hgext/lfs/wrapper.py

43075:57875cf423c9

    util,
    vfs as vfsmod,
    wireprotov1server,
)

from mercurial.interfaces import (
    repository,
)

from mercurial.utils import (
    storageutil,
    stringutil,
)

    pointer,
)

eh = exthelper.exthelper()

@eh.wrapfunction(localrepo, 'makefilestorage')
def localrepomakefilestorage(orig, requirements, features, **kwargs):
    if b'lfs' in requirements:
        features.add(repository.REPO_FEATURE_LFS)

    return orig(requirements=requirements, features=features, **kwargs)

@eh.wrapfunction(changegroup, 'allsupportedversions')
def allsupportedversions(orig, ui):
    versions = orig(ui)
    versions.add('03')
    return versions

@eh.wrapfunction(wireprotov1server, '_capabilities')
def _capabilities(orig, repo, proto):
    '''Wrap server command to announce lfs server capability'''
    caps = orig(repo, proto)

            caps.append('lfs-serve')

        caps.append('lfs')
    return caps

def bypasscheckhash(self, text):
    return False

def readfromstore(self, text):
    """Read filelog content from local blobstore transform for flagprocessor.

    Default tranform for flagprocessor, returning contents from blobstore.

    # pack hg filelog metadata
    hgmeta = {}
    for k in p.keys():
        if k.startswith('x-hg-'):
            name = k[len('x-hg-'):]
            hgmeta[name] = p[k]
    if hgmeta or text.startswith('\1\n'):
        text = storageutil.packmeta(hgmeta, text)

    return (text, True, {})

def writetostore(self, text, sidedata):
    # hg filelog metadata (includes rename, etc)
    hgmeta, offset = storageutil.parsemeta(text)
    if offset and offset > 0:

        for k, v in hgmeta.iteritems():
            metadata['x-hg-%s' % k] = v

    rawtext = metadata.serialize()
    return (rawtext, False)

def _islfs(rlog, node=None, rev=None):
    if rev is None:
        if node is None:
            # both None - likely working copy content where node is not ready

    if node == nullid:
        return False
    flags = rlog._revlog.flags(rev)
    return bool(flags & revlog.REVIDX_EXTSTORED)

# Wrapping may also be applied by remotefilelog
def filelogaddrevision(orig, self, text, transaction, link, p1, p2,
                       cachedelta=None, node=None,
                       flags=revlog.REVIDX_DEFAULT_FLAGS, **kwds):
    # The matcher isn't available if reposetup() wasn't called.
    lfstrack = self._revlog.opener.options.get('lfstrack')

    if lfstrack:
        textlen = len(text)

            textlen -= offset

        if lfstrack(self._revlog.filename, textlen):
            flags |= revlog.REVIDX_EXTSTORED

    return orig(self, text, transaction, link, p1, p2, cachedelta=cachedelta,
                node=node, flags=flags, **kwds)

# Wrapping may also be applied by remotefilelog
def filelogrenamed(orig, self, node):
    if _islfs(self, node):
        rawtext = self._revlog.rawdata(node)

            return metadata['x-hg-copy'], bin(metadata['x-hg-copyrev'])
        else:
            return False
    return orig(self, node)

# Wrapping may also be applied by remotefilelog
def filelogsize(orig, self, rev):
    if _islfs(self, rev=rev):
        # fast path: use lfs metadata to answer size
        rawtext = self._revlog.rawdata(rev)
        metadata = pointer.deserialize(rawtext)
        return int(metadata['size'])
    return orig(self, rev)

@eh.wrapfunction(context.basefilectx, 'cmp')
def filectxcmp(orig, self, fctx):
    """returns True if text is different than fctx"""
    # some fctx (ex. hg-git) is not based on basefilectx and do not have islfs

        p1 = pointer.deserialize(self.rawdata())
        p2 = pointer.deserialize(fctx.rawdata())
        return p1.oid() != p2.oid()
    return orig(self, fctx)

@eh.wrapfunction(context.basefilectx, 'isbinary')
def filectxisbinary(orig, self):
    if self.islfs():
        # fast path: use lfs metadata to answer isbinary
        metadata = pointer.deserialize(self.rawdata())
        # if lfs metadata says nothing, assume it's binary by default
        return bool(int(metadata.get('x-is-binary', 1)))
    return orig(self)

def filectxislfs(self):
    return _islfs(self.filelog(), self.filenode())

@eh.wrapfunction(cmdutil, '_updatecatformatter')
def _updatecatformatter(orig, fm, ctx, matcher, path, decode):
    orig(fm, ctx, matcher, path, decode)
    fm.data(rawdata=ctx[path].rawdata())

@eh.wrapfunction(scmutil, 'wrapconvertsink')
def convertsink(orig, sink):
    sink = orig(sink)
    if sink.repotype == 'hg':
        class lfssink(sink.__class__):
            def putcommit(self, files, copies, parents, commit, source, revmap,
                          full, cleanp2):
                pc = super(lfssink, self).putcommit
                node = pc(files, copies, parents, commit, source, revmap, full,
                          cleanp2)

                if 'lfs' not in self.repo.requirements:
                    ctx = self.repo[node]

                    # The file list may contain removed files, so check for

                return node

        sink.__class__ = lfssink

    return sink

# bundlerepo uses "vfsmod.readonlyvfs(othervfs)", we need to make sure lfs
# options and blob stores are passed from othervfs to the new readonlyvfs.
@eh.wrapfunction(vfsmod.readonlyvfs, '__init__')
def vfsinit(orig, self, othervfs):

    # blobstore attributes are not always ready at this time.
    for name in ['lfslocalblobstore', 'lfsremoteblobstore']:
        if util.safehasattr(othervfs, name):
            setattr(self, name, getattr(othervfs, name))

def _prefetchfiles(repo, revs, match):
    """Ensure that required LFS blobs are present, fetching them as a group if
    needed."""
    if not util.safehasattr(repo.svfs, 'lfslocalblobstore'):
        return

    if pointers:
        # Recalculating the repo store here allows 'paths.default' that is set
        # on the repo by a clone command to be used for the update.
        blobstore.remote(repo).readbatch(pointers, localstore)

def _canskipupload(repo):
    # Skip if this hasn't been passed to reposetup()
    if not util.safehasattr(repo.svfs, 'lfsremoteblobstore'):
        return True

    # if remotestore is a null store, upload is a no-op and can be skipped
    return isinstance(repo.svfs.lfsremoteblobstore, blobstore._nullremote)

def candownload(repo):
    # Skip if this hasn't been passed to reposetup()
    if not util.safehasattr(repo.svfs, 'lfsremoteblobstore'):
        return False

    # if remotestore is a null store, downloads will lead to nothing
    return not isinstance(repo.svfs.lfsremoteblobstore, blobstore._nullremote)

def uploadblobsfromrevs(repo, revs):
    '''upload lfs blobs introduced by revs

    Note: also used by other extensions e. g. infinitepush. avoid renaming.

    if _canskipupload(repo):
        return
    pointers = extractpointers(repo, revs)
    uploadblobs(repo, pointers)

def prepush(pushop):
    """Prepush hook.

    Read through the revisions to push, looking for filelog entries that can be
    deserialized into metadata so that we can block the push on their upload to
    the remote blobstore.
    """
    return uploadblobsfromrevs(pushop.repo, pushop.outgoing.missing)

@eh.wrapfunction(exchange, 'push')
def push(orig, repo, remote, *args, **kwargs):
    """bail on push if the extension isn't enabled on remote when needed, and
    update the remote store based on the destination path."""

        # this repo use lfs, and the remote repo needs the extension loaded.
        if not remote.local() and not remote.capable('lfs'):
            # This is a copy of the message in exchange.push() when requirements
            # are missing between local repos.
            m = _("required features are not supported in the destination: %s")
            raise error.Abort(m % 'lfs',
                              hint=_('enable the lfs extension on the server'))

        # Repositories where this extension is disabled won't have the field.
        # But if there's a requirement, then the extension must be loaded AND
        # there may be blobs to push.
        remotestore = repo.svfs.lfsremoteblobstore

        finally:
            repo.svfs.lfsremoteblobstore = remotestore
    else:
        return orig(repo, remote, *args, **kwargs)

# when writing a bundle via "hg bundle" command, upload related LFS blobs
@eh.wrapfunction(bundle2, 'writenewbundle')
def writenewbundle(orig, ui, repo, source, filename, bundletype, outgoing,
                   *args, **kwargs):
    """upload LFS blobs added by outgoing revisions on 'hg bundle'"""
    uploadblobsfromrevs(repo, outgoing.missing)
    return orig(ui, repo, source, filename, bundletype, outgoing, *args,
                **kwargs)

def extractpointers(repo, revs):
    """return a list of lfs pointers added by given revs"""
    repo.ui.debug('lfs: computing set of blobs to upload\n')
    pointers = {}

            ctx = repo[r]
            for p in pointersfromctx(ctx).values():
                pointers[p.oid()] = p
            progress.increment()
        return sorted(pointers.values(), key=lambda p: p.oid())

def pointerfromctx(ctx, f, removed=False):
    """return a pointer for the named file from the given changectx, or None if
    the file isn't LFS.

        p = pointer.deserialize(fctx.rawdata())
        if ctx == _ctx:
            return p
        return {}
    except pointer.InvalidPointer as ex:
        raise error.Abort(_('lfs: corrupted pointer (%s@%s): %s\n')
                          % (f, short(_ctx.node()), ex))

def pointersfromctx(ctx, removed=False):
    """return a dict {path: pointer} for given single changectx.

    If ``removed`` == True and the LFS file was removed from ``ctx``, the value

        p = pointerfromctx(ctx, f, removed=removed)
        if p is not None:
            result[f] = p
    return result

def uploadblobs(repo, pointers):
    """upload given pointers from local blobstore"""
    if not pointers:
        return

    remoteblob = repo.svfs.lfsremoteblobstore
    remoteblob.writebatch(pointers, repo.svfs.lfslocalblobstore)

@eh.wrapfunction(upgrade, '_finishdatamigration')
def upgradefinishdatamigration(orig, ui, srcrepo, dstrepo, requirements):
    orig(ui, srcrepo, dstrepo, requirements)

    # Skip if this hasn't been passed to reposetup()
    if (util.safehasattr(srcrepo.svfs, 'lfslocalblobstore') and
        util.safehasattr(dstrepo.svfs, 'lfslocalblobstore')):
        srclfsvfs = srcrepo.svfs.lfslocalblobstore.vfs
        dstlfsvfs = dstrepo.svfs.lfslocalblobstore.vfs

        for dirpath, dirs, files in srclfsvfs.walk():
            for oid in files:
                ui.write(_('copying lfs blob %s\n') % oid)
                lfutil.link(srclfsvfs.join(oid), dstlfsvfs.join(oid))

@eh.wrapfunction(upgrade, 'preservedrequirements')
@eh.wrapfunction(upgrade, 'supporteddestrequirements')
def upgraderequirements(orig, repo):
    reqs = orig(repo)

43076:2372284d9457

    util,
    vfs as vfsmod,
    wireprotov1server,
)

from mercurial.interfaces import repository

from mercurial.utils import (
    storageutil,
    stringutil,
)

    pointer,
)

eh = exthelper.exthelper()


@eh.wrapfunction(localrepo, 'makefilestorage')
def localrepomakefilestorage(orig, requirements, features, **kwargs):
    if b'lfs' in requirements:
        features.add(repository.REPO_FEATURE_LFS)

    return orig(requirements=requirements, features=features, **kwargs)


@eh.wrapfunction(changegroup, 'allsupportedversions')
def allsupportedversions(orig, ui):
    versions = orig(ui)
    versions.add('03')
    return versions


@eh.wrapfunction(wireprotov1server, '_capabilities')
def _capabilities(orig, repo, proto):
    '''Wrap server command to announce lfs server capability'''
    caps = orig(repo, proto)

            caps.append('lfs-serve')

        caps.append('lfs')
    return caps


def bypasscheckhash(self, text):
    return False


def readfromstore(self, text):
    """Read filelog content from local blobstore transform for flagprocessor.

    Default tranform for flagprocessor, returning contents from blobstore.

    # pack hg filelog metadata
    hgmeta = {}
    for k in p.keys():
        if k.startswith('x-hg-'):
            name = k[len('x-hg-') :]
            hgmeta[name] = p[k]
    if hgmeta or text.startswith('\1\n'):
        text = storageutil.packmeta(hgmeta, text)

    return (text, True, {})


def writetostore(self, text, sidedata):
    # hg filelog metadata (includes rename, etc)
    hgmeta, offset = storageutil.parsemeta(text)
    if offset and offset > 0:

        for k, v in hgmeta.iteritems():
            metadata['x-hg-%s' % k] = v

    rawtext = metadata.serialize()
    return (rawtext, False)


def _islfs(rlog, node=None, rev=None):
    if rev is None:
        if node is None:
            # both None - likely working copy content where node is not ready

    if node == nullid:
        return False
    flags = rlog._revlog.flags(rev)
    return bool(flags & revlog.REVIDX_EXTSTORED)


# Wrapping may also be applied by remotefilelog
def filelogaddrevision(
    orig,
    self,
    text,
    transaction,
    link,
    p1,
    p2,
    cachedelta=None,
    node=None,
    flags=revlog.REVIDX_DEFAULT_FLAGS,
    **kwds
):
    # The matcher isn't available if reposetup() wasn't called.
    lfstrack = self._revlog.opener.options.get('lfstrack')

    if lfstrack:
        textlen = len(text)

            textlen -= offset

        if lfstrack(self._revlog.filename, textlen):
            flags |= revlog.REVIDX_EXTSTORED

    return orig(
        self,
        text,
        transaction,
        link,
        p1,
        p2,
        cachedelta=cachedelta,
        node=node,
        flags=flags,
        **kwds
    )


# Wrapping may also be applied by remotefilelog
def filelogrenamed(orig, self, node):
    if _islfs(self, node):
        rawtext = self._revlog.rawdata(node)

            return metadata['x-hg-copy'], bin(metadata['x-hg-copyrev'])
        else:
            return False
    return orig(self, node)


# Wrapping may also be applied by remotefilelog
def filelogsize(orig, self, rev):
    if _islfs(self, rev=rev):
        # fast path: use lfs metadata to answer size
        rawtext = self._revlog.rawdata(rev)
        metadata = pointer.deserialize(rawtext)
        return int(metadata['size'])
    return orig(self, rev)


@eh.wrapfunction(context.basefilectx, 'cmp')
def filectxcmp(orig, self, fctx):
    """returns True if text is different than fctx"""
    # some fctx (ex. hg-git) is not based on basefilectx and do not have islfs

        p1 = pointer.deserialize(self.rawdata())
        p2 = pointer.deserialize(fctx.rawdata())
        return p1.oid() != p2.oid()
    return orig(self, fctx)


@eh.wrapfunction(context.basefilectx, 'isbinary')
def filectxisbinary(orig, self):
    if self.islfs():
        # fast path: use lfs metadata to answer isbinary
        metadata = pointer.deserialize(self.rawdata())
        # if lfs metadata says nothing, assume it's binary by default
        return bool(int(metadata.get('x-is-binary', 1)))
    return orig(self)


def filectxislfs(self):
    return _islfs(self.filelog(), self.filenode())


@eh.wrapfunction(cmdutil, '_updatecatformatter')
def _updatecatformatter(orig, fm, ctx, matcher, path, decode):
    orig(fm, ctx, matcher, path, decode)
    fm.data(rawdata=ctx[path].rawdata())


@eh.wrapfunction(scmutil, 'wrapconvertsink')
def convertsink(orig, sink):
    sink = orig(sink)
    if sink.repotype == 'hg':

        class lfssink(sink.__class__):
            def putcommit(
                self,
                files,
                copies,
                parents,
                commit,
                source,
                revmap,
                full,
                cleanp2,
            ):
                pc = super(lfssink, self).putcommit
                node = pc(
                    files,
                    copies,
                    parents,
                    commit,
                    source,
                    revmap,
                    full,
                    cleanp2,
                )

                if 'lfs' not in self.repo.requirements:
                    ctx = self.repo[node]

                    # The file list may contain removed files, so check for

                return node

        sink.__class__ = lfssink

    return sink


# bundlerepo uses "vfsmod.readonlyvfs(othervfs)", we need to make sure lfs
# options and blob stores are passed from othervfs to the new readonlyvfs.
@eh.wrapfunction(vfsmod.readonlyvfs, '__init__')
def vfsinit(orig, self, othervfs):

    # blobstore attributes are not always ready at this time.
    for name in ['lfslocalblobstore', 'lfsremoteblobstore']:
        if util.safehasattr(othervfs, name):
            setattr(self, name, getattr(othervfs, name))


def _prefetchfiles(repo, revs, match):
    """Ensure that required LFS blobs are present, fetching them as a group if
    needed."""
    if not util.safehasattr(repo.svfs, 'lfslocalblobstore'):
        return

    if pointers:
        # Recalculating the repo store here allows 'paths.default' that is set
        # on the repo by a clone command to be used for the update.
        blobstore.remote(repo).readbatch(pointers, localstore)


def _canskipupload(repo):
    # Skip if this hasn't been passed to reposetup()
    if not util.safehasattr(repo.svfs, 'lfsremoteblobstore'):
        return True

    # if remotestore is a null store, upload is a no-op and can be skipped
    return isinstance(repo.svfs.lfsremoteblobstore, blobstore._nullremote)


def candownload(repo):
    # Skip if this hasn't been passed to reposetup()
    if not util.safehasattr(repo.svfs, 'lfsremoteblobstore'):
        return False

    # if remotestore is a null store, downloads will lead to nothing
    return not isinstance(repo.svfs.lfsremoteblobstore, blobstore._nullremote)


def uploadblobsfromrevs(repo, revs):
    '''upload lfs blobs introduced by revs

    Note: also used by other extensions e. g. infinitepush. avoid renaming.

    if _canskipupload(repo):
        return
    pointers = extractpointers(repo, revs)
    uploadblobs(repo, pointers)


def prepush(pushop):
    """Prepush hook.

    Read through the revisions to push, looking for filelog entries that can be
    deserialized into metadata so that we can block the push on their upload to
    the remote blobstore.
    """
    return uploadblobsfromrevs(pushop.repo, pushop.outgoing.missing)


@eh.wrapfunction(exchange, 'push')
def push(orig, repo, remote, *args, **kwargs):
    """bail on push if the extension isn't enabled on remote when needed, and
    update the remote store based on the destination path."""

        # this repo use lfs, and the remote repo needs the extension loaded.
        if not remote.local() and not remote.capable('lfs'):
            # This is a copy of the message in exchange.push() when requirements
            # are missing between local repos.
            m = _("required features are not supported in the destination: %s")
            raise error.Abort(
                m % 'lfs', hint=_('enable the lfs extension on the server')
            )

        # Repositories where this extension is disabled won't have the field.
        # But if there's a requirement, then the extension must be loaded AND
        # there may be blobs to push.
        remotestore = repo.svfs.lfsremoteblobstore

        finally:
            repo.svfs.lfsremoteblobstore = remotestore
    else:
        return orig(repo, remote, *args, **kwargs)


# when writing a bundle via "hg bundle" command, upload related LFS blobs
@eh.wrapfunction(bundle2, 'writenewbundle')
def writenewbundle(
    orig, ui, repo, source, filename, bundletype, outgoing, *args, **kwargs
):
    """upload LFS blobs added by outgoing revisions on 'hg bundle'"""
    uploadblobsfromrevs(repo, outgoing.missing)
    return orig(
        ui, repo, source, filename, bundletype, outgoing, *args, **kwargs
    )


def extractpointers(repo, revs):
    """return a list of lfs pointers added by given revs"""
    repo.ui.debug('lfs: computing set of blobs to upload\n')
    pointers = {}

            ctx = repo[r]
            for p in pointersfromctx(ctx).values():
                pointers[p.oid()] = p
            progress.increment()
        return sorted(pointers.values(), key=lambda p: p.oid())


def pointerfromctx(ctx, f, removed=False):
    """return a pointer for the named file from the given changectx, or None if
    the file isn't LFS.

        p = pointer.deserialize(fctx.rawdata())
        if ctx == _ctx:
            return p
        return {}
    except pointer.InvalidPointer as ex:
        raise error.Abort(
            _('lfs: corrupted pointer (%s@%s): %s\n')
            % (f, short(_ctx.node()), ex)
        )


def pointersfromctx(ctx, removed=False):
    """return a dict {path: pointer} for given single changectx.

    If ``removed`` == True and the LFS file was removed from ``ctx``, the value

        p = pointerfromctx(ctx, f, removed=removed)
        if p is not None:
            result[f] = p
    return result


def uploadblobs(repo, pointers):
    """upload given pointers from local blobstore"""
    if not pointers:
        return

    remoteblob = repo.svfs.lfsremoteblobstore
    remoteblob.writebatch(pointers, repo.svfs.lfslocalblobstore)


@eh.wrapfunction(upgrade, '_finishdatamigration')
def upgradefinishdatamigration(orig, ui, srcrepo, dstrepo, requirements):
    orig(ui, srcrepo, dstrepo, requirements)

    # Skip if this hasn't been passed to reposetup()
    if util.safehasattr(srcrepo.svfs, 'lfslocalblobstore') and util.safehasattr(
        dstrepo.svfs, 'lfslocalblobstore'
    ):
        srclfsvfs = srcrepo.svfs.lfslocalblobstore.vfs
        dstlfsvfs = dstrepo.svfs.lfslocalblobstore.vfs

        for dirpath, dirs, files in srclfsvfs.walk():
            for oid in files:
                ui.write(_('copying lfs blob %s\n') % oid)
                lfutil.link(srclfsvfs.join(oid), dstlfsvfs.join(oid))


@eh.wrapfunction(upgrade, 'preservedrequirements')
@eh.wrapfunction(upgrade, 'supporteddestrequirements')
def upgraderequirements(orig, repo):
    reqs = orig(repo)