wrapfunction: use sysstr instead of bytes as argument in "lfs"

This is as valid and simpler, it will help us to eventually get ride of
`safehasattr`.

hgext/lfs/__init__.py

@@ -1,446 +1,446
 # lfs - hash-preserving large file support using Git-LFS protocol
 #
 # 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.
 
 """lfs - large file support (EXPERIMENTAL)
 
 This extension allows large files to be tracked outside of the normal
 repository storage and stored on a centralized server, similar to the
 ``largefiles`` extension.  The ``git-lfs`` protocol is used when
 communicating with the server, so existing git infrastructure can be
 harnessed.  Even though the files are stored outside of the repository,
 they are still integrity checked in the same manner as normal files.
 
 The files stored outside of the repository are downloaded on demand,
 which reduces the time to clone, and possibly the local disk usage.
 This changes fundamental workflows in a DVCS, so careful thought
 should be given before deploying it.  :hg:`convert` can be used to
 convert LFS repositories to normal repositories that no longer
 require this extension, and do so without changing the commit hashes.
 This allows the extension to be disabled if the centralized workflow
 becomes burdensome.  However, the pre and post convert clones will
 not be able to communicate with each other unless the extension is
 enabled on both.
 
 To start a new repository, or to add LFS files to an existing one, just
 create an ``.hglfs`` file as described below in the root directory of
 the repository.  Typically, this file should be put under version
 control, so that the settings will propagate to other repositories with
 push and pull.  During any commit, Mercurial will consult this file to
 determine if an added or modified file should be stored externally.  The
 type of storage depends on the characteristics of the file at each
 commit.  A file that is near a size threshold may switch back and forth
 between LFS and normal storage, as needed.
 
 Alternately, both normal repositories and largefile controlled
 repositories can be converted to LFS by using :hg:`convert` and the
 ``lfs.track`` config option described below.  The ``.hglfs`` file
 should then be created and added, to control subsequent LFS selection.
 The hashes are also unchanged in this case.  The LFS and non-LFS
 repositories can be distinguished because the LFS repository will
 abort any command if this extension is disabled.
 
 Committed LFS files are held locally, until the repository is pushed.
 Prior to pushing the normal repository data, the LFS files that are
 tracked by the outgoing commits are automatically uploaded to the
 configured central server.  No LFS files are transferred on
 :hg:`pull` or :hg:`clone`.  Instead, the files are downloaded on
 demand as they need to be read, if a cached copy cannot be found
 locally.  Both committing and downloading an LFS file will link the
 file to a usercache, to speed up future access.  See the `usercache`
 config setting described below.
 
 The extension reads its configuration from a versioned ``.hglfs``
 configuration file found in the root of the working directory. The
 ``.hglfs`` file uses the same syntax as all other Mercurial
 configuration files. It uses a single section, ``[track]``.
 
 The ``[track]`` section specifies which files are stored as LFS (or
 not). Each line is keyed by a file pattern, with a predicate value.
 The first file pattern match is used, so put more specific patterns
 first.  The available predicates are ``all()``, ``none()``, and
 ``size()``. See "hg help filesets.size" for the latter.
 
 Example versioned ``.hglfs`` file::
 
   [track]
   # No Makefile or python file, anywhere, will be LFS
   **Makefile = none()
   **.py = none()
 
   **.zip = all()
   **.exe = size(">1MB")
 
   # Catchall for everything not matched above
   ** = size(">10MB")
 
 Configs::
 
     [lfs]
     # Remote endpoint. Multiple protocols are supported:
     # - http(s)://user:[e-mail]/path
     #   git-lfs endpoint
     # - file:///tmp/path
     #   local filesystem, usually for testing
     # if unset, lfs will assume the remote repository also handles blob storage
     # for http(s) URLs.  Otherwise, lfs will prompt to set this when it must
     # use this value.
     # (default: unset)
     url = https://example.com/repo.git/info/lfs
 
     # Which files to track in LFS.  Path tests are "**.extname" for file
     # extensions, and "path:under/some/directory" for path prefix.  Both
     # are relative to the repository root.
     # File size can be tested with the "size()" fileset, and tests can be
     # joined with fileset operators.  (See "hg help filesets.operators".)
     #
     # Some examples:
     # - all()                       # everything
     # - none()                      # nothing
     # - size(">20MB")               # larger than 20MB
     # - !**.txt                     # anything not a *.txt file
     # - **.zip | **.tar.gz | **.7z  # some types of compressed files
     # - path:bin                    # files under "bin" in the project root
     # - (**.php & size(">2MB")) | (**.js & size(">5MB")) | **.tar.gz
     #     | (path:bin & !path:/bin/README) | size(">1GB")
     # (default: none())
     #
     # This is ignored if there is a tracked '.hglfs' file, and this setting
     # will eventually be deprecated and removed.
     track = size(">10M")
 
     # how many times to retry before giving up on transferring an object
     retry = 5
 
     # the local directory to store lfs files for sharing across local clones.
     # If not set, the cache is located in an OS specific cache location.
     usercache = /path/to/global/cache
 """
 
 
 import sys
 
 from mercurial.i18n import _
 from mercurial.node import bin
 
 from mercurial import (
     bundlecaches,
     config,
     context,
     error,
     extensions,
     exthelper,
     filelog,
     filesetlang,
     localrepo,
     logcmdutil,
     minifileset,
     pycompat,
     revlog,
     scmutil,
     templateutil,
     util,
 )
 
 from mercurial.interfaces import repository
 
 from . import (
     blobstore,
     wireprotolfsserver,
     wrapper,
 )
 
 # Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
 # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
 # be specifying the version(s) of Mercurial they are tested with, or
 # leave the attribute unspecified.
 testedwith = b'ships-with-hg-core'
 
 eh = exthelper.exthelper()
 eh.merge(wrapper.eh)
 eh.merge(wireprotolfsserver.eh)
 
 cmdtable = eh.cmdtable
 configtable = eh.configtable
 extsetup = eh.finalextsetup
 uisetup = eh.finaluisetup
 filesetpredicate = eh.filesetpredicate
 reposetup = eh.finalreposetup
 templatekeyword = eh.templatekeyword
 
 eh.configitem(
     b'experimental',
     b'lfs.serve',
     default=True,
 )
 eh.configitem(
     b'experimental',
     b'lfs.user-agent',
     default=None,
 )
 eh.configitem(
     b'experimental',
     b'lfs.disableusercache',
     default=False,
 )
 eh.configitem(
     b'experimental',
     b'lfs.worker-enable',
     default=True,
 )
 
 eh.configitem(
     b'lfs',
     b'url',
     default=None,
 )
 eh.configitem(
     b'lfs',
     b'usercache',
     default=None,
 )
 # Deprecated
 eh.configitem(
     b'lfs',
     b'threshold',
     default=None,
 )
 eh.configitem(
     b'lfs',
     b'track',
     default=b'none()',
 )
 eh.configitem(
     b'lfs',
     b'retry',
     default=5,
 )
 
 lfsprocessor = (
     wrapper.readfromstore,
     wrapper.writetostore,
     wrapper.bypasscheckhash,
 )
 
 
 def featuresetup(ui, supported):
     # don't die on seeing a repo with the lfs requirement
     supported |= {b'lfs'}
 
 
 @eh.uisetup
 def _uisetup(ui):
     localrepo.featuresetupfuncs.add(featuresetup)
 
 
 @eh.reposetup
 def _reposetup(ui, repo):
     # Nothing to do with a remote repo
     if not repo.local():
         return
 
     repo.svfs.lfslocalblobstore = blobstore.local(repo)
     repo.svfs.lfsremoteblobstore = blobstore.remote(repo)
 
     class lfsrepo(repo.__class__):
         @localrepo.unfilteredmethod
         def commitctx(self, ctx, error=False, origctx=None):
             repo.svfs.options[b'lfstrack'] = _trackedmatcher(self)
             return super(lfsrepo, self).commitctx(ctx, error, origctx=origctx)
 
     repo.__class__ = lfsrepo
 
     if b'lfs' not in repo.requirements:
 
         def checkrequireslfs(ui, repo, **kwargs):
             with repo.lock():
                 if b'lfs' in repo.requirements:
                     return 0
 
                 last = kwargs.get('node_last')
                 if last:
                     s = repo.set(b'%n:%n', bin(kwargs['node']), bin(last))
                 else:
                     s = repo.set(b'%n', bin(kwargs['node']))
                 match = repo._storenarrowmatch
                 for ctx in s:
                     # TODO: is there a way to just walk the files in the commit?
                     if any(
                         ctx[f].islfs()
                         for f in ctx.files()
                         if f in ctx and match(f)
                     ):
                         repo.requirements.add(b'lfs')
                         repo.features.add(repository.REPO_FEATURE_LFS)
                         scmutil.writereporequirements(repo)
                         repo.prepushoutgoinghooks.add(b'lfs', wrapper.prepush)
                         break
 
         ui.setconfig(b'hooks', b'commit.lfs', checkrequireslfs, b'lfs')
         ui.setconfig(
             b'hooks', b'pretxnchangegroup.lfs', checkrequireslfs, b'lfs'
         )
     else:
         repo.prepushoutgoinghooks.add(b'lfs', wrapper.prepush)
 
 
 def _trackedmatcher(repo):
     """Return a function (path, size) -> bool indicating whether or not to
     track a given file with lfs."""
     if not repo.wvfs.exists(b'.hglfs'):
         # No '.hglfs' in wdir.  Fallback to config for now.
         trackspec = repo.ui.config(b'lfs', b'track')
 
         # deprecated config: lfs.threshold
         threshold = repo.ui.configbytes(b'lfs', b'threshold')
         if threshold:
             filesetlang.parse(trackspec)  # make sure syntax errors are confined
             trackspec = b"(%s) | size('>%d')" % (trackspec, threshold)
 
         return minifileset.compile(trackspec)
 
     data = repo.wvfs.tryread(b'.hglfs')
     if not data:
         return lambda p, s: False
 
     # Parse errors here will abort with a message that points to the .hglfs file
     # and line number.
     cfg = config.config()
     cfg.parse(b'.hglfs', data)
 
     try:
         rules = [
             (minifileset.compile(pattern), minifileset.compile(rule))
             for pattern, rule in cfg.items(b'track')
         ]
     except error.ParseError as e:
         # The original exception gives no indicator that the error is in the
         # .hglfs file, so add that.
 
         # TODO: See if the line number of the file can be made available.
         raise error.Abort(_(b'parse error in .hglfs: %s') % e)
 
     def _match(path, size):
         for pat, rule in rules:
             if pat(path, size):
                 return rule(path, size)
 
         return False
 
     return _match
 
 
 # Called by remotefilelog
 def wrapfilelog(filelog):
     wrapfunction = extensions.wrapfunction
 
     wrapfunction(filelog, 'addrevision', wrapper.filelogaddrevision)
     wrapfunction(filelog, 'renamed', wrapper.filelogrenamed)
     wrapfunction(filelog, 'size', wrapper.filelogsize)
 
 
[e-mail](localrepo, b'resolverevlogstorevfsoptions')
[e-mail](localrepo, 'resolverevlogstorevfsoptions')
 def _resolverevlogstorevfsoptions(orig, ui, requirements, features):
     opts = orig(ui, requirements, features)
     for name, module in extensions.extensions(ui):
         if module is sys.modules[__name__]:
             if revlog.REVIDX_EXTSTORED in opts[b'flagprocessors']:
                 msg = (
                     _(b"cannot register multiple processors on flag '%#x'.")
                     % revlog.REVIDX_EXTSTORED
                 )
                 raise error.Abort(msg)
 
             opts[b'flagprocessors'][revlog.REVIDX_EXTSTORED] = lfsprocessor
             break
 
     return opts
 
 
 @eh.extsetup
 def _extsetup(ui):
     wrapfilelog(filelog.filelog)
 
     context.basefilectx.islfs = wrapper.filectxislfs
 
     scmutil.fileprefetchhooks.add(b'lfs', wrapper._prefetchfiles)
 
     # Make bundle choose changegroup3 instead of changegroup2. This affects
     # "hg bundle" command. Note: it does not cover all bundle formats like
     # "packed1". Using "packed1" with lfs will likely cause trouble.
     bundlecaches._bundlespeccontentopts[b"v2"][b"cg.version"] = b"03"
 
 
 @eh.filesetpredicate(b'lfs()')
 def lfsfileset(mctx, x):
     """File that uses LFS storage."""
     # i18n: "lfs" is a keyword
     filesetlang.getargs(x, 0, 0, _(b"lfs takes no arguments"))
     ctx = mctx.ctx
 
     def lfsfilep(f):
         return wrapper.pointerfromctx(ctx, f, removed=True) is not None
 
     return mctx.predicate(lfsfilep, predrepr=b'<lfs>')
 
 
 @eh.templatekeyword(b'lfs_files', requires={b'ctx'})
 def lfsfiles(context, mapping):
     """List of strings. All files modified, added, or removed by this
     changeset."""
     ctx = context.resource(mapping, b'ctx')
 
     pointers = wrapper.pointersfromctx(ctx, removed=True)  # {path: pointer}
     files = sorted(pointers.keys())
 
     def pointer(v):
         # In the file spec, version is first and the other keys are sorted.
         sortkeyfunc = lambda x: (x[0] != b'version', x)
         items = sorted(pointers[v].items(), key=sortkeyfunc)
         return util.sortdict(items)
 
     makemap = lambda v: {
         b'file': v,
         b'lfsoid': pointers[v].oid() if pointers[v] else None,
         b'lfspointer': templateutil.hybriddict(pointer(v)),
     }
 
     # TODO: make the separator ', '?
     f = templateutil._showcompatlist(context, mapping, b'lfs_file', files)
     return templateutil.hybrid(f, files, makemap, pycompat.identity)
 
 
 @eh.command(
     b'debuglfsupload',
     [(b'r', b'rev', [], _(b'upload large files introduced by REV'))],
 )
 def debuglfsupload(ui, repo, **opts):
     """upload lfs blobs added by the working copy parent or given revisions"""
     revs = opts.get('rev', [])
     pointers = wrapper.extractpointers(repo, logcmdutil.revrange(repo, revs))
     wrapper.uploadblobs(repo, pointers)
 
 
 @eh.wrapcommand(
     b'verify',
     opts=[(b'', b'no-lfs', None, _(b'skip missing lfs blob content'))],
 )
 def verify(orig, ui, repo, **opts):
     skipflags = repo.ui.configint(b'verify', b'skipflags')
     no_lfs = opts.pop('no_lfs')
 
     if skipflags:
         # --lfs overrides the config bit, if set.
         if no_lfs is False:
             skipflags &= ~repository.REVISION_FLAG_EXTSTORED
     else:
         skipflags = 0
 
     if no_lfs is True:
         skipflags |= repository.REVISION_FLAG_EXTSTORED
 
     with ui.configoverride({(b'verify', b'skipflags'): skipflags}):
         return orig(ui, repo, **opts)

hgext/lfs/wireprotolfsserver.py

@@ -1,369 +1,369
 # wireprotolfsserver.py - lfs protocol server side implementation
 #
 # Copyright 2018 Matt Harbison <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 
 import datetime
 import errno
 import json
 import traceback
 
 from mercurial.hgweb import common as hgwebcommon
 
 from mercurial import (
     exthelper,
     pycompat,
     util,
     wireprotoserver,
 )
 
 from . import blobstore
 
 HTTP_OK = hgwebcommon.HTTP_OK
 HTTP_CREATED = hgwebcommon.HTTP_CREATED
 HTTP_BAD_REQUEST = hgwebcommon.HTTP_BAD_REQUEST
 HTTP_NOT_FOUND = hgwebcommon.HTTP_NOT_FOUND
 HTTP_METHOD_NOT_ALLOWED = hgwebcommon.HTTP_METHOD_NOT_ALLOWED
 HTTP_NOT_ACCEPTABLE = hgwebcommon.HTTP_NOT_ACCEPTABLE
 HTTP_UNSUPPORTED_MEDIA_TYPE = hgwebcommon.HTTP_UNSUPPORTED_MEDIA_TYPE
 
 eh = exthelper.exthelper()
 
 
[e-mail](wireprotoserver, b'handlewsgirequest')
[e-mail](wireprotoserver, 'handlewsgirequest')
 def handlewsgirequest(orig, rctx, req, res, checkperm):
     """Wrap wireprotoserver.handlewsgirequest() to possibly process an LFS
     request if it is left unprocessed by the wrapped method.
     """
     if orig(rctx, req, res, checkperm):
         return True
 
     if not rctx.repo.ui.configbool(b'experimental', b'lfs.serve'):
         return False
 
     if not util.safehasattr(rctx.repo.svfs, 'lfslocalblobstore'):
         return False
 
     if not req.dispatchpath:
         return False
 
     try:
         if req.dispatchpath == b'.git/info/lfs/objects/batch':
             checkperm(rctx, req, b'pull')
             return _processbatchrequest(rctx.repo, req, res)
         # TODO: reserve and use a path in the proposed http wireprotocol /api/
         #       namespace?
         elif req.dispatchpath.startswith(b'.hg/lfs/objects'):
             return _processbasictransfer(
                 rctx.repo, req, res, lambda perm: checkperm(rctx, req, perm)
             )
         return False
     except hgwebcommon.ErrorResponse as e:
         # XXX: copied from the handler surrounding wireprotoserver._callhttp()
         #      in the wrapped function.  Should this be moved back to hgweb to
         #      be a common handler?
         for k, v in e.headers:
             res.headers[k] = v
         res.status = hgwebcommon.statusmessage(e.code, pycompat.bytestr(e))
         res.setbodybytes(b'0\n%s\n' % pycompat.bytestr(e))
         return True
 
 
 def _sethttperror(res, code, message=None):
     res.status = hgwebcommon.statusmessage(code, message=message)
     res.headers[b'Content-Type'] = b'text/plain; charset=utf-8'
     res.setbodybytes(b'')
 
 
 def _logexception(req):
     """Write information about the current exception to wsgi.errors."""
     tb = pycompat.sysbytes(traceback.format_exc())
     errorlog = req.rawenv[b'wsgi.errors']
 
     uri = b''
     if req.apppath:
         uri += req.apppath
     uri += b'/' + req.dispatchpath
 
     errorlog.write(
         b"Exception happened while processing request '%s':\n%s" % (uri, tb)
     )
 
 
 def _processbatchrequest(repo, req, res):
     """Handle a request for the Batch API, which is the gateway to granting file
     access.
 
     https://github.com/git-lfs/git-lfs/blob/master/docs/api/batch.md
     """
 
     # Mercurial client request:
     #
     #   HOST: localhost:$HGPORT
     #   ACCEPT: application/vnd.git-lfs+json
     #   ACCEPT-ENCODING: identity
     #   USER-AGENT: git-lfs/2.3.4 (Mercurial 4.5.2+1114-f48b9754f04c+20180316)
     #   Content-Length: 125
     #   Content-Type: application/vnd.git-lfs+json
     #
     #   {
     #     "objects": [
     #       {
     #         "oid": "31cf...8e5b"
     #         "size": 12
     #       }
     #     ]
     #     "operation": "upload"
     #  }
 
     if req.method != b'POST':
         _sethttperror(res, HTTP_METHOD_NOT_ALLOWED)
         return True
 
     if req.headers[b'Content-Type'] != b'application/vnd.git-lfs+json':
         _sethttperror(res, HTTP_UNSUPPORTED_MEDIA_TYPE)
         return True
 
     if req.headers[b'Accept'] != b'application/vnd.git-lfs+json':
         _sethttperror(res, HTTP_NOT_ACCEPTABLE)
         return True
 
     # XXX: specify an encoding?
     lfsreq = pycompat.json_loads(req.bodyfh.read())
 
     # If no transfer handlers are explicitly requested, 'basic' is assumed.
     if 'basic' not in lfsreq.get('transfers', ['basic']):
         _sethttperror(
             res,
             HTTP_BAD_REQUEST,
             b'Only the basic LFS transfer handler is supported',
         )
         return True
 
     operation = lfsreq.get('operation')
     operation = pycompat.bytestr(operation)
 
     if operation not in (b'upload', b'download'):
         _sethttperror(
             res,
             HTTP_BAD_REQUEST,
             b'Unsupported LFS transfer operation: %s' % operation,
         )
         return True
 
     localstore = repo.svfs.lfslocalblobstore
 
     objects = [
         p
         for p in _batchresponseobjects(
             req, lfsreq.get('objects', []), operation, localstore
         )
     ]
 
     rsp = {
         'transfer': 'basic',
         'objects': objects,
     }
 
     res.status = hgwebcommon.statusmessage(HTTP_OK)
     res.headers[b'Content-Type'] = b'application/vnd.git-lfs+json'
     res.setbodybytes(pycompat.bytestr(json.dumps(rsp)))
 
     return True
 
 
 def _batchresponseobjects(req, objects, action, store):
     """Yield one dictionary of attributes for the Batch API response for each
     object in the list.
 
     req: The parsedrequest for the Batch API request
     objects: The list of objects in the Batch API object request list
     action: 'upload' or 'download'
     store: The local blob store for servicing requests"""
 
     # Successful lfs-test-server response to solict an upload:
     # {
     #    u'objects': [{
     #       u'size': 12,
     #       u'oid': u'31cf...8e5b',
     #       u'actions': {
     #           u'upload': {
     #               u'href': u'http://localhost:$HGPORT/objects/31cf...8e5b',
     #               u'expires_at': u'0001-01-01T00:00:00Z',
     #               u'header': {
     #                   u'Accept': u'application/vnd.git-lfs'
     #               }
     #           }
     #       }
     #    }]
     # }
 
     # TODO: Sort out the expires_at/expires_in/authenticated keys.
 
     for obj in objects:
         # Convert unicode to ASCII to create a filesystem path
         soid = obj.get('oid')
         oid = soid.encode('ascii')
         rsp = {
             'oid': soid,
             'size': obj.get('size'),  # XXX: should this check the local size?
             # 'authenticated': True,
         }
 
         exists = True
         verifies = False
 
         # Verify an existing file on the upload request, so that the client is
         # solicited to re-upload if it corrupt locally.  Download requests are
         # also verified, so the error can be flagged in the Batch API response.
         # (Maybe we can use this to short circuit the download for `hg verify`,
         # IFF the client can assert that the remote end is an hg server.)
         # Otherwise, it's potentially overkill on download, since it is also
         # verified as the file is streamed to the caller.
         try:
             verifies = store.verify(oid)
             if verifies and action == b'upload':
                 # The client will skip this upload, but make sure it remains
                 # available locally.
                 store.linkfromusercache(oid)
         except IOError as inst:
             if inst.errno != errno.ENOENT:
                 _logexception(req)
 
                 rsp['error'] = {
                     'code': 500,
                     'message': inst.strerror or 'Internal Server Server',
                 }
                 yield rsp
                 continue
 
             exists = False
 
         # Items are always listed for downloads.  They are dropped for uploads
         # IFF they already exist locally.
         if action == b'download':
             if not exists:
                 rsp['error'] = {
                     'code': 404,
                     'message': "The object does not exist",
                 }
                 yield rsp
                 continue
 
             elif not verifies:
                 rsp['error'] = {
                     'code': 422,  # XXX: is this the right code?
                     'message': "The object is corrupt",
                 }
                 yield rsp
                 continue
 
         elif verifies:
             yield rsp  # Skip 'actions': already uploaded
             continue
 
         expiresat = datetime.datetime.now() + datetime.timedelta(minutes=10)
 
         def _buildheader():
             # The spec doesn't mention the Accept header here, but avoid
             # a gratuitous deviation from lfs-test-server in the test
             # output.
             hdr = {'Accept': 'application/vnd.git-lfs'}
 
             auth = req.headers.get(b'Authorization', b'')
             if auth.startswith(b'Basic '):
                 hdr['Authorization'] = pycompat.strurl(auth)
 
             return hdr
 
         rsp['actions'] = {
             '%s'
             % pycompat.strurl(action): {
                 'href': pycompat.strurl(
                     b'%s%s/.hg/lfs/objects/%s' % (req.baseurl, req.apppath, oid)
                 ),
                 # datetime.isoformat() doesn't include the 'Z' suffix
                 "expires_at": expiresat.strftime('%Y-%m-%dT%H:%M:%SZ'),
                 'header': _buildheader(),
             }
         }
 
         yield rsp
 
 
 def _processbasictransfer(repo, req, res, checkperm):
     """Handle a single file upload (PUT) or download (GET) action for the Basic
     Transfer Adapter.
 
     After determining if the request is for an upload or download, the access
     must be checked by calling ``checkperm()`` with either 'pull' or 'upload'
     before accessing the files.
 
     https://github.com/git-lfs/git-lfs/blob/master/docs/api/basic-transfers.md
     """
 
     method = req.method
     oid = req.dispatchparts[-1]
     localstore = repo.svfs.lfslocalblobstore
 
     if len(req.dispatchparts) != 4:
         _sethttperror(res, HTTP_NOT_FOUND)
         return True
 
     if method == b'PUT':
         checkperm(b'upload')
 
         # TODO: verify Content-Type?
 
         existed = localstore.has(oid)
 
         # TODO: how to handle timeouts?  The body proxy handles limiting to
         #       Content-Length, but what happens if a client sends less than it
         #       says it will?
 
         statusmessage = hgwebcommon.statusmessage
         try:
             localstore.download(oid, req.bodyfh, req.headers[b'Content-Length'])
             res.status = statusmessage(HTTP_OK if existed else HTTP_CREATED)
         except blobstore.LfsCorruptionError:
             _logexception(req)
 
             # XXX: Is this the right code?
             res.status = statusmessage(422, b'corrupt blob')
 
         # There's no payload here, but this is the header that lfs-test-server
         # sends back.  This eliminates some gratuitous test output conditionals.
         res.headers[b'Content-Type'] = b'text/plain; charset=utf-8'
         res.setbodybytes(b'')
 
         return True
     elif method == b'GET':
         checkperm(b'pull')
 
         res.status = hgwebcommon.statusmessage(HTTP_OK)
         res.headers[b'Content-Type'] = b'application/octet-stream'
 
         try:
             # TODO: figure out how to send back the file in chunks, instead of
             #       reading the whole thing.  (Also figure out how to send back
             #       an error status if an IOError occurs after a partial write
             #       in that case.  Here, everything is read before starting.)
             res.setbodybytes(localstore.read(oid))
         except blobstore.LfsCorruptionError:
             _logexception(req)
 
             # XXX: Is this the right code?
             res.status = hgwebcommon.statusmessage(422, b'corrupt blob')
             res.setbodybytes(b'')
 
         return True
     else:
         _sethttperror(
             res,
             HTTP_METHOD_NOT_ALLOWED,
             message=b'Unsupported LFS transfer method: %s' % method,
         )
         return True

hgext/lfs/wrapper.py

@@ -1,548 +1,548
 # 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.
 
 
 import hashlib
 
 from mercurial.i18n import _
 from mercurial.node import bin, hex, short
 from mercurial.pycompat import (
     getattr,
     setattr,
 )
 
 from mercurial import (
     bundle2,
     changegroup,
     cmdutil,
     context,
     error,
     exchange,
     exthelper,
     localrepo,
     revlog,
     scmutil,
     util,
     vfs as vfsmod,
     wireprotov1server,
 )
 
 from mercurial.upgrade_utils import (
     actions as upgrade_actions,
     engine as upgrade_engine,
 )
 
 from mercurial.interfaces import repository
 
 from mercurial.utils import (
     storageutil,
     stringutil,
 )
 
 from ..largefiles import lfutil
 
 from . import (
     blobstore,
     pointer,
 )
 
 eh = exthelper.exthelper()
 
 
[e-mail](localrepo, b'makefilestorage')
[e-mail](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)
 
 
[e-mail](changegroup, b'allsupportedversions')
[e-mail](changegroup, 'allsupportedversions')
 def allsupportedversions(orig, ui):
     versions = orig(ui)
     versions.add(b'03')
     return versions
 
 
[e-mail](wireprotov1server, b'_capabilities')
[e-mail](wireprotov1server, '_capabilities')
 def _capabilities(orig, repo, proto):
     '''Wrap server command to announce lfs server capability'''
     caps = orig(repo, proto)
     if util.safehasattr(repo.svfs, b'lfslocalblobstore'):
         # Advertise a slightly different capability when lfs is *required*, so
         # that the client knows it MUST load the extension.  If lfs is not
         # required on the server, there's no reason to autoload the extension
         # on the client.
         if b'lfs' in repo.requirements:
             caps.append(b'lfs-serve')
 
         caps.append(b'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 = self.filename
         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(b'x-hg-'):
             name = k[len(b'x-hg-') :]
             hgmeta[name] = p[k]
     if hgmeta or text.startswith(b'\1\n'):
         text = storageutil.packmeta(hgmeta, text)
 
     return (text, True)
 
 
 def writetostore(self, text):
     # hg filelog metadata (includes rename, etc)
     hgmeta, offset = storageutil.parsemeta(text)
     if offset and offset > 0:
         # lfs blob does not contain hg filelog metadata
         text = text[offset:]
 
     # git-lfs only supports sha256
     oid = hex(hashlib.sha256(text).digest())
     self.opener.lfslocalblobstore.write(oid, text)
 
     # replace contents with metadata
     longoid = b'sha256:%s' % oid
     metadata = pointer.gitlfspointer(oid=longoid, size=b'%d' % 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 stringutil.binary(text):
         # not hg filelog metadata (affecting commit hash), no "x-hg-" prefix
         metadata[b'x-is-binary'] = b'0'
 
     # translate hg filelog metadata to lfs metadata with "x-hg-" prefix
     if hgmeta is not None:
         for k, v in hgmeta.items():
             metadata[b'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 == rlog.nullid:
         return False
     flags = rlog.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(b'lfstrack')
 
     if lfstrack:
         textlen = len(text)
         # exclude hg rename meta from file size
         meta, offset = storageutil.parsemeta(text)
         if offset:
             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._revlog, node):
         rawtext = self._revlog.rawdata(node)
         if not rawtext:
             return False
         metadata = pointer.deserialize(rawtext)
         if b'x-hg-copy' in metadata and b'x-hg-copyrev' in metadata:
             return metadata[b'x-hg-copy'], bin(metadata[b'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._revlog, rev=rev):
         # fast path: use lfs metadata to answer size
         rawtext = self._revlog.rawdata(rev)
         metadata = pointer.deserialize(rawtext)
         return int(metadata[b'size'])
     return orig(self, rev)
 
 
[e-mail](revlog, b'_verify_revision')
[e-mail](revlog, '_verify_revision')
 def _verify_revision(orig, rl, skipflags, state, node):
     if _islfs(rl, node=node):
         rawtext = rl.rawdata(node)
         metadata = pointer.deserialize(rawtext)
 
         # Don't skip blobs that are stored locally, as local verification is
         # relatively cheap and there's no other way to verify the raw data in
         # the revlog.
         if rl.opener.lfslocalblobstore.has(metadata.oid()):
             skipflags &= ~revlog.REVIDX_EXTSTORED
         elif skipflags & revlog.REVIDX_EXTSTORED:
             # The wrapped method will set `skipread`, but there's enough local
             # info to check renames.
             state[b'safe_renamed'].add(node)
 
     orig(rl, skipflags, state, node)
 
 
[e-mail](context.basefilectx, b'cmp')
[e-mail](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
     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)
 
 
[e-mail](context.basefilectx, b'isbinary')
[e-mail](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(b'x-is-binary', 1)))
     return orig(self)
 
 
 def filectxislfs(self):
     return _islfs(self.filelog()._revlog, self.filenode())
 
 
[e-mail](cmdutil, b'_updatecatformatter')
[e-mail](cmdutil, '_updatecatformatter')
 def _updatecatformatter(orig, fm, ctx, matcher, path, decode):
     orig(fm, ctx, matcher, path, decode)
     fm.data(rawdata=ctx[path].rawdata())
 
 
[e-mail](scmutil, b'wrapconvertsink')
[e-mail](scmutil, 'wrapconvertsink')
 def convertsink(orig, sink):
     sink = orig(sink)
     if sink.repotype == b'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 b'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(b'lfs')
                         scmutil.writereporequirements(self.repo)
 
                 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.
[e-mail](vfsmod.readonlyvfs, b'__init__')
[e-mail](vfsmod.readonlyvfs, '__init__')
 def vfsinit(orig, self, othervfs):
     orig(self, othervfs)
     # copy lfs related options
     for k, v in othervfs.options.items():
         if k.startswith(b'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 [b'lfslocalblobstore', b'lfsremoteblobstore']:
         if util.safehasattr(othervfs, name):
             setattr(self, name, getattr(othervfs, name))
 
 
 def _prefetchfiles(repo, revmatches):
     """Ensure that required LFS blobs are present, fetching them as a group if
     needed."""
     if not util.safehasattr(repo.svfs, b'lfslocalblobstore'):
         return
 
     pointers = []
     oids = set()
     localstore = repo.svfs.lfslocalblobstore
 
     for rev, match in revmatches:
         ctx = repo[rev]
         for f in ctx.walk(match):
             p = pointerfromctx(ctx, f)
             if p and p.oid() not in oids and not localstore.has(p.oid()):
                 p.filename = f
                 pointers.append(p)
                 oids.add(p.oid())
 
     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, b'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, b'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)
 
 
[e-mail](exchange, b'push')
[e-mail](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."""
     if b'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(b'lfs'):
             # This is a copy of the message in exchange.push() when requirements
             # are missing between local repos.
             m = _(b"required features are not supported in the destination: %s")
             raise error.Abort(
                 m % b'lfs', hint=_(b'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
         try:
             repo.svfs.lfsremoteblobstore = blobstore.remote(repo, remote.url())
             return orig(repo, remote, *args, **kwargs)
         finally:
             repo.svfs.lfsremoteblobstore = remotestore
     else:
         return orig(repo, remote, *args, **kwargs)
 
 
 # when writing a bundle via "hg bundle" command, upload related LFS blobs
[e-mail](bundle2, b'writenewbundle')
[e-mail](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(b'lfs: computing set of blobs to upload\n')
     pointers = {}
 
     makeprogress = repo.ui.makeprogress
     with makeprogress(
         _(b'lfs search'), _(b'changesets'), len(revs)
     ) as progress:
         for r in revs:
             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.
 
     Optionally, the pointer for a file deleted from the context can be returned.
     Since no such pointer is actually stored, and to distinguish from a non LFS
     file, this pointer is represented by an empty dict.
     """
     _ctx = ctx
     if f not in ctx:
         if not removed:
             return None
         if f in ctx.p1():
             _ctx = ctx.p1()
         elif f in ctx.p2():
             _ctx = ctx.p2()
         else:
             return None
     fctx = _ctx[f]
     if not _islfs(fctx.filelog()._revlog, fctx.filenode()):
         return None
     try:
         p = pointer.deserialize(fctx.rawdata())
         if ctx == _ctx:
             return p
         return {}
     except pointer.InvalidPointer as ex:
         raise error.Abort(
             _(b'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
     stored for the path is an empty dict.
     """
     result = {}
     m = ctx.repo().narrowmatch()
 
     # TODO: consider manifest.fastread() instead
     for f in ctx.files():
         if not m(f):
             continue
         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)
 
 
[e-mail](upgrade_engine, b'finishdatamigration')
[e-mail](upgrade_engine, '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, b'lfslocalblobstore'
     ) and util.safehasattr(dstrepo.svfs, b'lfslocalblobstore'):
         srclfsvfs = srcrepo.svfs.lfslocalblobstore.vfs
         dstlfsvfs = dstrepo.svfs.lfslocalblobstore.vfs
 
         for dirpath, dirs, files in srclfsvfs.walk():
             for oid in files:
                 ui.write(_(b'copying lfs blob %s\n') % oid)
                 lfutil.link(srclfsvfs.join(oid), dstlfsvfs.join(oid))
 
 
[e-mail](upgrade_actions, b'preservedrequirements')
[e-mail](upgrade_actions, b'supporteddestrequirements')
[e-mail](upgrade_actions, 'preservedrequirements')
[e-mail](upgrade_actions, 'supporteddestrequirements')
 def upgraderequirements(orig, repo):
     reqs = orig(repo)
     if b'lfs' in repo.requirements:
         reqs.add(b'lfs')
     return reqs