hgext/largefiles/proto.py

largefiles: don't copy largefiles from working dir to the store while converting

Previously, if one or more largefiles for a repo being converted were not in the
usercache, the convert would abort with a reference to the largefile being
missing (as opposed to the previous patch, where the standin was referenced as
missing).  This is because commitctx() tries to copy all largefiles to the
local store, first from the user cache, and if the file isn't found there, from
the working directory.  No files will exist in the working directory during a
convert, however.  It is not sufficient to force the source repo to be local
before proceeding, because clone and pull do not download largefiles by default.

This is slightly less than ideal because while the conversion will now complete,
it won't be possible to update to revs with missing largefiles unless the user
intervenes manually, because there is no default path pointing back to the
source repo.  Ideally these files would be cached during the conversion.

This check could have been done in reposetup.commitctx() instead, but this
ensures the local store directory is created, which is necessary to enable the
standin matcher.

The rm -> 'rm -f' change in the test is to temporarily suppress an error
clearing the cache- as noted, the cache is is not repopulated during convert.
When that is fixed, this can be changed back and the verification errors will
disappear too.

# 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.

import os
import urllib2

from mercurial import error, httppeer, util, wireproto
from mercurial.wireproto import batchable, future
from mercurial.i18n import _

import lfutil

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

def putlfile(repo, proto, sha):
    '''Put 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:
        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, e:
            repo.ui.warn(_('largefiles: failed to put %s into store: %s') %
                         (sha, e.strerror))
            return wireproto.pushres(1)
    finally:
        tmpfp.discard()

    return wireproto.pushres(0)

def getlfile(repo, proto, sha):
    '''Retrieve a largefile from the repository-local cache or system
    cache.'''
    filename = lfutil.findfile(repo, sha)
    if not filename:
        raise util.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 f:
            yield chunk
    return wireproto.streamres(generator())

def statlfile(repo, proto, sha):
    '''Return '2\n' if the largefile is missing, '1\n' if it has a
    mismatched checksum, or '0\n' if it is in good condition'''
    filename = lfutil.findfile(repo, sha)
    if not filename:
        return '2\n'
    fd = None
    try:
        fd = open(filename, 'rb')
        return lfutil.hexsha1(fd) == sha and '0\n' or '1\n'
    finally:
        if fd:
            fd.close()

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 = None
                try:
                    res = self._call('putlfile', data=fd, sha=sha,
                        headers={'content-type':'application/mercurial-0.1'})
                    d, output = res.split('\n', 1)
                    for l in output.splitlines(True):
                        self.ui.warn(_('remote: '), l, '\n')
                    return int(d)
                except (ValueError, urllib2.HTTPError):
                    self.ui.warn(_('unexpected putlfile response: %s') % 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):
            stream = self._callstream("getlfile", sha=sha)
            length = stream.readline()
            try:
                length = int(length)
            except ValueError:
                self._abort(error.ResponseError(_("unexpected response:"),
                                                length))
            return (length, stream)

        @batchable
        def statlfile(self, sha):
            f = future()
            result = {'sha': sha}
            yield result, f
            try:
                yield int(f.value)
            except (ValueError, urllib2.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):
    return capabilitiesorig(repo, proto) + ' largefiles=serve'

# duplicate what Mercurial's new out-of-band errors mechanism does, because
# clients old and new alike both handle it well
def webprotorefuseclient(self, message):
    self.req.header([('Content-Type', 'application/hg-error')])
    return message

def sshprotorefuseclient(self, message):
    self.ui.write_err('%s\n-\n' % message)
    self.fout.write('\n')
    self.fout.flush()

    return ''

def heads(repo, proto):
    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)

def httprepocallstream(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 httpoldcallstream(self, cmd, **args)