:
            raise IOError(None, inst.reason[1])

        if code == 200:
            # HTTPRangeHandler does nothing if remote does not support
            # Range headers and returns the full entity. Let's slice it.
            if bytes:
                data = data[self.pos:self.pos + bytes]
            else:
                data = data[self.pos:]
        elif bytes:
            data = data[:bytes]
        self.pos += len(data)
        return data
    def readlines(self):
        return self.read().splitlines(True)
    def __iter__(self):
        return iter(self.readlines())
    def close(self):
        pass

def build_opener(ui, authinfo):
    # urllib cannot handle URLs with embedded user or passwd
    urlopener = url.opener(ui, authinfo)
    urlopener.add_handler(byterange.HTTPRangeHandler())

    class statichttpvfs(scmutil.abstractvfs):
        def __init__(self, base):
            self.base = base

        def __call__(self, path, mode='r', *args, **kw):
            if mode not in ('r', 'rb'):
                raise IOError('Permission denied')
            f = "/".join((self.base, urllib.quote(path)))
            return httprangereader(f, urlopener)

        def join(self, path):
            if path:
                return os.path.join(self.base, path)
            else:
                return self.base

    return statichttpvfs

class statichttppeer(localrepo.localpeer):
    def local(self):
        return None
    def canpush(self):
        return False

class statichttprepository(localrepo.localrepository):
    supported = localrepo.localrepository._basesupported

    def __init__(self, ui, path):
        self._url = path
        self.ui = ui

        self.root = path
        u = util.url(path.rstrip('/') + "/.hg")
        self.path, authinfo = u.authinfo()

        opener = build_opener(ui, authinfo)
        self.opener = opener(self.path)
        self.vfs = self.opener
        self._phasedefaults = []

        self.names = namespaces.namespaces()

        try:
            requirements = scmutil.readrequires(self.vfs, self.supported)
        except IOError as inst:
            if inst.errno != errno.ENOENT:
                raise
            requirements = set()

            # check if it is a non-empty old-style repository
            try:
                fp = self.vfs("00changelog.i")
                fp.read(1)
                fp.close()
            except IOError as inst:
                if inst.errno != errno.ENOENT:
                    raise
                # we do not care about empty old-style repositories here
                msg = _("'%s' does not appear to be an hg repository") % path
                raise error.RepoError(msg)

        # setup store
        self.store = store.store(requirements, self.path, opener)
        self.spath = self.store.path
        self.svfs = self.store.opener
        self.sjoin = self.store.join
        self._filecache = {}
        self.requirements = requirements

        self.manifest = manifest.manifest(self.svfs)
        self.changelog = changelog.changelog(self.svfs)
        self._tags = None
        self.nodetagscache = None
        self._branchcaches = {}
        self._revbranchcache = None
        self.encodepats = None
        self.decodepats = None
        self._transref = None

    def _restrictcapabilities(self, caps):
        caps = super(statichttprepository, self)._restrictcapabilities(caps)
        return caps.difference(["pushkey"])

    def url(self):
        return self._url

    def local(self):
        return False

    def peer(self):
        return statichttppeer(self)

    def lock(self, wait=True):
        raise util.Abort(_('cannot lock static-http repository'))

def instance(ui, path, create):
    if create:
        raise util.Abort(_('cannot create new static-http repository'))
    return statichttprepository(ui, path[7:])