lfs: use sysstr to check for attribute presence

We do not need bytes here.

hgext/lfs/blobstore.py

@@ -1,789 +1,789 b''
 # 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.
 
 
 import contextlib
 import errno
 import hashlib
 import json
 import os
 import re
 import socket
 
 from mercurial.i18n import _
 from mercurial.pycompat import getattr
 from mercurial.node import hex
 
 from mercurial import (
     encoding,
     error,
     httpconnection as httpconnectionmod,
     pathutil,
     pycompat,
     url as urlmod,
     util,
     vfs as vfsmod,
     worker,
 )
 
 from mercurial.utils import (
     stringutil,
     urlutil,
 )
 
 from ..largefiles import lfutil
 
 # 64 bytes for SHA256
 _lfsre = re.compile(br'\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(b'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 b''), 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 (b'', [], oids)
 
 
 class nullvfs(lfsvfs):
     def __init__(self):
         pass
 
     def exists(self, oid):
         return False
 
     def read(self, oid):
         # store.read() calls into here if the blob doesn't exist in its
         # self.vfs.  Raise the same error as a normal vfs when asked to read a
         # file that doesn't exist.  The only difference is the full file path
         # isn't available in the error.
         raise IOError(
             errno.ENOENT,
             pycompat.sysstr(b'%s: No such file or directory' % oid),
         )
 
     def walk(self, path=None, onerror=None):
         return (b'', [], [])
 
     def write(self, oid, data):
         pass
 
 
 class lfsuploadfile(httpconnectionmod.httpsendfile):
     """a file-like object that supports keepalive."""
 
     def __init__(self, ui, filename):
         super(lfsuploadfile, self).__init__(ui, filename, b'rb')
         self.read = self._data.read
 
     def _makeprogress(self):
         return None  # progress is handled by the worker client
 
 
 class local:
     """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(b'lfs/objects')
         self.vfs = lfsvfs(fullpath)
 
         if repo.ui.configbool(b'experimental', b'lfs.disableusercache'):
             self.cachevfs = nullvfs()
         else:
             usercache = lfutil._usercachedir(repo.ui, b'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."""
         return open(self.path(oid), 'rb')
 
     def path(self, oid):
         """Build the path for the given blob ``oid``.
 
         If the blob exists locally, the path may point to either the usercache
         or the local store.  If it doesn't, it will point to the local store.
         This is meant for situations where existing code that isn't LFS aware
         needs to open a blob.  Generally, prefer the ``open`` method on this
         class.
         """
         # 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.join(oid)
 
         return self.vfs.join(oid)
 
     def download(self, oid, src, content_length):
         """Read the blob from the remote source in chunks, verify the content,
         and write to this local blobstore."""
         sha256 = hashlib.sha256()
         size = 0
 
         with self.vfs(oid, b'wb', atomictemp=True) as fp:
             for chunk in util.filechunkiter(src, size=1048576):
                 fp.write(chunk)
                 sha256.update(chunk)
                 size += len(chunk)
 
             # If the server advertised a length longer than what we actually
             # received, then we should expect that the server crashed while
             # producing the response (but the server has no way of telling us
             # that), and we really don't need to try to write the response to
             # the localstore, because it's not going to match the expected.
             # The server also uses this method to store data uploaded by the
             # client, so if this happens on the server side, it's possible
             # that the client crashed or an antivirus interfered with the
             # upload.
             if content_length is not None and int(content_length) != size:
                 msg = (
                     b"Response length (%d) does not match Content-Length "
                     b"header (%d) for %s"
                 )
                 raise LfsRemoteError(_(msg) % (size, int(content_length), oid))
 
             realoid = hex(sha256.digest())
             if realoid != oid:
                 raise LfsCorruptionError(
                     _(b'corrupt remote lfs object: %s') % oid
                 )
 
         self._linktousercache(oid)
 
     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, b'wb', atomictemp=True) as fp:
             fp.write(data)
 
         self._linktousercache(oid)
 
     def linkfromusercache(self, oid):
         """Link blobs found in the user cache into this store.
 
         The server module needs to do this when it lets the client know not to
         upload the blob, to ensure it is always available in this store.
         Normally this is done implicitly when the client reads or writes the
         blob, but that doesn't happen when the server tells the client that it
         already has the blob.
         """
         if not isinstance(self.cachevfs, nullvfs) and not self.vfs.exists(oid):
             self.ui.note(_(b'lfs: found %s in the usercache\n') % oid)
             lfutil.link(self.cachevfs.join(oid), self.vfs.join(oid))
 
     def _linktousercache(self, 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) and not isinstance(
             self.cachevfs, nullvfs
         ):
             self.ui.note(_(b'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 hex(hashlib.sha256(blob).digest()) == oid:
                 self.ui.note(_(b'lfs: found %s in the usercache\n') % oid)
                 lfutil.link(self.cachevfs.join(oid), self.vfs.join(oid))
         else:
             self.ui.note(_(b'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 verify(self, oid):
         """Indicate whether or not the hash of the underlying file matches its
         name."""
         sha256 = hashlib.sha256()
 
         with self.open(oid) as fp:
             for chunk in util.filechunkiter(fp, size=1048576):
                 sha256.update(chunk)
 
         return oid == hex(sha256.digest())
 
     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)
 
 
 def _urlerrorreason(urlerror):
     """Create a friendly message for the given URLError to be used in an
     LfsRemoteError message.
     """
     inst = urlerror
 
     if isinstance(urlerror.reason, Exception):
         inst = urlerror.reason
 
-    if util.safehasattr(inst, b'reason'):
+    if util.safehasattr(inst, 'reason'):
         try:  # usually it is in the form (errno, strerror)
             reason = inst.reason.args[1]
         except (AttributeError, IndexError):
             # it might be anything, for example a string
             reason = inst.reason
         if isinstance(reason, str):
             # SSLError of Python 2.7.9 contains a unicode
             reason = encoding.unitolocal(reason)
         return reason
     elif getattr(inst, "strerror", None):
         return encoding.strtolocal(inst.strerror)
     else:
         return stringutil.forcebytestr(urlerror)
 
 
 class lfsauthhandler(util.urlreq.basehandler):
     handler_order = 480  # Before HTTPDigestAuthHandler (== 490)
 
     def http_error_401(self, req, fp, code, msg, headers):
         """Enforces that any authentication performed is HTTP Basic
         Authentication.  No authentication is also acceptable.
         """
         authreq = headers.get('www-authenticate', None)
         if authreq:
             scheme = authreq.split()[0]
 
             if scheme.lower() != 'basic':
                 msg = _(b'the server must support Basic Authentication')
                 raise util.urlerr.httperror(
                     req.get_full_url(),
                     code,
                     encoding.strfromlocal(msg),
                     headers,
                     fp,
                 )
         return None
 
 
 class _gitlfsremote:
     def __init__(self, repo, url):
         ui = repo.ui
         self.ui = ui
         baseurl, authinfo = url.authinfo()
         self.baseurl = baseurl.rstrip(b'/')
         useragent = repo.ui.config(b'experimental', b'lfs.user-agent')
         if not useragent:
             useragent = b'git-lfs/2.3.4 (Mercurial %s)' % util.version()
         self.urlopener = urlmod.opener(ui, authinfo, useragent)
         self.urlopener.add_handler(lfsauthhandler())
         self.retry = ui.configint(b'lfs', b'retry')
 
     def writebatch(self, pointers, fromstore):
         """Batch upload from local to remote blobstore."""
         self._batch(_deduplicate(pointers), fromstore, b'upload')
 
     def readbatch(self, pointers, tostore):
         """Batch download from remote to local blostore."""
         self._batch(_deduplicate(pointers), tostore, b'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': pycompat.strurl(p.oid()), 'size': p.size()}
             for p in pointers
         ]
         requestdata = pycompat.bytesurl(
             json.dumps(
                 {
                     'objects': objects,
                     'operation': pycompat.strurl(action),
                 }
             )
         )
         url = b'%s/objects/batch' % self.baseurl
         batchreq = util.urlreq.request(pycompat.strurl(url), data=requestdata)
         batchreq.add_header('Accept', 'application/vnd.git-lfs+json')
         batchreq.add_header('Content-Type', 'application/vnd.git-lfs+json')
         try:
             with contextlib.closing(self.urlopener.open(batchreq)) as rsp:
                 rawjson = rsp.read()
         except util.urlerr.httperror as ex:
             hints = {
                 400: _(
                     b'check that lfs serving is enabled on %s and "%s" is '
                     b'supported'
                 )
                 % (self.baseurl, action),
                 404: _(b'the "lfs.url" config may be used to override %s')
                 % self.baseurl,
             }
             hint = hints.get(ex.code, _(b'api=%s, action=%s') % (url, action))
             raise LfsRemoteError(
                 _(b'LFS HTTP error: %s') % stringutil.forcebytestr(ex),
                 hint=hint,
             )
         except util.urlerr.urlerror as ex:
             hint = (
                 _(b'the "lfs.url" config may be used to override %s')
                 % self.baseurl
             )
             raise LfsRemoteError(
                 _(b'LFS error: %s') % _urlerrorreason(ex), hint=hint
             )
         try:
             response = pycompat.json_loads(rawjson)
         except ValueError:
             raise LfsRemoteError(
                 _(b'LFS server returns invalid JSON: %s')
                 % rawjson.encode("utf-8")
             )
 
         if self.ui.debugflag:
             self.ui.debug(b'Status: %d\n' % rsp.status)
             # lfs-test-server and hg serve return headers in different order
             headers = pycompat.bytestr(rsp.info()).strip()
             self.ui.debug(b'%s\n' % b'\n'.join(sorted(headers.splitlines())))
 
             if 'objects' in response:
                 response['objects'] = sorted(
                     response['objects'], key=lambda p: p['oid']
                 )
             self.ui.debug(
                 b'%s\n'
                 % pycompat.bytesurl(
                     json.dumps(
                         response,
                         indent=2,
                         separators=('', ': '),
                         sort_keys=True,
                     )
                 )
             )
 
         def encodestr(x):
             if isinstance(x, str):
                 return x.encode('utf-8')
             return x
 
         return pycompat.rapply(encodestr, response)
 
     def _checkforservererror(self, pointers, responses, action):
         """Scans errors from objects
 
         Raises LfsRemoteError if any objects have an error"""
         for response in responses:
             # The server should return 404 when objects cannot be found. Some
             # server implementation (ex. lfs-test-server)  does not set "error"
             # but just removes "download" from "actions". Treat that case
             # as the same as 404 error.
             if b'error' not in response:
                 if action == b'download' and action not in response.get(
                     b'actions', []
                 ):
                     code = 404
                 else:
                     continue
             else:
                 # An error dict without a code doesn't make much sense, so
                 # treat as a server error.
                 code = response.get(b'error').get(b'code', 500)
 
             ptrmap = {p.oid(): p for p in pointers}
             p = ptrmap.get(response[b'oid'], None)
             if p:
                 filename = getattr(p, 'filename', b'unknown')
                 errors = {
                     404: b'The object does not exist',
                     410: b'The object was removed by the owner',
                     422: b'Validation error',
                     500: b'Internal server error',
                 }
                 msg = errors.get(code, b'status code %d' % code)
                 raise LfsRemoteError(
                     _(b'LFS server error for "%s": %s') % (filename, msg)
                 )
             else:
                 raise LfsRemoteError(
                     _(b'LFS server error. Unsolicited response for oid %s')
                     % response[b'oid']
                 )
 
     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(b'objects', [])
         self._checkforservererror(pointers, objects, action)
 
         # 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(b'actions', [])
         ]
 
         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 = obj[b'oid']
         href = obj[b'actions'][action].get(b'href')
         headers = obj[b'actions'][action].get(b'header', {}).items()
 
         request = util.urlreq.request(pycompat.strurl(href))
         if action == b'upload':
             # If uploading blobs, read data from local blobstore.
             if not localstore.verify(oid):
                 raise error.Abort(
                     _(b'detected corrupt lfs object: %s') % oid,
                     hint=_(b'run hg verify'),
                 )
 
         for k, v in headers:
             request.add_header(pycompat.strurl(k), pycompat.strurl(v))
 
         try:
             if action == b'upload':
                 request.data = lfsuploadfile(self.ui, localstore.path(oid))
                 request.get_method = lambda: 'PUT'
                 request.add_header('Content-Type', 'application/octet-stream')
                 request.add_header('Content-Length', request.data.length)
 
             with contextlib.closing(self.urlopener.open(request)) as res:
                 contentlength = res.info().get(b"content-length")
                 ui = self.ui  # Shorten debug lines
                 if self.ui.debugflag:
                     ui.debug(b'Status: %d\n' % res.status)
                     # lfs-test-server and hg serve return headers in different
                     # order
                     headers = pycompat.bytestr(res.info()).strip()
                     ui.debug(b'%s\n' % b'\n'.join(sorted(headers.splitlines())))
 
                 if action == b'download':
                     # If downloading blobs, store downloaded data to local
                     # blobstore
                     localstore.download(oid, res, contentlength)
                 else:
                     blocks = []
                     while True:
                         data = res.read(1048576)
                         if not data:
                             break
                         blocks.append(data)
 
                     response = b"".join(blocks)
                     if response:
                         ui.debug(b'lfs %s response: %s' % (action, response))
         except util.urlerr.httperror as ex:
             if self.ui.debugflag:
                 self.ui.debug(
                     b'%s: %s\n' % (oid, ex.read())
                 )  # XXX: also bytes?
             raise LfsRemoteError(
                 _(b'LFS HTTP error: %s (oid=%s, action=%s)')
                 % (stringutil.forcebytestr(ex), oid, action)
             )
         except util.urlerr.urlerror as ex:
             hint = _(b'attempted connection to %s') % pycompat.bytesurl(
                 util.urllibcompat.getfullurl(request)
             )
             raise LfsRemoteError(
                 _(b'LFS error: %s') % _urlerrorreason(ex), hint=hint
             )
         finally:
             if request.data:
                 request.data.close()
 
     def _batch(self, pointers, localstore, action):
         if action not in [b'upload', b'download']:
             raise error.ProgrammingError(b'invalid Git-LFS action: %s' % action)
 
         response = self._batchrequest(pointers, action)
         objects = self._extractobjects(response, pointers, action)
         total = sum(x.get(b'size', 0) for x in objects)
         sizes = {}
         for obj in objects:
             sizes[obj.get(b'oid')] = obj.get(b'size', 0)
         topic = {
             b'upload': _(b'lfs uploading'),
             b'download': _(b'lfs downloading'),
         }[action]
         if len(objects) > 1:
             self.ui.note(
                 _(b'lfs: need to transfer %d objects (%s)\n')
                 % (len(objects), util.bytecount(total))
             )
 
         def transfer(chunk):
             for obj in chunk:
                 objsize = obj.get(b'size', 0)
                 if self.ui.verbose:
                     if action == b'download':
                         msg = _(b'lfs: downloading %s (%s)\n')
                     elif action == b'upload':
                         msg = _(b'lfs: uploading %s (%s)\n')
                     self.ui.note(
                         msg % (obj.get(b'oid'), util.bytecount(objsize))
                     )
                 retry = self.retry
                 while True:
                     try:
                         self._basictransfer(obj, action, localstore)
                         yield 1, obj.get(b'oid')
                         break
                     except socket.error as ex:
                         if retry > 0:
                             self.ui.note(
                                 _(b'lfs: failed: %r (remaining retry %d)\n')
                                 % (stringutil.forcebytestr(ex), retry)
                             )
                             retry -= 1
                             continue
                         raise
 
         # Until https multiplexing gets sorted out.  It's not clear if
         # ConnectionManager.set_ready() is externally synchronized for thread
         # safety with Windows workers.
         if self.ui.configbool(b'experimental', b'lfs.worker-enable'):
             # The POSIX workers are forks of this process, so before spinning
             # them up, close all pooled connections.  Otherwise, there's no way
             # to coordinate between them about who is using what, and the
             # transfers will get corrupted.
             #
             # TODO: add a function to keepalive.ConnectionManager to mark all
             #  ready connections as in use, and roll that back after the fork?
             #  That would allow the existing pool of connections in this process
             #  to be preserved.
             def prefork():
                 for h in self.urlopener.handlers:
                     getattr(h, "close_all", lambda: None)()
 
             oids = worker.worker(
                 self.ui,
                 0.1,
                 transfer,
                 (),
                 sorted(objects, key=lambda o: o.get(b'oid')),
                 prefork=prefork,
             )
         else:
             oids = transfer(sorted(objects, key=lambda o: o.get(b'oid')))
 
         with self.ui.makeprogress(
             topic, unit=_(b"bytes"), total=total
         ) as progress:
             progress.update(0)
             processed = 0
             blobs = 0
             for _one, oid in oids:
                 processed += sizes[oid]
                 blobs += 1
                 progress.update(processed)
                 self.ui.note(_(b'lfs: processed: %s\n') % oid)
 
         if blobs > 0:
             if action == b'upload':
                 self.ui.status(
                     _(b'lfs: uploaded %d files (%s)\n')
                     % (blobs, util.bytecount(processed))
                 )
             elif action == b'download':
                 self.ui.status(
                     _(b'lfs: downloaded %d files (%s)\n')
                     % (blobs, util.bytecount(processed))
                 )
 
     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:
     """Dummy store storing blobs to temp directory."""
 
     def __init__(self, repo, url):
         fullpath = repo.vfs.join(b'lfs', url.path)
         self.vfs = lfsvfs(fullpath)
 
     def writebatch(self, pointers, fromstore):
         for p in _deduplicate(pointers):
             content = fromstore.read(p.oid(), verify=True)
             with self.vfs(p.oid(), b'wb', atomictemp=True) as fp:
                 fp.write(content)
 
     def readbatch(self, pointers, tostore):
         for p in _deduplicate(pointers):
             with self.vfs(p.oid(), b'rb') as fp:
                 tostore.download(p.oid(), fp, None)
 
 
 class _nullremote:
     """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:
     """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(_(b'lfs.url needs to be configured'))
 
 
 _storemap = {
     b'https': _gitlfsremote,
     b'http': _gitlfsremote,
     b'file': _dummyremote,
     b'null': _nullremote,
     None: _promptremote,
 }
 
 
 def _deduplicate(pointers):
     """Remove any duplicate oids that exist in the list"""
     reduced = util.sortdict()
     for p in pointers:
         reduced[p.oid()] = p
     return reduced.values()
 
 
 def _verify(oid, content):
     realoid = hex(hashlib.sha256(content).digest())
     if realoid != oid:
         raise LfsCorruptionError(
             _(b'detected corrupt lfs object: %s') % oid,
             hint=_(b'run hg verify'),
         )
 
 
 def remote(repo, remote=None):
     """remotestore factory. return a store in _storemap depending on config
 
     If ``lfs.url`` is specified, use that remote endpoint.  Otherwise, try to
     infer the endpoint, based on the remote repository using the same path
     adjustments as git.  As an extension, 'http' is supported as well so that
     ``hg serve`` works out of the box.
 
     https://github.com/git-lfs/git-lfs/blob/master/docs/api/server-discovery.md
     """
     lfsurl = repo.ui.config(b'lfs', b'url')
     url = urlutil.url(lfsurl or b'')
     if lfsurl is None:
         if remote:
             path = remote
-        elif util.safehasattr(repo, b'_subtoppath'):
+        elif util.safehasattr(repo, '_subtoppath'):
             # The pull command sets this during the optional update phase, which
             # tells exactly where the pull originated, whether 'paths.default'
             # or explicit.
             path = repo._subtoppath
         else:
             # TODO: investigate 'paths.remote:lfsurl' style path customization,
             # and fall back to inferring from 'paths.remote' if unspecified.
             path = repo.ui.config(b'paths', b'default') or b''
 
         defaulturl = urlutil.url(path)
 
         # TODO: support local paths as well.
         # TODO: consider the ssh -> https transformation that git applies
         if defaulturl.scheme in (b'http', b'https'):
             if defaulturl.path and defaulturl.path[:-1] != b'/':
                 defaulturl.path += b'/'
             defaulturl.path = (defaulturl.path or b'') + b'.git/info/lfs'
 
             url = urlutil.url(bytes(defaulturl))
             repo.ui.note(_(b'lfs: assuming remote store: %s\n') % url)
 
     scheme = url.scheme
     if scheme not in _storemap:
         raise error.Abort(_(b'lfs: unknown url scheme: %s') % scheme)
     return _storemap[scheme](repo, url)
 
 
 class LfsRemoteError(error.StorageError):
     pass
 
 
 class LfsCorruptionError(error.Abort):
     """Raised when a corrupt blob is detected, aborting an operation
 
     It exists to allow specialized handling on the server side."""

hgext/lfs/wrapper.py

@@ -1,545 +1,545 b''
 # 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()
 
 
 @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(b'03')
     return versions
 
 
 @eh.wrapfunction(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'):
+    if util.safehasattr(repo.svfs, '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)
 
 
 @eh.wrapfunction(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)
 
 
 @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
     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)
 
 
 @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(b'x-is-binary', 1)))
     return orig(self)
 
 
 def filectxislfs(self):
     return _islfs(self.filelog()._revlog, 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 == 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.
 @eh.wrapfunction(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']:
+    for name in ['lfslocalblobstore', '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'):
+    if not util.safehasattr(repo.svfs, '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'):
+    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, b'lfsremoteblobstore'):
+    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"""
     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."""
     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
 @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(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)
 
 
 @eh.wrapfunction(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'):
+    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(_(b'copying lfs blob %s\n') % oid)
                 lfutil.link(srclfsvfs.join(oid), dstlfsvfs.join(oid))
 
 
 @eh.wrapfunction(upgrade_actions, 'preservedrequirements')
 @eh.wrapfunction(upgrade_actions, 'supporteddestrequirements')
 def upgraderequirements(orig, repo):
     reqs = orig(repo)
     if b'lfs' in repo.requirements:
         reqs.add(b'lfs')
     return reqs