lfs: remove the verification option when writing to the local store

This partially reverts 417e8e040102 and bb6a80fc969a.  But since there's now a
dedicated download function, there's no functional change.  The last sentence in
the commit message of the latter is wrong- write() didn't need the one time hash
check if verification wasn't requested.  I suspect I missed 'read()' in there
("... but _read()_ also needs to do a one time check..."), because that did fail
without the hash check before linking to the usercache.  The write() method
simply took the same check for consistency.

While here, clarify that the write() method is *only* for storing content
directly from filelog, which has already checked the hash.

If someone can come up with a way to bridge the differences between writing to a
file and sending a urlreq.request across the wire, we can create an upload()
function and cleanup read() in a similar way.  About the only common thread I
see is an open() that verifies the content before returning a file descriptor.

hgext/lfs/blobstore.py

@@ -1,470 +1,470
 # blobstore.py - local and remote (speaking Git-LFS protocol) blob storages
 #
 # Copyright 2017 Facebook, Inc.
 #
 # 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 hashlib
 import json
 import os
 import re
 import socket
 
 from mercurial.i18n import _
 
 from mercurial import (
     error,
     pathutil,
     url as urlmod,
     util,
     vfs as vfsmod,
     worker,
 )
 
 from ..largefiles import lfutil
 
 # 64 bytes for SHA256
 _lfsre = re.compile(r'\A[a-f0-9]{64}\Z')
 
 class lfsvfs(vfsmod.vfs):
     def join(self, path):
         """split the path at first two characters, like: XX/XXXXX..."""
         if not _lfsre.match(path):
             raise error.ProgrammingError('unexpected lfs path: %s' % path)
         return super(lfsvfs, self).join(path[0:2], path[2:])
 
     def walk(self, path=None, onerror=None):
         """Yield (dirpath, [], oids) tuple for blobs under path
 
         Oids only exist in the root of this vfs, so dirpath is always ''.
         """
         root = os.path.normpath(self.base)
         # when dirpath == root, dirpath[prefixlen:] becomes empty
         # because len(dirpath) < prefixlen.
         prefixlen = len(pathutil.normasprefix(root))
         oids = []
 
         for dirpath, dirs, files in os.walk(self.reljoin(self.base, path or ''),
                                             onerror=onerror):
             dirpath = dirpath[prefixlen:]
 
             # Silently skip unexpected files and directories
             if len(dirpath) == 2:
                 oids.extend([dirpath + f for f in files
                              if _lfsre.match(dirpath + f)])
 
         yield ('', [], oids)
 
 class filewithprogress(object):
     """a file-like object that supports __len__ and read.
 
     Useful to provide progress information for how many bytes are read.
     """
 
     def __init__(self, fp, callback):
         self._fp = fp
         self._callback = callback # func(readsize)
         fp.seek(0, os.SEEK_END)
         self._len = fp.tell()
         fp.seek(0)
 
     def __len__(self):
         return self._len
 
     def read(self, size):
         if self._fp is None:
             return b''
         data = self._fp.read(size)
         if data:
             if self._callback:
                 self._callback(len(data))
         else:
             self._fp.close()
             self._fp = None
         return data
 
 class local(object):
     """Local blobstore for large file contents.
 
     This blobstore is used both as a cache and as a staging area for large blobs
     to be uploaded to the remote blobstore.
     """
 
     def __init__(self, repo):
         fullpath = repo.svfs.join('lfs/objects')
         self.vfs = lfsvfs(fullpath)
         usercache = lfutil._usercachedir(repo.ui, 'lfs')
         self.cachevfs = lfsvfs(usercache)
         self.ui = repo.ui
 
     def open(self, oid):
         """Open a read-only file descriptor to the named blob, in either the
         usercache or the local store."""
         # The usercache is the most likely place to hold the file.  Commit will
         # write to both it and the local store, as will anything that downloads
         # the blobs.  However, things like clone without an update won't
         # populate the local store.  For an init + push of a local clone,
         # the usercache is the only place it _could_ be.  If not present, the
         # missing file msg here will indicate the local repo, not the usercache.
         if self.cachevfs.exists(oid):
             return self.cachevfs(oid, 'rb')
 
         return self.vfs(oid, 'rb')
 
     def download(self, oid, src):
         """Read the blob from the remote source in chunks, verify the content,
         and write to this local blobstore."""
         sha256 = hashlib.sha256()
 
         with self.vfs(oid, 'wb', atomictemp=True) as fp:
             for chunk in util.filechunkiter(src, size=1048576):
                 fp.write(chunk)
                 sha256.update(chunk)
 
             realoid = sha256.hexdigest()
             if realoid != oid:
                 raise error.Abort(_('corrupt remote lfs object: %s') % oid)
 
         # XXX: should we verify the content of the cache, and hardlink back to
         # the local store on success, but truncate, write and link on failure?
         if not self.cachevfs.exists(oid):
             self.ui.note(_('lfs: adding %s to the usercache\n') % oid)
             lfutil.link(self.vfs.join(oid), self.cachevfs.join(oid))
 
-    def write(self, oid, data, verify=True):
-        """Write blob to local blobstore."""
-        if verify:
-            _verify(oid, data)
+    def write(self, oid, data):
+        """Write blob to local blobstore.
 
+        This should only be called from the filelog during a commit or similar.
+        As such, there is no need to verify the data.  Imports from a remote
+        store must use ``download()`` instead."""
         with self.vfs(oid, 'wb', atomictemp=True) as fp:
             fp.write(data)
 
         # XXX: should we verify the content of the cache, and hardlink back to
         # the local store on success, but truncate, write and link on failure?
         if not self.cachevfs.exists(oid):
-            if verify or hashlib.sha256(data).hexdigest() == oid:
-                self.ui.note(_('lfs: adding %s to the usercache\n') % oid)
-                lfutil.link(self.vfs.join(oid), self.cachevfs.join(oid))
+            self.ui.note(_('lfs: adding %s to the usercache\n') % oid)
+            lfutil.link(self.vfs.join(oid), self.cachevfs.join(oid))
 
     def read(self, oid, verify=True):
         """Read blob from local blobstore."""
         if not self.vfs.exists(oid):
             blob = self._read(self.cachevfs, oid, verify)
 
             # Even if revlog will verify the content, it needs to be verified
             # now before making the hardlink to avoid propagating corrupt blobs.
             # Don't abort if corruption is detected, because `hg verify` will
             # give more useful info about the corruption- simply don't add the
             # hardlink.
             if verify or hashlib.sha256(blob).hexdigest() == oid:
                 self.ui.note(_('lfs: found %s in the usercache\n') % oid)
                 lfutil.link(self.cachevfs.join(oid), self.vfs.join(oid))
         else:
             self.ui.note(_('lfs: found %s in the local lfs store\n') % oid)
             blob = self._read(self.vfs, oid, verify)
         return blob
 
     def _read(self, vfs, oid, verify):
         """Read blob (after verifying) from the given store"""
         blob = vfs.read(oid)
         if verify:
             _verify(oid, blob)
         return blob
 
     def has(self, oid):
         """Returns True if the local blobstore contains the requested blob,
         False otherwise."""
         return self.cachevfs.exists(oid) or self.vfs.exists(oid)
 
 class _gitlfsremote(object):
 
     def __init__(self, repo, url):
         ui = repo.ui
         self.ui = ui
         baseurl, authinfo = url.authinfo()
         self.baseurl = baseurl.rstrip('/')
         useragent = repo.ui.config('experimental', 'lfs.user-agent')
         if not useragent:
             useragent = 'mercurial/%s git/2.15.1' % util.version()
         self.urlopener = urlmod.opener(ui, authinfo, useragent)
         self.retry = ui.configint('lfs', 'retry')
 
     def writebatch(self, pointers, fromstore):
         """Batch upload from local to remote blobstore."""
         self._batch(pointers, fromstore, 'upload')
 
     def readbatch(self, pointers, tostore):
         """Batch download from remote to local blostore."""
         self._batch(pointers, tostore, 'download')
 
     def _batchrequest(self, pointers, action):
         """Get metadata about objects pointed by pointers for given action
 
         Return decoded JSON object like {'objects': [{'oid': '', 'size': 1}]}
         See https://github.com/git-lfs/git-lfs/blob/master/docs/api/batch.md
         """
         objects = [{'oid': p.oid(), 'size': p.size()} for p in pointers]
         requestdata = json.dumps({
             'objects': objects,
             'operation': action,
         })
         batchreq = util.urlreq.request('%s/objects/batch' % self.baseurl,
                                        data=requestdata)
         batchreq.add_header('Accept', 'application/vnd.git-lfs+json')
         batchreq.add_header('Content-Type', 'application/vnd.git-lfs+json')
         try:
             rawjson = self.urlopener.open(batchreq).read()
         except util.urlerr.httperror as ex:
             raise LfsRemoteError(_('LFS HTTP error: %s (action=%s)')
                                  % (ex, action))
         try:
             response = json.loads(rawjson)
         except ValueError:
             raise LfsRemoteError(_('LFS server returns invalid JSON: %s')
                                  % rawjson)
         return response
 
     def _checkforservererror(self, pointers, responses):
         """Scans errors from objects
 
         Returns LfsRemoteError if any objects has an error"""
         for response in responses:
             error = response.get('error')
             if error:
                 ptrmap = {p.oid(): p for p in pointers}
                 p = ptrmap.get(response['oid'], None)
                 if error['code'] == 404 and p:
                     filename = getattr(p, 'filename', 'unknown')
                     raise LfsRemoteError(
                         _(('LFS server error. Remote object '
                           'for file %s not found: %r')) % (filename, response))
                 raise LfsRemoteError(_('LFS server error: %r') % response)
 
     def _extractobjects(self, response, pointers, action):
         """extract objects from response of the batch API
 
         response: parsed JSON object returned by batch API
         return response['objects'] filtered by action
         raise if any object has an error
         """
         # Scan errors from objects - fail early
         objects = response.get('objects', [])
         self._checkforservererror(pointers, objects)
 
         # Filter objects with given action. Practically, this skips uploading
         # objects which exist in the server.
         filteredobjects = [o for o in objects if action in o.get('actions', [])]
         # But for downloading, we want all objects. Therefore missing objects
         # should be considered an error.
         if action == 'download':
             if len(filteredobjects) < len(objects):
                 missing = [o.get('oid', '?')
                            for o in objects
                            if action not in o.get('actions', [])]
                 raise LfsRemoteError(
                     _('LFS server claims required objects do not exist:\n%s')
                     % '\n'.join(missing))
 
         return filteredobjects
 
     def _basictransfer(self, obj, action, localstore):
         """Download or upload a single object using basic transfer protocol
 
         obj: dict, an object description returned by batch API
         action: string, one of ['upload', 'download']
         localstore: blobstore.local
 
         See https://github.com/git-lfs/git-lfs/blob/master/docs/api/\
         basic-transfers.md
         """
         oid = str(obj['oid'])
 
         href = str(obj['actions'][action].get('href'))
         headers = obj['actions'][action].get('header', {}).items()
 
         request = util.urlreq.request(href)
         if action == 'upload':
             # If uploading blobs, read data from local blobstore.
             with localstore.open(oid) as fp:
                 _verifyfile(oid, fp)
             request.data = filewithprogress(localstore.open(oid), None)
             request.get_method = lambda: 'PUT'
 
         for k, v in headers:
             request.add_header(k, v)
 
         response = b''
         try:
             req = self.urlopener.open(request)
             if action == 'download':
                 # If downloading blobs, store downloaded data to local blobstore
                 localstore.download(oid, req)
             else:
                 while True:
                     data = req.read(1048576)
                     if not data:
                         break
                     response += data
                 if response:
                     self.ui.debug('lfs %s response: %s' % (action, response))
         except util.urlerr.httperror as ex:
             raise LfsRemoteError(_('HTTP error: %s (oid=%s, action=%s)')
                                  % (ex, oid, action))
 
     def _batch(self, pointers, localstore, action):
         if action not in ['upload', 'download']:
             raise error.ProgrammingError('invalid Git-LFS action: %s' % action)
 
         response = self._batchrequest(pointers, action)
         objects = self._extractobjects(response, pointers, action)
         total = sum(x.get('size', 0) for x in objects)
         sizes = {}
         for obj in objects:
             sizes[obj.get('oid')] = obj.get('size', 0)
         topic = {'upload': _('lfs uploading'),
                  'download': _('lfs downloading')}[action]
         if len(objects) > 1:
             self.ui.note(_('lfs: need to transfer %d objects (%s)\n')
                          % (len(objects), util.bytecount(total)))
         self.ui.progress(topic, 0, total=total)
         def transfer(chunk):
             for obj in chunk:
                 objsize = obj.get('size', 0)
                 if self.ui.verbose:
                     if action == 'download':
                         msg = _('lfs: downloading %s (%s)\n')
                     elif action == 'upload':
                         msg = _('lfs: uploading %s (%s)\n')
                     self.ui.note(msg % (obj.get('oid'),
                                  util.bytecount(objsize)))
                 retry = self.retry
                 while True:
                     try:
                         self._basictransfer(obj, action, localstore)
                         yield 1, obj.get('oid')
                         break
                     except socket.error as ex:
                         if retry > 0:
                             self.ui.note(
                                 _('lfs: failed: %r (remaining retry %d)\n')
                                 % (ex, retry))
                             retry -= 1
                             continue
                         raise
 
         oids = worker.worker(self.ui, 0.1, transfer, (),
                              sorted(objects, key=lambda o: o.get('oid')))
         processed = 0
         for _one, oid in oids:
             processed += sizes[oid]
             self.ui.progress(topic, processed, total=total)
             self.ui.note(_('lfs: processed: %s\n') % oid)
         self.ui.progress(topic, pos=None, total=total)
 
     def __del__(self):
         # copied from mercurial/httppeer.py
         urlopener = getattr(self, 'urlopener', None)
         if urlopener:
             for h in urlopener.handlers:
                 h.close()
                 getattr(h, "close_all", lambda : None)()
 
 class _dummyremote(object):
     """Dummy store storing blobs to temp directory."""
 
     def __init__(self, repo, url):
         fullpath = repo.vfs.join('lfs', url.path)
         self.vfs = lfsvfs(fullpath)
 
     def writebatch(self, pointers, fromstore):
         for p in pointers:
             content = fromstore.read(p.oid(), verify=True)
             with self.vfs(p.oid(), 'wb', atomictemp=True) as fp:
                 fp.write(content)
 
     def readbatch(self, pointers, tostore):
         for p in pointers:
             with self.vfs(p.oid(), 'rb') as fp:
                 tostore.download(p.oid(), fp)
 
 class _nullremote(object):
     """Null store storing blobs to /dev/null."""
 
     def __init__(self, repo, url):
         pass
 
     def writebatch(self, pointers, fromstore):
         pass
 
     def readbatch(self, pointers, tostore):
         pass
 
 class _promptremote(object):
     """Prompt user to set lfs.url when accessed."""
 
     def __init__(self, repo, url):
         pass
 
     def writebatch(self, pointers, fromstore, ui=None):
         self._prompt()
 
     def readbatch(self, pointers, tostore, ui=None):
         self._prompt()
 
     def _prompt(self):
         raise error.Abort(_('lfs.url needs to be configured'))
 
 _storemap = {
     'https': _gitlfsremote,
     'http': _gitlfsremote,
     'file': _dummyremote,
     'null': _nullremote,
     None: _promptremote,
 }
 
 def _verify(oid, content):
     realoid = hashlib.sha256(content).hexdigest()
     if realoid != oid:
         raise error.Abort(_('detected corrupt lfs object: %s') % oid,
                           hint=_('run hg verify'))
 
 def _verifyfile(oid, fp):
     sha256 = hashlib.sha256()
     while True:
         data = fp.read(1024 * 1024)
         if not data:
             break
         sha256.update(data)
     realoid = sha256.hexdigest()
     if realoid != oid:
         raise error.Abort(_('detected corrupt lfs object: %s') % oid,
                           hint=_('run hg verify'))
 
 def remote(repo):
     """remotestore factory. return a store in _storemap depending on config"""
     defaulturl = ''
 
     # convert deprecated configs to the new url. TODO: remove this if other
     # places are migrated to the new url config.
     # deprecated config: lfs.remotestore
     deprecatedstore = repo.ui.config('lfs', 'remotestore')
     if deprecatedstore == 'dummy':
         # deprecated config: lfs.remotepath
         defaulturl = 'file://' + repo.ui.config('lfs', 'remotepath')
     elif deprecatedstore == 'git-lfs':
         # deprecated config: lfs.remoteurl
         defaulturl = repo.ui.config('lfs', 'remoteurl')
     elif deprecatedstore == 'null':
         defaulturl = 'null://'
 
     url = util.url(repo.ui.config('lfs', 'url', defaulturl))
     scheme = url.scheme
     if scheme not in _storemap:
         raise error.Abort(_('lfs: unknown url scheme: %s') % scheme)
     return _storemap[scheme](repo, url)
 
 class LfsRemoteError(error.RevlogError):
     pass

hgext/lfs/wrapper.py

@@ -1,345 +1,345
 # wrapper.py - methods wrapping core mercurial logic
 #
 # Copyright 2017 Facebook, Inc.
 #
 # 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 hashlib
 
 from mercurial.i18n import _
 from mercurial.node import bin, nullid, short
 
 from mercurial import (
     error,
     filelog,
     revlog,
     util,
 )
 
 from ..largefiles import lfutil
 
 from . import (
     blobstore,
     pointer,
 )
 
 def supportedoutgoingversions(orig, repo):
     versions = orig(repo)
     if 'lfs' in repo.requirements:
         versions.discard('01')
         versions.discard('02')
     versions.add('03')
     return versions
 
 def allsupportedversions(orig, ui):
     versions = orig(ui)
     versions.add('03')
     return versions
 
 def _capabilities(orig, repo, proto):
     '''Wrap server command to announce lfs server capability'''
     caps = orig(repo, proto)
     # XXX: change to 'lfs=serve' when separate git server isn't required?
     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.
     Returns a 2-typle (text, validatehash) where validatehash is True as the
     contents of the blobstore should be checked using checkhash.
     """
     p = pointer.deserialize(text)
     oid = p.oid()
     store = self.opener.lfslocalblobstore
     if not store.has(oid):
         p.filename = getattr(self, 'indexfile', None)
         self.opener.lfsremoteblobstore.readbatch([p], store)
 
     # The caller will validate the content
     text = store.read(oid, verify=False)
 
     # 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 = filelog.packmeta(hgmeta, text)
 
     return (text, True)
 
 def writetostore(self, text):
     # hg filelog metadata (includes rename, etc)
     hgmeta, offset = filelog.parsemeta(text)
     if offset and offset > 0:
         # lfs blob does not contain hg filelog metadata
         text = text[offset:]
 
     # git-lfs only supports sha256
     oid = hashlib.sha256(text).hexdigest()
-    self.opener.lfslocalblobstore.write(oid, text, verify=False)
+    self.opener.lfslocalblobstore.write(oid, text)
 
     # replace contents with metadata
     longoid = 'sha256:%s' % oid
     metadata = pointer.gitlfspointer(oid=longoid, size=str(len(text)))
 
     # by default, we expect the content to be binary. however, LFS could also
     # be used for non-binary content. add a special entry for non-binary data.
     # this will be used by filectx.isbinary().
     if not util.binary(text):
         # not hg filelog metadata (affecting commit hash), no "x-hg-" prefix
         metadata['x-is-binary'] = '0'
 
     # translate hg filelog metadata to lfs metadata with "x-hg-" prefix
     if hgmeta is not None:
         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
             return False
         rev = rlog.rev(node)
     else:
         node = rlog.node(rev)
     if node == nullid:
         return False
     flags = rlog.flags(rev)
     return bool(flags & revlog.REVIDX_EXTSTORED)
 
 def filelogaddrevision(orig, self, text, transaction, link, p1, p2,
                        cachedelta=None, node=None,
                        flags=revlog.REVIDX_DEFAULT_FLAGS, **kwds):
     threshold = self.opener.options['lfsthreshold']
     textlen = len(text)
     # exclude hg rename meta from file size
     meta, offset = filelog.parsemeta(text)
     if offset:
         textlen -= offset
 
     if threshold and textlen > threshold:
         flags |= revlog.REVIDX_EXTSTORED
 
     return orig(self, text, transaction, link, p1, p2, cachedelta=cachedelta,
                 node=node, flags=flags, **kwds)
 
 def filelogrenamed(orig, self, node):
     if _islfs(self, node):
         rawtext = self.revision(node, raw=True)
         if not rawtext:
             return False
         metadata = pointer.deserialize(rawtext)
         if 'x-hg-copy' in metadata and 'x-hg-copyrev' in metadata:
             return metadata['x-hg-copy'], bin(metadata['x-hg-copyrev'])
         else:
             return False
     return orig(self, node)
 
 def filelogsize(orig, self, rev):
     if _islfs(self, rev=rev):
         # fast path: use lfs metadata to answer size
         rawtext = self.revision(rev, raw=True)
         metadata = pointer.deserialize(rawtext)
         return int(metadata['size'])
     return orig(self, rev)
 
 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
     if self.islfs() and getattr(fctx, 'islfs', lambda: False)():
         # fast path: check LFS oid
         p1 = pointer.deserialize(self.rawdata())
         p2 = pointer.deserialize(fctx.rawdata())
         return p1.oid() != p2.oid()
     return orig(self, fctx)
 
 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())
 
 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
                     # membership before assuming it is in the context.
                     if any(f in ctx and ctx[f].islfs() for f, n in files):
                         self.repo.requirements.add('lfs')
                         self.repo._writerequirements()
 
                         # Permanently enable lfs locally
                         with self.repo.vfs('hgrc', 'a', text=True) as fp:
                             fp.write('\n[extensions]\nlfs=\n')
 
                 return node
 
         sink.__class__ = lfssink
 
     return sink
 
 def vfsinit(orig, self, othervfs):
     orig(self, othervfs)
     # copy lfs related options
     for k, v in othervfs.options.items():
         if k.startswith('lfs'):
             self.options[k] = v
     # also copy lfs blobstores. note: this can run before reposetup, so lfs
     # 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 hgclone(orig, ui, opts, *args, **kwargs):
     result = orig(ui, opts, *args, **kwargs)
 
     if result is not None:
         sourcerepo, destrepo = result
         repo = destrepo.local()
 
         # When cloning to a remote repo (like through SSH), no repo is available
         # from the peer.  Therefore the hgrc can't be updated.
         if not repo:
             return result
 
         # If lfs is required for this repo, permanently enable it locally
         if 'lfs' in repo.requirements:
             with repo.vfs('hgrc', 'a', text=True) as fp:
                 fp.write('\n[extensions]\nlfs=\n')
 
     return result
 
 def hgpostshare(orig, sourcerepo, destrepo, bookmarks=True, defaultpath=None):
     orig(sourcerepo, destrepo, bookmarks, defaultpath)
 
     # If lfs is required for this repo, permanently enable it locally
     if 'lfs' in destrepo.requirements:
         with destrepo.vfs('hgrc', 'a', text=True) as fp:
             fp.write('\n[extensions]\nlfs=\n')
 
 def _canskipupload(repo):
     # 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):
     # 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)
 
 def push(orig, repo, remote, *args, **kwargs):
     """bail on push if the extension isn't enabled on remote when needed"""
     if 'lfs' in repo.requirements:
         # If the remote peer is for a local repo, the requirement tests in the
         # base class method enforce lfs support.  Otherwise, some revisions in
         # 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'))
     return orig(repo, remote, *args, **kwargs)
 
 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 = {}
     for r in revs:
         ctx = repo[r]
         for p in pointersfromctx(ctx).values():
             pointers[p.oid()] = p
     return sorted(pointers.values())
 
 def pointersfromctx(ctx):
     """return a dict {path: pointer} for given single changectx"""
     result = {}
     for f in ctx.files():
         if f not in ctx:
             continue
         fctx = ctx[f]
         if not _islfs(fctx.filelog(), fctx.filenode()):
             continue
         try:
             result[f] = pointer.deserialize(fctx.rawdata())
         except pointer.InvalidPointer as ex:
             raise error.Abort(_('lfs: corrupted pointer (%s@%s): %s\n')
                               % (f, short(ctx.node()), ex))
     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)
 
 def upgradefinishdatamigration(orig, ui, srcrepo, dstrepo, requirements):
     orig(ui, srcrepo, dstrepo, requirements)
 
     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))
 
 def upgraderequirements(orig, repo):
     reqs = orig(repo)
     if 'lfs' in repo.requirements:
         reqs.add('lfs')
     return reqs