hgext/largefiles/proto.py

httppeer: detect redirect to URL without query string (issue5860)

197d10e157ce subtly changed the HTTP peer's handling of HTTP redirects.

Before that changeset, we instantiated an HTTP peer instance and
performed the capabilities lookup with that instance. The old code had
the following relevant properties:

1) The HTTP request layer would automatically follow HTTP redirects.
2) An encountered HTTP redirect would update a peer instance variable
   pointing to the repo URL.
3) The peer would automagically perform a "capabilities" command
   request if a caller requested capabilities but capabilities were
   not yet defined.

The first HTTP request issued by a peer is for ?cmd=capabilities. If
the server responds with an HTTP redirect to a ?cmd=capabilities URL,
the HTTP request layer automatically followed it, retrieved a valid
capabilities response, and the peer's base URL was updated
automatically so subsequent requests used the proper URL. In other
words, things "just worked."

In the case where the server redirected to a URL without the
?cmd=capabilities query string, the HTTP request layer would follow
the redirect and likely encounter HTML. The peer's base URL would be
updated and the unexpected Content-Type would raise a RepoError. We
would catch RepoError and immediately call between() (testing the case
for pre 0.9.1 servers not supporting the "capabilities" command). e.g.

    try:
        inst._fetchcaps()
    except error.RepoError:
        inst.between([(nullid, nullid)])

between() would eventually call into _callstream(). And _callstream()
made a call to self.capable('httpheader'). capable() would call
self.capabilities(), which would see that no capabilities were set
(because HTML was returned for that request) and call the "capabilities"
command to fetch capabilities. Because the base URL had been updated
from the redirect, this 2nd "capabilities" command would succeed and
the client would immediately call "between," which would also succeed.
The legacy handshake succeeded. Only because "capabilities" was
successfully executed as a side effect did the peer recognize that it
was talking to a modern server. In other words, this all appeared to
work accidentally.

After 197d10e157ce, we stopped calling the "capabilities" command on
the peer instance. Instead, we made the request via a low-level opener,
detected the redirect as part of response handling code, and passed the
redirected URL into the constructed peer instance.

For cases where the redirected URL included the query string, this
"just worked." But for cases where the redirected URL stripped the query
string, we threw RepoError and because we removed the "between" handshake
fallback, we fell through to the "is a static HTTP repo" check and
performed an HTTP request for .hg/requires.

While 197d10e157ce was marked as backwards incompatible, the only
intended backwards incompatible behavior was not performing the
"between" fallback. It was not realized that the "between" command
had the side-effect of recovering from an errant redirect that
dropped the query string.

This commit restores the previous behavior and allows clients to
handle a redirect that drops the query string. In the case where
the request is redirected and the query string is dropped, we raise
a special case of RepoError. We then catch this special exception in
the handshake code and perform another "capabilities" request against
the redirected URL. If that works, all is well. Otherwise, we fall back
to the "is a static HTTP repo" check.

The new code is arguably better than before 197d10e157ce, as it is
explicit about the expected behavior and we avoid performing a
"between" request, saving a server round trip.

Differential Revision: https://phab.mercurial-scm.org/D3433

# Copyright 2011 Fog Creek Software
#
# 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
import re

from mercurial.i18n import _

from mercurial import (
    error,
    httppeer,
    util,
    wireprototypes,
    wireprotov1peer,
)

from . import (
    lfutil,
)

urlerr = util.urlerr
urlreq = util.urlreq

LARGEFILES_REQUIRED_MSG = ('\nThis repository uses the largefiles extension.'
                           '\n\nPlease enable it in your Mercurial config '
                           'file.\n')

# these will all be replaced by largefiles.uisetup
ssholdcallstream = None
httpoldcallstream = None

def putlfile(repo, proto, sha):
    '''Server command for putting a largefile into a repository's local store
    and into the user cache.'''
    with proto.mayberedirectstdio() as output:
        path = lfutil.storepath(repo, sha)
        util.makedirs(os.path.dirname(path))
        tmpfp = util.atomictempfile(path, createmode=repo.store.createmode)

        try:
            for p in proto.getpayload():
                tmpfp.write(p)
            tmpfp._fp.seek(0)
            if sha != lfutil.hexsha1(tmpfp._fp):
                raise IOError(0, _('largefile contents do not match hash'))
            tmpfp.close()
            lfutil.linktousercache(repo, sha)
        except IOError as e:
            repo.ui.warn(_('largefiles: failed to put %s into store: %s\n') %
                         (sha, e.strerror))
            return wireprototypes.pushres(
                1, output.getvalue() if output else '')
        finally:
            tmpfp.discard()

    return wireprototypes.pushres(0, output.getvalue() if output else '')

def getlfile(repo, proto, sha):
    '''Server command for retrieving a largefile from the repository-local
    cache or user cache.'''
    filename = lfutil.findfile(repo, sha)
    if not filename:
        raise error.Abort(_('requested largefile %s not present in cache')
                          % sha)
    f = open(filename, 'rb')
    length = os.fstat(f.fileno())[6]

    # Since we can't set an HTTP content-length header here, and
    # Mercurial core provides no way to give the length of a streamres
    # (and reading the entire file into RAM would be ill-advised), we
    # just send the length on the first line of the response, like the
    # ssh proto does for string responses.
    def generator():
        yield '%d\n' % length
        for chunk in util.filechunkiter(f):
            yield chunk
    return wireprototypes.streamreslegacy(gen=generator())

def statlfile(repo, proto, sha):
    '''Server command for checking if a largefile is present - returns '2\n' if
    the largefile is missing, '0\n' if it seems to be in good condition.

    The value 1 is reserved for mismatched checksum, but that is too expensive
    to be verified on every stat and must be caught be running 'hg verify'
    server side.'''
    filename = lfutil.findfile(repo, sha)
    if not filename:
        return wireprototypes.bytesresponse('2\n')
    return wireprototypes.bytesresponse('0\n')

def wirereposetup(ui, repo):
    class lfileswirerepository(repo.__class__):
        def putlfile(self, sha, fd):
            # unfortunately, httprepository._callpush tries to convert its
            # input file-like into a bundle before sending it, so we can't use
            # it ...
            if issubclass(self.__class__, httppeer.httppeer):
                res = self._call('putlfile', data=fd, sha=sha,
                    headers={r'content-type': r'application/mercurial-0.1'})
                try:
                    d, output = res.split('\n', 1)
                    for l in output.splitlines(True):
                        self.ui.warn(_('remote: '), l) # assume l ends with \n
                    return int(d)
                except ValueError:
                    self.ui.warn(_('unexpected putlfile response: %r\n') % res)
                    return 1
            # ... but we can't use sshrepository._call because the data=
            # argument won't get sent, and _callpush does exactly what we want
            # in this case: send the data straight through
            else:
                try:
                    ret, output = self._callpush("putlfile", fd, sha=sha)
                    if ret == "":
                        raise error.ResponseError(_('putlfile failed:'),
                                output)
                    return int(ret)
                except IOError:
                    return 1
                except ValueError:
                    raise error.ResponseError(
                        _('putlfile failed (unexpected response):'), ret)

        def getlfile(self, sha):
            """returns an iterable with the chunks of the file with sha sha"""
            stream = self._callstream("getlfile", sha=sha)
            length = stream.readline()
            try:
                length = int(length)
            except ValueError:
                self._abort(error.ResponseError(_("unexpected response:"),
                                                length))

            # SSH streams will block if reading more than length
            for chunk in util.filechunkiter(stream, limit=length):
                yield chunk
            # HTTP streams must hit the end to process the last empty
            # chunk of Chunked-Encoding so the connection can be reused.
            if issubclass(self.__class__, httppeer.httppeer):
                chunk = stream.read(1)
                if chunk:
                    self._abort(error.ResponseError(_("unexpected response:"),
                                                    chunk))

        @wireprotov1peer.batchable
        def statlfile(self, sha):
            f = wireprotov1peer.future()
            result = {'sha': sha}
            yield result, f
            try:
                yield int(f.value)
            except (ValueError, urlerr.httperror):
                # If the server returns anything but an integer followed by a
                # newline, newline, it's not speaking our language; if we get
                # an HTTP error, we can't be sure the largefile is present;
                # either way, consider it missing.
                yield 2

    repo.__class__ = lfileswirerepository

# advertise the largefiles=serve capability
def _capabilities(orig, repo, proto):
    '''announce largefile server capability'''
    caps = orig(repo, proto)
    caps.append('largefiles=serve')
    return caps

def heads(orig, repo, proto):
    '''Wrap server command - largefile capable clients will know to call
    lheads instead'''
    if lfutil.islfilesrepo(repo):
        return wireprototypes.ooberror(LARGEFILES_REQUIRED_MSG)

    return orig(repo, proto)

def sshrepocallstream(self, cmd, **args):
    if cmd == 'heads' and self.capable('largefiles'):
        cmd = 'lheads'
    if cmd == 'batch' and self.capable('largefiles'):
        args[r'cmds'] = args[r'cmds'].replace('heads ', 'lheads ')
    return ssholdcallstream(self, cmd, **args)

headsre = re.compile(br'(^|;)heads\b')

def httprepocallstream(self, cmd, **args):
    if cmd == 'heads' and self.capable('largefiles'):
        cmd = 'lheads'
    if cmd == 'batch' and self.capable('largefiles'):
        args[r'cmds'] = headsre.sub('lheads', args[r'cmds'])
    return httpoldcallstream(self, cmd, **args)