hgext/largefiles/proto.py

wireproto: perform chunking and compression at protocol layer (API)

Currently, the "streamres" response type is populated with a generator
of chunks with compression possibly already applied. This puts the onus
on commands to perform chunking and compression. Architecturally, I
think this is the wrong place to perform this work. I think commands
should say "here is the data" and the protocol layer should take care
of encoding the final bytes to put on the wire.

Additionally, upcoming commits will improve wire protocol support for
compression. Having a central place for performing compression in the
protocol transport layer will be easier than having to deal with
compression at the commands layer.

This commit refactors the "streamres" response type to accept either
a generator or an object with "read." Additionally, the type now
accepts a flag indicating whether the response is a "version 1
compressible" response. This basically identifies all commands
currently performing compression. I could have used a special type
for this, but a flag works just as well. The argument name
foreshadows the introduction of wire protocol changes, hence the "v1."

The code for chunking and compressing has been moved to the output
generation function for each protocol transport. Some code has been
inlined, resulting in the deletion of now unused methods.

# 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,
    wireproto,
)

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
capabilitiesorig = None
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.'''
    proto.redirect()

    path = lfutil.storepath(repo, sha)
    util.makedirs(os.path.dirname(path))
    tmpfp = util.atomictempfile(path, createmode=repo.store.createmode)

    try:
        proto.getfile(tmpfp)
        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 wireproto.pushres(1)
    finally:
        tmpfp.discard()

    return wireproto.pushres(0)

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 wireproto.streamres(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 '2\n'
    return '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={'content-type':'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))

        @wireproto.batchable
        def statlfile(self, sha):
            f = wireproto.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(repo, proto):
    '''Wrap server command to announce largefile server capability'''
    return capabilitiesorig(repo, proto) + ' largefiles=serve'

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

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

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

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