store: lazily get file size on demand for the fncache case

We don't have the information in the first place, so we can avoid querying the
file system inconditionnaly for use case we don't needs it.

This change requires the StoreFile class to be passed a vfs to retrieve the
file_size if needed.

In the non-fncache case, we already have the information from file system
walking, so we keep it and use it.

mercurial/store.py

@@ -1,963 +1,967 b''
 # store.py - repository store handling for Mercurial
 #
 # Copyright 2008 Olivia Mackall <[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 functools
 import os
 import re
 import stat
 from typing import Generator
 
 from .i18n import _
 from .pycompat import getattr
 from .thirdparty import attr
 from .node import hex
 from . import (
     changelog,
     error,
     manifest,
     policy,
     pycompat,
     util,
     vfs as vfsmod,
 )
 from .utils import hashutil
 
 parsers = policy.importmod('parsers')
 # how much bytes should be read from fncache in one read
 # It is done to prevent loading large fncache files into memory
 fncache_chunksize = 10 ** 6
 
 
 def _matchtrackedpath(path, matcher):
     """parses a fncache entry and returns whether the entry is tracking a path
     matched by matcher or not.
 
     If matcher is None, returns True"""
 
     if matcher is None:
         return True
     path = decodedir(path)
     if path.startswith(b'data/'):
         return matcher(path[len(b'data/') : -len(b'.i')])
     elif path.startswith(b'meta/'):
         return matcher.visitdir(path[len(b'meta/') : -len(b'/00manifest.i')])
 
     raise error.ProgrammingError(b"cannot decode path %s" % path)
 
 
 # This avoids a collision between a file named foo and a dir named
 # foo.i or foo.d
 def _encodedir(path):
     """
     >>> _encodedir(b'data/foo.i')
     'data/foo.i'
     >>> _encodedir(b'data/foo.i/bla.i')
     'data/foo.i.hg/bla.i'
     >>> _encodedir(b'data/foo.i.hg/bla.i')
     'data/foo.i.hg.hg/bla.i'
     >>> _encodedir(b'data/foo.i\\ndata/foo.i/bla.i\\ndata/foo.i.hg/bla.i\\n')
     'data/foo.i\\ndata/foo.i.hg/bla.i\\ndata/foo.i.hg.hg/bla.i\\n'
     """
     return (
         path.replace(b".hg/", b".hg.hg/")
         .replace(b".i/", b".i.hg/")
         .replace(b".d/", b".d.hg/")
     )
 
 
 encodedir = getattr(parsers, 'encodedir', _encodedir)
 
 
 def decodedir(path):
     """
     >>> decodedir(b'data/foo.i')
     'data/foo.i'
     >>> decodedir(b'data/foo.i.hg/bla.i')
     'data/foo.i/bla.i'
     >>> decodedir(b'data/foo.i.hg.hg/bla.i')
     'data/foo.i.hg/bla.i'
     """
     if b".hg/" not in path:
         return path
     return (
         path.replace(b".d.hg/", b".d/")
         .replace(b".i.hg/", b".i/")
         .replace(b".hg.hg/", b".hg/")
     )
 
 
 def _reserved():
     """characters that are problematic for filesystems
 
     * ascii escapes (0..31)
     * ascii hi (126..255)
     * windows specials
 
     these characters will be escaped by encodefunctions
     """
     winreserved = [ord(x) for x in u'\\:*?"<>|']
     for x in range(32):
         yield x
     for x in range(126, 256):
         yield x
     for x in winreserved:
         yield x
 
 
 def _buildencodefun():
     """
     >>> enc, dec = _buildencodefun()
 
     >>> enc(b'nothing/special.txt')
     'nothing/special.txt'
     >>> dec(b'nothing/special.txt')
     'nothing/special.txt'
 
     >>> enc(b'HELLO')
     '_h_e_l_l_o'
     >>> dec(b'_h_e_l_l_o')
     'HELLO'
 
     >>> enc(b'hello:world?')
     'hello~3aworld~3f'
     >>> dec(b'hello~3aworld~3f')
     'hello:world?'
 
     >>> enc(b'the\\x07quick\\xADshot')
     'the~07quick~adshot'
     >>> dec(b'the~07quick~adshot')
     'the\\x07quick\\xadshot'
     """
     e = b'_'
     xchr = pycompat.bytechr
     asciistr = list(map(xchr, range(127)))
     capitals = list(range(ord(b"A"), ord(b"Z") + 1))
 
     cmap = {x: x for x in asciistr}
     for x in _reserved():
         cmap[xchr(x)] = b"~%02x" % x
     for x in capitals + [ord(e)]:
         cmap[xchr(x)] = e + xchr(x).lower()
 
     dmap = {}
     for k, v in cmap.items():
         dmap[v] = k
 
     def decode(s):
         i = 0
         while i < len(s):
             for l in range(1, 4):
                 try:
                     yield dmap[s[i : i + l]]
                     i += l
                     break
                 except KeyError:
                     pass
             else:
                 raise KeyError
 
     return (
         lambda s: b''.join([cmap[s[c : c + 1]] for c in range(len(s))]),
         lambda s: b''.join(list(decode(s))),
     )
 
 
 _encodefname, _decodefname = _buildencodefun()
 
 
 def encodefilename(s):
     """
     >>> encodefilename(b'foo.i/bar.d/bla.hg/hi:world?/HELLO')
     'foo.i.hg/bar.d.hg/bla.hg.hg/hi~3aworld~3f/_h_e_l_l_o'
     """
     return _encodefname(encodedir(s))
 
 
 def decodefilename(s):
     """
     >>> decodefilename(b'foo.i.hg/bar.d.hg/bla.hg.hg/hi~3aworld~3f/_h_e_l_l_o')
     'foo.i/bar.d/bla.hg/hi:world?/HELLO'
     """
     return decodedir(_decodefname(s))
 
 
 def _buildlowerencodefun():
     """
     >>> f = _buildlowerencodefun()
     >>> f(b'nothing/special.txt')
     'nothing/special.txt'
     >>> f(b'HELLO')
     'hello'
     >>> f(b'hello:world?')
     'hello~3aworld~3f'
     >>> f(b'the\\x07quick\\xADshot')
     'the~07quick~adshot'
     """
     xchr = pycompat.bytechr
     cmap = {xchr(x): xchr(x) for x in range(127)}
     for x in _reserved():
         cmap[xchr(x)] = b"~%02x" % x
     for x in range(ord(b"A"), ord(b"Z") + 1):
         cmap[xchr(x)] = xchr(x).lower()
 
     def lowerencode(s):
         return b"".join([cmap[c] for c in pycompat.iterbytestr(s)])
 
     return lowerencode
 
 
 lowerencode = getattr(parsers, 'lowerencode', None) or _buildlowerencodefun()
 
 # Windows reserved names: con, prn, aux, nul, com1..com9, lpt1..lpt9
 _winres3 = (b'aux', b'con', b'prn', b'nul')  # length 3
 _winres4 = (b'com', b'lpt')  # length 4 (with trailing 1..9)
 
 
 def _auxencode(path, dotencode):
     """
     Encodes filenames containing names reserved by Windows or which end in
     period or space. Does not touch other single reserved characters c.
     Specifically, c in '\\:*?"<>|' or ord(c) <= 31 are *not* encoded here.
     Additionally encodes space or period at the beginning, if dotencode is
     True. Parameter path is assumed to be all lowercase.
     A segment only needs encoding if a reserved name appears as a
     basename (e.g. "aux", "aux.foo"). A directory or file named "foo.aux"
     doesn't need encoding.
 
     >>> s = b'.foo/aux.txt/txt.aux/con/prn/nul/foo.'
     >>> _auxencode(s.split(b'/'), True)
     ['~2efoo', 'au~78.txt', 'txt.aux', 'co~6e', 'pr~6e', 'nu~6c', 'foo~2e']
     >>> s = b'.com1com2/lpt9.lpt4.lpt1/conprn/com0/lpt0/foo.'
     >>> _auxencode(s.split(b'/'), False)
     ['.com1com2', 'lp~749.lpt4.lpt1', 'conprn', 'com0', 'lpt0', 'foo~2e']
     >>> _auxencode([b'foo. '], True)
     ['foo.~20']
     >>> _auxencode([b' .foo'], True)
     ['~20.foo']
     """
     for i, n in enumerate(path):
         if not n:
             continue
         if dotencode and n[0] in b'. ':
             n = b"~%02x" % ord(n[0:1]) + n[1:]
             path[i] = n
         else:
             l = n.find(b'.')
             if l == -1:
                 l = len(n)
             if (l == 3 and n[:3] in _winres3) or (
                 l == 4
                 and n[3:4] <= b'9'
                 and n[3:4] >= b'1'
                 and n[:3] in _winres4
             ):
                 # encode third letter ('aux' -> 'au~78')
                 ec = b"~%02x" % ord(n[2:3])
                 n = n[0:2] + ec + n[3:]
                 path[i] = n
         if n[-1] in b'. ':
             # encode last period or space ('foo...' -> 'foo..~2e')
             path[i] = n[:-1] + b"~%02x" % ord(n[-1:])
     return path
 
 
 _maxstorepathlen = 120
 _dirprefixlen = 8
 _maxshortdirslen = 8 * (_dirprefixlen + 1) - 4
 
 
 def _hashencode(path, dotencode):
     digest = hex(hashutil.sha1(path).digest())
     le = lowerencode(path[5:]).split(b'/')  # skips prefix 'data/' or 'meta/'
     parts = _auxencode(le, dotencode)
     basename = parts[-1]
     _root, ext = os.path.splitext(basename)
     sdirs = []
     sdirslen = 0
     for p in parts[:-1]:
         d = p[:_dirprefixlen]
         if d[-1] in b'. ':
             # Windows can't access dirs ending in period or space
             d = d[:-1] + b'_'
         if sdirslen == 0:
             t = len(d)
         else:
             t = sdirslen + 1 + len(d)
             if t > _maxshortdirslen:
                 break
         sdirs.append(d)
         sdirslen = t
     dirs = b'/'.join(sdirs)
     if len(dirs) > 0:
         dirs += b'/'
     res = b'dh/' + dirs + digest + ext
     spaceleft = _maxstorepathlen - len(res)
     if spaceleft > 0:
         filler = basename[:spaceleft]
         res = b'dh/' + dirs + filler + digest + ext
     return res
 
 
 def _hybridencode(path, dotencode):
     """encodes path with a length limit
 
     Encodes all paths that begin with 'data/', according to the following.
 
     Default encoding (reversible):
 
     Encodes all uppercase letters 'X' as '_x'. All reserved or illegal
     characters are encoded as '~xx', where xx is the two digit hex code
     of the character (see encodefilename).
     Relevant path components consisting of Windows reserved filenames are
     masked by encoding the third character ('aux' -> 'au~78', see _auxencode).
 
     Hashed encoding (not reversible):
 
     If the default-encoded path is longer than _maxstorepathlen, a
     non-reversible hybrid hashing of the path is done instead.
     This encoding uses up to _dirprefixlen characters of all directory
     levels of the lowerencoded path, but not more levels than can fit into
     _maxshortdirslen.
     Then follows the filler followed by the sha digest of the full path.
     The filler is the beginning of the basename of the lowerencoded path
     (the basename is everything after the last path separator). The filler
     is as long as possible, filling in characters from the basename until
     the encoded path has _maxstorepathlen characters (or all chars of the
     basename have been taken).
     The extension (e.g. '.i' or '.d') is preserved.
 
     The string 'data/' at the beginning is replaced with 'dh/', if the hashed
     encoding was used.
     """
     path = encodedir(path)
     ef = _encodefname(path).split(b'/')
     res = b'/'.join(_auxencode(ef, dotencode))
     if len(res) > _maxstorepathlen:
         res = _hashencode(path, dotencode)
     return res
 
 
 def _pathencode(path):
     de = encodedir(path)
     if len(path) > _maxstorepathlen:
         return _hashencode(de, True)
     ef = _encodefname(de).split(b'/')
     res = b'/'.join(_auxencode(ef, True))
     if len(res) > _maxstorepathlen:
         return _hashencode(de, True)
     return res
 
 
 _pathencode = getattr(parsers, 'pathencode', _pathencode)
 
 
 def _plainhybridencode(f):
     return _hybridencode(f, False)
 
 
 def _calcmode(vfs):
     try:
         # files in .hg/ will be created using this mode
         mode = vfs.stat().st_mode
         # avoid some useless chmods
         if (0o777 & ~util.umask) == (0o777 & mode):
             mode = None
     except OSError:
         mode = None
     return mode
 
 
 _data = [
     b'bookmarks',
     b'narrowspec',
     b'data',
     b'meta',
     b'00manifest.d',
     b'00manifest.i',
     b'00changelog.d',
     b'00changelog.i',
     b'phaseroots',
     b'obsstore',
     b'requires',
 ]
 
 REVLOG_FILES_MAIN_EXT = (b'.i',)
 REVLOG_FILES_OTHER_EXT = (
     b'.idx',
     b'.d',
     b'.dat',
     b'.n',
     b'.nd',
     b'.sda',
 )
 # files that are "volatile" and might change between listing and streaming
 #
 # note: the ".nd" file are nodemap data and won't "change" but they might be
 # deleted.
 REVLOG_FILES_VOLATILE_EXT = (b'.n', b'.nd')
 
 # some exception to the above matching
 #
 # XXX This is currently not in use because of issue6542
 EXCLUDED = re.compile(br'.*undo\.[^/]+\.(nd?|i)$')
 
 
 def is_revlog(f, kind, st):
     if kind != stat.S_IFREG:
         return None
     return revlog_type(f)
 
 
 def revlog_type(f):
     # XXX we need to filter `undo.` created by the transaction here, however
     # being naive about it also filter revlog for `undo.*` files, leading to
     # issue6542. So we no longer use EXCLUDED.
     if f.endswith(REVLOG_FILES_MAIN_EXT):
         return FILEFLAGS_REVLOG_MAIN
     elif f.endswith(REVLOG_FILES_OTHER_EXT):
         t = FILETYPE_FILELOG_OTHER
         if f.endswith(REVLOG_FILES_VOLATILE_EXT):
             t |= FILEFLAGS_VOLATILE
         return t
     return None
 
 
 # the file is part of changelog data
 FILEFLAGS_CHANGELOG = 1 << 13
 # the file is part of manifest data
 FILEFLAGS_MANIFESTLOG = 1 << 12
 # the file is part of filelog data
 FILEFLAGS_FILELOG = 1 << 11
 # file that are not directly part of a revlog
 FILEFLAGS_OTHER = 1 << 10
 
 # the main entry point for a revlog
 FILEFLAGS_REVLOG_MAIN = 1 << 1
 # a secondary file for a revlog
 FILEFLAGS_REVLOG_OTHER = 1 << 0
 
 # files that are "volatile" and might change between listing and streaming
 FILEFLAGS_VOLATILE = 1 << 20
 
 FILETYPE_CHANGELOG_MAIN = FILEFLAGS_CHANGELOG | FILEFLAGS_REVLOG_MAIN
 FILETYPE_CHANGELOG_OTHER = FILEFLAGS_CHANGELOG | FILEFLAGS_REVLOG_OTHER
 FILETYPE_MANIFESTLOG_MAIN = FILEFLAGS_MANIFESTLOG | FILEFLAGS_REVLOG_MAIN
 FILETYPE_MANIFESTLOG_OTHER = FILEFLAGS_MANIFESTLOG | FILEFLAGS_REVLOG_OTHER
 FILETYPE_FILELOG_MAIN = FILEFLAGS_FILELOG | FILEFLAGS_REVLOG_MAIN
 FILETYPE_FILELOG_OTHER = FILEFLAGS_FILELOG | FILEFLAGS_REVLOG_OTHER
 FILETYPE_OTHER = FILEFLAGS_OTHER
 
 
 @attr.s(slots=True, init=False)
 class BaseStoreEntry:
     """An entry in the store
 
     This is returned by `store.walk` and represent some data in the store."""
 
     unencoded_path = attr.ib()
     _is_volatile = attr.ib(default=False)
     _file_size = attr.ib(default=None)
 
     def __init__(
         self,
         unencoded_path,
         is_volatile=False,
         file_size=None,
     ):
         self.unencoded_path = unencoded_path
         self._is_volatile = is_volatile
         self._file_size = file_size
 
     def files(self):
         return [
             StoreFile(
                 unencoded_path=self.unencoded_path,
                 file_size=self._file_size,
                 is_volatile=self._is_volatile,
             )
         ]
 
 
 @attr.s(slots=True, init=False)
 class SimpleStoreEntry(BaseStoreEntry):
     """A generic entry in the store"""
 
     is_revlog = False
 
 
 @attr.s(slots=True, init=False)
 class RevlogStoreEntry(BaseStoreEntry):
     """A revlog entry in the store"""
 
     is_revlog = True
     revlog_type = attr.ib(default=None)
     is_revlog_main = attr.ib(default=None)
 
     def __init__(
         self,
         unencoded_path,
         revlog_type,
         is_revlog_main=False,
         is_volatile=False,
         file_size=None,
     ):
         super().__init__(
             unencoded_path=unencoded_path,
             is_volatile=is_volatile,
             file_size=file_size,
         )
         self.revlog_type = revlog_type
         self.is_revlog_main = is_revlog_main
 
 
 @attr.s(slots=True)
 class StoreFile:
     """a file matching an entry"""
 
     unencoded_path = attr.ib()
-    file_size = attr.ib()
+    _file_size = attr.ib(default=False)
     is_volatile = attr.ib(default=False)
 
+    def file_size(self, vfs):
+        if self._file_size is not None:
+            return self._file_size
+        try:
+            return vfs.stat(self.unencoded_path).st_size
+        except FileNotFoundError:
+            return 0
+
 
 class basicstore:
     '''base class for local repository stores'''
 
     def __init__(self, path, vfstype):
         vfs = vfstype(path)
         self.path = vfs.base
         self.createmode = _calcmode(vfs)
         vfs.createmode = self.createmode
         self.rawvfs = vfs
         self.vfs = vfsmod.filtervfs(vfs, encodedir)
         self.opener = self.vfs
 
     def join(self, f):
         return self.path + b'/' + encodedir(f)
 
     def _walk(self, relpath, recurse):
         '''yields (revlog_type, unencoded, size)'''
         path = self.path
         if relpath:
             path += b'/' + relpath
         striplen = len(self.path) + 1
         l = []
         if self.rawvfs.isdir(path):
             visit = [path]
             readdir = self.rawvfs.readdir
             while visit:
                 p = visit.pop()
                 for f, kind, st in readdir(p, stat=True):
                     fp = p + b'/' + f
                     rl_type = is_revlog(f, kind, st)
                     if rl_type is not None:
                         n = util.pconvert(fp[striplen:])
                         l.append((rl_type, decodedir(n), st.st_size))
                     elif kind == stat.S_IFDIR and recurse:
                         visit.append(fp)
         l.sort()
         return l
 
     def changelog(self, trypending, concurrencychecker=None):
         return changelog.changelog(
             self.vfs,
             trypending=trypending,
             concurrencychecker=concurrencychecker,
         )
 
     def manifestlog(self, repo, storenarrowmatch):
         rootstore = manifest.manifestrevlog(repo.nodeconstants, self.vfs)
         return manifest.manifestlog(self.vfs, repo, rootstore, storenarrowmatch)
 
     def datafiles(
         self, matcher=None, undecodable=None
     ) -> Generator[BaseStoreEntry, None, None]:
         """Like walk, but excluding the changelog and root manifest.
 
         When [undecodable] is None, revlogs names that can't be
         decoded cause an exception. When it is provided, it should
         be a list and the filenames that can't be decoded are added
         to it instead. This is very rarely needed."""
         files = self._walk(b'data', True) + self._walk(b'meta', True)
         for (t, u, s) in files:
             if t is not None:
                 yield RevlogStoreEntry(
                     unencoded_path=u,
                     revlog_type=FILEFLAGS_FILELOG,
                     is_revlog_main=bool(t & FILEFLAGS_REVLOG_MAIN),
                     is_volatile=bool(t & FILEFLAGS_VOLATILE),
                     file_size=s,
                 )
 
     def topfiles(self) -> Generator[BaseStoreEntry, None, None]:
         # yield manifest before changelog
         files = reversed(self._walk(b'', False))
         for (t, u, s) in files:
             if u.startswith(b'00changelog'):
                 yield RevlogStoreEntry(
                     unencoded_path=u,
                     revlog_type=FILEFLAGS_CHANGELOG,
                     is_revlog_main=bool(t & FILEFLAGS_REVLOG_MAIN),
                     is_volatile=bool(t & FILEFLAGS_VOLATILE),
                     file_size=s,
                 )
             elif u.startswith(b'00manifest'):
                 yield RevlogStoreEntry(
                     unencoded_path=u,
                     revlog_type=FILEFLAGS_MANIFESTLOG,
                     is_revlog_main=bool(t & FILEFLAGS_REVLOG_MAIN),
                     is_volatile=bool(t & FILEFLAGS_VOLATILE),
                     file_size=s,
                 )
             else:
                 yield SimpleStoreEntry(
                     unencoded_path=u,
                     is_volatile=bool(t & FILEFLAGS_VOLATILE),
                     file_size=s,
                 )
 
     def walk(self, matcher=None) -> Generator[BaseStoreEntry, None, None]:
         """return files related to data storage (ie: revlogs)
 
         yields (file_type, unencoded, size)
 
         if a matcher is passed, storage files of only those tracked paths
         are passed with matches the matcher
         """
         # yield data files first
         for x in self.datafiles(matcher):
             yield x
         for x in self.topfiles():
             yield x
 
     def copylist(self):
         return _data
 
     def write(self, tr):
         pass
 
     def invalidatecaches(self):
         pass
 
     def markremoved(self, fn):
         pass
 
     def __contains__(self, path):
         '''Checks if the store contains path'''
         path = b"/".join((b"data", path))
         # file?
         if self.vfs.exists(path + b".i"):
             return True
         # dir?
         if not path.endswith(b"/"):
             path = path + b"/"
         return self.vfs.exists(path)
 
 
 class encodedstore(basicstore):
     def __init__(self, path, vfstype):
         vfs = vfstype(path + b'/store')
         self.path = vfs.base
         self.createmode = _calcmode(vfs)
         vfs.createmode = self.createmode
         self.rawvfs = vfs
         self.vfs = vfsmod.filtervfs(vfs, encodefilename)
         self.opener = self.vfs
 
     # note: topfiles would also need a decode phase. It is just that in
     # practice we do not have any file outside of `data/` that needs encoding.
     # However that might change so we should probably add a test and encoding
     # decoding for it too. see issue6548
 
     def datafiles(
         self, matcher=None, undecodable=None
     ) -> Generator[BaseStoreEntry, None, None]:
         for entry in super(encodedstore, self).datafiles():
             try:
                 f1 = entry.unencoded_path
                 f2 = decodefilename(f1)
             except KeyError:
                 if undecodable is None:
                     msg = _(b'undecodable revlog name %s') % f1
                     raise error.StorageError(msg)
                 else:
                     undecodable.append(f1)
                     continue
             if not _matchtrackedpath(f2, matcher):
                 continue
             entry.unencoded_path = f2
             yield entry
 
     def join(self, f):
         return self.path + b'/' + encodefilename(f)
 
     def copylist(self):
         return [b'requires', b'00changelog.i'] + [b'store/' + f for f in _data]
 
 
 class fncache:
     # the filename used to be partially encoded
     # hence the encodedir/decodedir dance
     def __init__(self, vfs):
         self.vfs = vfs
         self._ignores = set()
         self.entries = None
         self._dirty = False
         # set of new additions to fncache
         self.addls = set()
 
     def ensureloaded(self, warn=None):
         """read the fncache file if not already read.
 
         If the file on disk is corrupted, raise. If warn is provided,
         warn and keep going instead."""
         if self.entries is None:
             self._load(warn)
 
     def _load(self, warn=None):
         '''fill the entries from the fncache file'''
         self._dirty = False
         try:
             fp = self.vfs(b'fncache', mode=b'rb')
         except IOError:
             # skip nonexistent file
             self.entries = set()
             return
 
         self.entries = set()
         chunk = b''
         for c in iter(functools.partial(fp.read, fncache_chunksize), b''):
             chunk += c
             try:
                 p = chunk.rindex(b'\n')
                 self.entries.update(decodedir(chunk[: p + 1]).splitlines())
                 chunk = chunk[p + 1 :]
             except ValueError:
                 # substring '\n' not found, maybe the entry is bigger than the
                 # chunksize, so let's keep iterating
                 pass
 
         if chunk:
             msg = _(b"fncache does not ends with a newline")
             if warn:
                 warn(msg + b'\n')
             else:
                 raise error.Abort(
                     msg,
                     hint=_(
                         b"use 'hg debugrebuildfncache' to "
                         b"rebuild the fncache"
                     ),
                 )
         self._checkentries(fp, warn)
         fp.close()
 
     def _checkentries(self, fp, warn):
         """make sure there is no empty string in entries"""
         if b'' in self.entries:
             fp.seek(0)
             for n, line in enumerate(fp):
                 if not line.rstrip(b'\n'):
                     t = _(b'invalid entry in fncache, line %d') % (n + 1)
                     if warn:
                         warn(t + b'\n')
                     else:
                         raise error.Abort(t)
 
     def write(self, tr):
         if self._dirty:
             assert self.entries is not None
             self.entries = self.entries | self.addls
             self.addls = set()
             tr.addbackup(b'fncache')
             fp = self.vfs(b'fncache', mode=b'wb', atomictemp=True)
             if self.entries:
                 fp.write(encodedir(b'\n'.join(self.entries) + b'\n'))
             fp.close()
             self._dirty = False
         if self.addls:
             # if we have just new entries, let's append them to the fncache
             tr.addbackup(b'fncache')
             fp = self.vfs(b'fncache', mode=b'ab', atomictemp=True)
             if self.addls:
                 fp.write(encodedir(b'\n'.join(self.addls) + b'\n'))
             fp.close()
             self.entries = None
             self.addls = set()
 
     def addignore(self, fn):
         self._ignores.add(fn)
 
     def add(self, fn):
         if fn in self._ignores:
             return
         if self.entries is None:
             self._load()
         if fn not in self.entries:
             self.addls.add(fn)
 
     def remove(self, fn):
         if self.entries is None:
             self._load()
         if fn in self.addls:
             self.addls.remove(fn)
             return
         try:
             self.entries.remove(fn)
             self._dirty = True
         except KeyError:
             pass
 
     def __contains__(self, fn):
         if fn in self.addls:
             return True
         if self.entries is None:
             self._load()
         return fn in self.entries
 
     def __iter__(self):
         if self.entries is None:
             self._load()
         return iter(self.entries | self.addls)
 
 
 class _fncachevfs(vfsmod.proxyvfs):
     def __init__(self, vfs, fnc, encode):
         vfsmod.proxyvfs.__init__(self, vfs)
         self.fncache = fnc
         self.encode = encode
 
     def __call__(self, path, mode=b'r', *args, **kw):
         encoded = self.encode(path)
         if (
             mode not in (b'r', b'rb')
             and (path.startswith(b'data/') or path.startswith(b'meta/'))
             and revlog_type(path) is not None
         ):
             # do not trigger a fncache load when adding a file that already is
             # known to exist.
             notload = self.fncache.entries is None and self.vfs.exists(encoded)
             if notload and b'r+' in mode and not self.vfs.stat(encoded).st_size:
                 # when appending to an existing file, if the file has size zero,
                 # it should be considered as missing. Such zero-size files are
                 # the result of truncation when a transaction is aborted.
                 notload = False
             if not notload:
                 self.fncache.add(path)
         return self.vfs(encoded, mode, *args, **kw)
 
     def join(self, path):
         if path:
             return self.vfs.join(self.encode(path))
         else:
             return self.vfs.join(path)
 
     def register_file(self, path):
         """generic hook point to lets fncache steer its stew"""
         if path.startswith(b'data/') or path.startswith(b'meta/'):
             self.fncache.add(path)
 
 
 class fncachestore(basicstore):
     def __init__(self, path, vfstype, dotencode):
         if dotencode:
             encode = _pathencode
         else:
             encode = _plainhybridencode
         self.encode = encode
         vfs = vfstype(path + b'/store')
         self.path = vfs.base
         self.pathsep = self.path + b'/'
         self.createmode = _calcmode(vfs)
         vfs.createmode = self.createmode
         self.rawvfs = vfs
         fnc = fncache(vfs)
         self.fncache = fnc
         self.vfs = _fncachevfs(vfs, fnc, encode)
         self.opener = self.vfs
 
     def join(self, f):
         return self.pathsep + self.encode(f)
 
     def getsize(self, path):
         return self.rawvfs.stat(path).st_size
 
     def datafiles(
         self, matcher=None, undecodable=None
     ) -> Generator[BaseStoreEntry, None, None]:
         for f in sorted(self.fncache):
             if not _matchtrackedpath(f, matcher):
                 continue
             ef = self.encode(f)
             t = revlog_type(f)
             if t is None:
                 # Note: this should not be in the fncache then…
                 #
                 # However the fncache might contains such file added by
                 # previous version of Mercurial.
                 continue
-            try:
-                yield RevlogStoreEntry(
-                    unencoded_path=f,
-                    revlog_type=FILEFLAGS_FILELOG,
-                    is_revlog_main=bool(t & FILEFLAGS_REVLOG_MAIN),
-                    is_volatile=bool(t & FILEFLAGS_VOLATILE),
-                    file_size=self.getsize(ef),
-                )
-            except FileNotFoundError:
-                pass
+            yield RevlogStoreEntry(
+                unencoded_path=f,
+                revlog_type=FILEFLAGS_FILELOG,
+                is_revlog_main=bool(t & FILEFLAGS_REVLOG_MAIN),
+                is_volatile=bool(t & FILEFLAGS_VOLATILE),
+            )
 
     def copylist(self):
         d = (
             b'bookmarks',
             b'narrowspec',
             b'data',
             b'meta',
             b'dh',
             b'fncache',
             b'phaseroots',
             b'obsstore',
             b'00manifest.d',
             b'00manifest.i',
             b'00changelog.d',
             b'00changelog.i',
             b'requires',
         )
         return [b'requires', b'00changelog.i'] + [b'store/' + f for f in d]
 
     def write(self, tr):
         self.fncache.write(tr)
 
     def invalidatecaches(self):
         self.fncache.entries = None
         self.fncache.addls = set()
 
     def markremoved(self, fn):
         self.fncache.remove(fn)
 
     def _exists(self, f):
         ef = self.encode(f)
         try:
             self.getsize(ef)
             return True
         except FileNotFoundError:
             return False
 
     def __contains__(self, path):
         '''Checks if the store contains path'''
         path = b"/".join((b"data", path))
         # check for files (exact match)
         e = path + b'.i'
         if e in self.fncache and self._exists(e):
             return True
         # now check for directories (prefix match)
         if not path.endswith(b'/'):
             path += b'/'
         for e in self.fncache:
             if e.startswith(path) and self._exists(e):
                 return True
         return False

mercurial/streamclone.py

@@ -1,937 +1,939 b''
 # streamclone.py - producing and consuming streaming repository data
 #
 # Copyright 2015 Gregory Szorc <[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 contextlib
 import os
 import struct
 
 from .i18n import _
 from .pycompat import open
 from .interfaces import repository
 from . import (
     bookmarks,
     cacheutil,
     error,
     narrowspec,
     phases,
     pycompat,
     requirements as requirementsmod,
     scmutil,
     store,
     transaction,
     util,
 )
 from .revlogutils import (
     nodemap,
 )
 
 
 def new_stream_clone_requirements(default_requirements, streamed_requirements):
     """determine the final set of requirement for a new stream clone
 
     this method combine the "default" requirements that a new repository would
     use with the constaint we get from the stream clone content. We keep local
     configuration choice when possible.
     """
     requirements = set(default_requirements)
     requirements -= requirementsmod.STREAM_FIXED_REQUIREMENTS
     requirements.update(streamed_requirements)
     return requirements
 
 
 def streamed_requirements(repo):
     """the set of requirement the new clone will have to support
 
     This is used for advertising the stream options and to generate the actual
     stream content."""
     requiredformats = (
         repo.requirements & requirementsmod.STREAM_FIXED_REQUIREMENTS
     )
     return requiredformats
 
 
 def canperformstreamclone(pullop, bundle2=False):
     """Whether it is possible to perform a streaming clone as part of pull.
 
     ``bundle2`` will cause the function to consider stream clone through
     bundle2 and only through bundle2.
 
     Returns a tuple of (supported, requirements). ``supported`` is True if
     streaming clone is supported and False otherwise. ``requirements`` is
     a set of repo requirements from the remote, or ``None`` if stream clone
     isn't supported.
     """
     repo = pullop.repo
     remote = pullop.remote
 
     bundle2supported = False
     if pullop.canusebundle2:
         if b'v2' in pullop.remotebundle2caps.get(b'stream', []):
             bundle2supported = True
         # else
         # Server doesn't support bundle2 stream clone or doesn't support
         # the versions we support. Fall back and possibly allow legacy.
 
     # Ensures legacy code path uses available bundle2.
     if bundle2supported and not bundle2:
         return False, None
     # Ensures bundle2 doesn't try to do a stream clone if it isn't supported.
     elif bundle2 and not bundle2supported:
         return False, None
 
     # Streaming clone only works on empty repositories.
     if len(repo):
         return False, None
 
     # Streaming clone only works if all data is being requested.
     if pullop.heads:
         return False, None
 
     streamrequested = pullop.streamclonerequested
 
     # If we don't have a preference, let the server decide for us. This
     # likely only comes into play in LANs.
     if streamrequested is None:
         # The server can advertise whether to prefer streaming clone.
         streamrequested = remote.capable(b'stream-preferred')
 
     if not streamrequested:
         return False, None
 
     # In order for stream clone to work, the client has to support all the
     # requirements advertised by the server.
     #
     # The server advertises its requirements via the "stream" and "streamreqs"
     # capability. "stream" (a value-less capability) is advertised if and only
     # if the only requirement is "revlogv1." Else, the "streamreqs" capability
     # is advertised and contains a comma-delimited list of requirements.
     requirements = set()
     if remote.capable(b'stream'):
         requirements.add(requirementsmod.REVLOGV1_REQUIREMENT)
     else:
         streamreqs = remote.capable(b'streamreqs')
         # This is weird and shouldn't happen with modern servers.
         if not streamreqs:
             pullop.repo.ui.warn(
                 _(
                     b'warning: stream clone requested but server has them '
                     b'disabled\n'
                 )
             )
             return False, None
 
         streamreqs = set(streamreqs.split(b','))
         # Server requires something we don't support. Bail.
         missingreqs = streamreqs - repo.supported
         if missingreqs:
             pullop.repo.ui.warn(
                 _(
                     b'warning: stream clone requested but client is missing '
                     b'requirements: %s\n'
                 )
                 % b', '.join(sorted(missingreqs))
             )
             pullop.repo.ui.warn(
                 _(
                     b'(see https://www.mercurial-scm.org/wiki/MissingRequirement '
                     b'for more information)\n'
                 )
             )
             return False, None
         requirements = streamreqs
 
     return True, requirements
 
 
 def maybeperformlegacystreamclone(pullop):
     """Possibly perform a legacy stream clone operation.
 
     Legacy stream clones are performed as part of pull but before all other
     operations.
 
     A legacy stream clone will not be performed if a bundle2 stream clone is
     supported.
     """
     from . import localrepo
 
     supported, requirements = canperformstreamclone(pullop)
 
     if not supported:
         return
 
     repo = pullop.repo
     remote = pullop.remote
 
     # Save remote branchmap. We will use it later to speed up branchcache
     # creation.
     rbranchmap = None
     if remote.capable(b'branchmap'):
         with remote.commandexecutor() as e:
             rbranchmap = e.callcommand(b'branchmap', {}).result()
 
     repo.ui.status(_(b'streaming all changes\n'))
 
     with remote.commandexecutor() as e:
         fp = e.callcommand(b'stream_out', {}).result()
 
     # TODO strictly speaking, this code should all be inside the context
     # manager because the context manager is supposed to ensure all wire state
     # is flushed when exiting. But the legacy peers don't do this, so it
     # doesn't matter.
     l = fp.readline()
     try:
         resp = int(l)
     except ValueError:
         raise error.ResponseError(
             _(b'unexpected response from remote server:'), l
         )
     if resp == 1:
         raise error.Abort(_(b'operation forbidden by server'))
     elif resp == 2:
         raise error.Abort(_(b'locking the remote repository failed'))
     elif resp != 0:
         raise error.Abort(_(b'the server sent an unknown error code'))
 
     l = fp.readline()
     try:
         filecount, bytecount = map(int, l.split(b' ', 1))
     except (ValueError, TypeError):
         raise error.ResponseError(
             _(b'unexpected response from remote server:'), l
         )
 
     with repo.lock():
         consumev1(repo, fp, filecount, bytecount)
         repo.requirements = new_stream_clone_requirements(
             repo.requirements,
             requirements,
         )
         repo.svfs.options = localrepo.resolvestorevfsoptions(
             repo.ui, repo.requirements, repo.features
         )
         scmutil.writereporequirements(repo)
         nodemap.post_stream_cleanup(repo)
 
         if rbranchmap:
             repo._branchcaches.replace(repo, rbranchmap)
 
         repo.invalidate()
 
 
 def allowservergeneration(repo):
     """Whether streaming clones are allowed from the server."""
     if repository.REPO_FEATURE_STREAM_CLONE not in repo.features:
         return False
 
     if not repo.ui.configbool(b'server', b'uncompressed', untrusted=True):
         return False
 
     # The way stream clone works makes it impossible to hide secret changesets.
     # So don't allow this by default.
     secret = phases.hassecret(repo)
     if secret:
         return repo.ui.configbool(b'server', b'uncompressedallowsecret')
 
     return True
 
 
 # This is it's own function so extensions can override it.
 def _walkstreamfiles(repo, matcher=None):
     return repo.store.walk(matcher)
 
 
 def generatev1(repo):
     """Emit content for version 1 of a streaming clone.
 
     This returns a 3-tuple of (file count, byte size, data iterator).
 
     The data iterator consists of N entries for each file being transferred.
     Each file entry starts as a line with the file name and integer size
     delimited by a null byte.
 
     The raw file data follows. Following the raw file data is the next file
     entry, or EOF.
 
     When used on the wire protocol, an additional line indicating protocol
     success will be prepended to the stream. This function is not responsible
     for adding it.
 
     This function will obtain a repository lock to ensure a consistent view of
     the store is captured. It therefore may raise LockError.
     """
     entries = []
     total_bytes = 0
     # Get consistent snapshot of repo, lock during scan.
     with repo.lock():
         repo.ui.debug(b'scanning\n')
         for entry in _walkstreamfiles(repo):
             for f in entry.files():
-                if f.file_size:
-                    entries.append((f.unencoded_path, f.file_size))
-                    total_bytes += f.file_size
+                file_size = f.file_size(repo.store.vfs)
+                if file_size:
+                    entries.append((f.unencoded_path, file_size))
+                    total_bytes += file_size
         _test_sync_point_walk_1(repo)
     _test_sync_point_walk_2(repo)
 
     repo.ui.debug(
         b'%d files, %d bytes to transfer\n' % (len(entries), total_bytes)
     )
 
     svfs = repo.svfs
     debugflag = repo.ui.debugflag
 
     def emitrevlogdata():
         for name, size in entries:
             if debugflag:
                 repo.ui.debug(b'sending %s (%d bytes)\n' % (name, size))
             # partially encode name over the wire for backwards compat
             yield b'%s\0%d\n' % (store.encodedir(name), size)
             # auditing at this stage is both pointless (paths are already
             # trusted by the local repo) and expensive
             with svfs(name, b'rb', auditpath=False) as fp:
                 if size <= 65536:
                     yield fp.read(size)
                 else:
                     for chunk in util.filechunkiter(fp, limit=size):
                         yield chunk
 
     return len(entries), total_bytes, emitrevlogdata()
 
 
 def generatev1wireproto(repo):
     """Emit content for version 1 of streaming clone suitable for the wire.
 
     This is the data output from ``generatev1()`` with 2 header lines. The
     first line indicates overall success. The 2nd contains the file count and
     byte size of payload.
 
     The success line contains "0" for success, "1" for stream generation not
     allowed, and "2" for error locking the repository (possibly indicating
     a permissions error for the server process).
     """
     if not allowservergeneration(repo):
         yield b'1\n'
         return
 
     try:
         filecount, bytecount, it = generatev1(repo)
     except error.LockError:
         yield b'2\n'
         return
 
     # Indicates successful response.
     yield b'0\n'
     yield b'%d %d\n' % (filecount, bytecount)
     for chunk in it:
         yield chunk
 
 
 def generatebundlev1(repo, compression=b'UN'):
     """Emit content for version 1 of a stream clone bundle.
 
     The first 4 bytes of the output ("HGS1") denote this as stream clone
     bundle version 1.
 
     The next 2 bytes indicate the compression type. Only "UN" is currently
     supported.
 
     The next 16 bytes are two 64-bit big endian unsigned integers indicating
     file count and byte count, respectively.
 
     The next 2 bytes is a 16-bit big endian unsigned short declaring the length
     of the requirements string, including a trailing \0. The following N bytes
     are the requirements string, which is ASCII containing a comma-delimited
     list of repo requirements that are needed to support the data.
 
     The remaining content is the output of ``generatev1()`` (which may be
     compressed in the future).
 
     Returns a tuple of (requirements, data generator).
     """
     if compression != b'UN':
         raise ValueError(b'we do not support the compression argument yet')
 
     requirements = streamed_requirements(repo)
     requires = b','.join(sorted(requirements))
 
     def gen():
         yield b'HGS1'
         yield compression
 
         filecount, bytecount, it = generatev1(repo)
         repo.ui.status(
             _(b'writing %d bytes for %d files\n') % (bytecount, filecount)
         )
 
         yield struct.pack(b'>QQ', filecount, bytecount)
         yield struct.pack(b'>H', len(requires) + 1)
         yield requires + b'\0'
 
         # This is where we'll add compression in the future.
         assert compression == b'UN'
 
         progress = repo.ui.makeprogress(
             _(b'bundle'), total=bytecount, unit=_(b'bytes')
         )
         progress.update(0)
 
         for chunk in it:
             progress.increment(step=len(chunk))
             yield chunk
 
         progress.complete()
 
     return requirements, gen()
 
 
 def consumev1(repo, fp, filecount, bytecount):
     """Apply the contents from version 1 of a streaming clone file handle.
 
     This takes the output from "stream_out" and applies it to the specified
     repository.
 
     Like "stream_out," the status line added by the wire protocol is not
     handled by this function.
     """
     with repo.lock():
         repo.ui.status(
             _(b'%d files to transfer, %s of data\n')
             % (filecount, util.bytecount(bytecount))
         )
         progress = repo.ui.makeprogress(
             _(b'clone'), total=bytecount, unit=_(b'bytes')
         )
         progress.update(0)
         start = util.timer()
 
         # TODO: get rid of (potential) inconsistency
         #
         # If transaction is started and any @filecache property is
         # changed at this point, it causes inconsistency between
         # in-memory cached property and streamclone-ed file on the
         # disk. Nested transaction prevents transaction scope "clone"
         # below from writing in-memory changes out at the end of it,
         # even though in-memory changes are discarded at the end of it
         # regardless of transaction nesting.
         #
         # But transaction nesting can't be simply prohibited, because
         # nesting occurs also in ordinary case (e.g. enabling
         # clonebundles).
 
         with repo.transaction(b'clone'):
             with repo.svfs.backgroundclosing(repo.ui, expectedcount=filecount):
                 for i in range(filecount):
                     # XXX doesn't support '\n' or '\r' in filenames
                     l = fp.readline()
                     try:
                         name, size = l.split(b'\0', 1)
                         size = int(size)
                     except (ValueError, TypeError):
                         raise error.ResponseError(
                             _(b'unexpected response from remote server:'), l
                         )
                     if repo.ui.debugflag:
                         repo.ui.debug(
                             b'adding %s (%s)\n' % (name, util.bytecount(size))
                         )
                     # for backwards compat, name was partially encoded
                     path = store.decodedir(name)
                     with repo.svfs(path, b'w', backgroundclose=True) as ofp:
                         for chunk in util.filechunkiter(fp, limit=size):
                             progress.increment(step=len(chunk))
                             ofp.write(chunk)
 
             # force @filecache properties to be reloaded from
             # streamclone-ed file at next access
             repo.invalidate(clearfilecache=True)
 
         elapsed = util.timer() - start
         if elapsed <= 0:
             elapsed = 0.001
         progress.complete()
         repo.ui.status(
             _(b'transferred %s in %.1f seconds (%s/sec)\n')
             % (
                 util.bytecount(bytecount),
                 elapsed,
                 util.bytecount(bytecount / elapsed),
             )
         )
 
 
 def readbundle1header(fp):
     compression = fp.read(2)
     if compression != b'UN':
         raise error.Abort(
             _(
                 b'only uncompressed stream clone bundles are '
                 b'supported; got %s'
             )
             % compression
         )
 
     filecount, bytecount = struct.unpack(b'>QQ', fp.read(16))
     requireslen = struct.unpack(b'>H', fp.read(2))[0]
     requires = fp.read(requireslen)
 
     if not requires.endswith(b'\0'):
         raise error.Abort(
             _(
                 b'malformed stream clone bundle: '
                 b'requirements not properly encoded'
             )
         )
 
     requirements = set(requires.rstrip(b'\0').split(b','))
 
     return filecount, bytecount, requirements
 
 
 def applybundlev1(repo, fp):
     """Apply the content from a stream clone bundle version 1.
 
     We assume the 4 byte header has been read and validated and the file handle
     is at the 2 byte compression identifier.
     """
     if len(repo):
         raise error.Abort(
             _(b'cannot apply stream clone bundle on non-empty repo')
         )
 
     filecount, bytecount, requirements = readbundle1header(fp)
     missingreqs = requirements - repo.supported
     if missingreqs:
         raise error.Abort(
             _(b'unable to apply stream clone: unsupported format: %s')
             % b', '.join(sorted(missingreqs))
         )
 
     consumev1(repo, fp, filecount, bytecount)
     nodemap.post_stream_cleanup(repo)
 
 
 class streamcloneapplier:
     """Class to manage applying streaming clone bundles.
 
     We need to wrap ``applybundlev1()`` in a dedicated type to enable bundle
     readers to perform bundle type-specific functionality.
     """
 
     def __init__(self, fh):
         self._fh = fh
 
     def apply(self, repo):
         return applybundlev1(repo, self._fh)
 
 
 # type of file to stream
 _fileappend = 0  # append only file
 _filefull = 1  # full snapshot file
 
 # Source of the file
 _srcstore = b's'  # store (svfs)
 _srccache = b'c'  # cache (cache)
 
 # This is it's own function so extensions can override it.
 def _walkstreamfullstorefiles(repo):
     """list snapshot file from the store"""
     fnames = []
     if not repo.publishing():
         fnames.append(b'phaseroots')
     return fnames
 
 
 def _filterfull(entry, copy, vfsmap):
     """actually copy the snapshot files"""
     src, name, ftype, data = entry
     if ftype != _filefull:
         return entry
     return (src, name, ftype, copy(vfsmap[src].join(name)))
 
 
 @contextlib.contextmanager
 def maketempcopies():
     """return a function to temporary copy file"""
 
     files = []
     dst_dir = pycompat.mkdtemp(prefix=b'hg-clone-')
     try:
 
         def copy(src):
             fd, dst = pycompat.mkstemp(
                 prefix=os.path.basename(src), dir=dst_dir
             )
             os.close(fd)
             files.append(dst)
             util.copyfiles(src, dst, hardlink=True)
             return dst
 
         yield copy
     finally:
         for tmp in files:
             util.tryunlink(tmp)
         util.tryrmdir(dst_dir)
 
 
 def _makemap(repo):
     """make a (src -> vfs) map for the repo"""
     vfsmap = {
         _srcstore: repo.svfs,
         _srccache: repo.cachevfs,
     }
     # we keep repo.vfs out of the on purpose, ther are too many danger there
     # (eg: .hg/hgrc)
     assert repo.vfs not in vfsmap.values()
 
     return vfsmap
 
 
 def _emit2(repo, entries, totalfilesize):
     """actually emit the stream bundle"""
     vfsmap = _makemap(repo)
     # we keep repo.vfs out of the on purpose, ther are too many danger there
     # (eg: .hg/hgrc),
     #
     # this assert is duplicated (from _makemap) as author might think this is
     # fine, while this is really not fine.
     if repo.vfs in vfsmap.values():
         raise error.ProgrammingError(
             b'repo.vfs must not be added to vfsmap for security reasons'
         )
 
     progress = repo.ui.makeprogress(
         _(b'bundle'), total=totalfilesize, unit=_(b'bytes')
     )
     progress.update(0)
     with maketempcopies() as copy, progress:
         # copy is delayed until we are in the try
         entries = [_filterfull(e, copy, vfsmap) for e in entries]
         yield None  # this release the lock on the repository
         totalbytecount = 0
 
         for src, name, ftype, data in entries:
             vfs = vfsmap[src]
             yield src
             yield util.uvarintencode(len(name))
             if ftype == _fileappend:
                 fp = vfs(name)
                 size = data
             elif ftype == _filefull:
                 fp = open(data, b'rb')
                 size = util.fstat(fp).st_size
             bytecount = 0
             try:
                 yield util.uvarintencode(size)
                 yield name
                 if size <= 65536:
                     chunks = (fp.read(size),)
                 else:
                     chunks = util.filechunkiter(fp, limit=size)
                 for chunk in chunks:
                     bytecount += len(chunk)
                     totalbytecount += len(chunk)
                     progress.update(totalbytecount)
                     yield chunk
                 if bytecount != size:
                     # Would most likely be caused by a race due to `hg strip` or
                     # a revlog split
                     raise error.Abort(
                         _(
                             b'clone could only read %d bytes from %s, but '
                             b'expected %d bytes'
                         )
                         % (bytecount, name, size)
                     )
             finally:
                 fp.close()
 
 
 def _test_sync_point_walk_1(repo):
     """a function for synchronisation during tests"""
 
 
 def _test_sync_point_walk_2(repo):
     """a function for synchronisation during tests"""
 
 
 def _v2_walk(repo, includes, excludes, includeobsmarkers):
     """emit a seris of files information useful to clone a repo
 
     return (entries, totalfilesize)
 
     entries is a list of tuple (vfs-key, file-path, file-type, size)
 
     - `vfs-key`: is a key to the right vfs to write the file (see _makemap)
     - `name`: file path of the file to copy (to be feed to the vfss)
     - `file-type`: do this file need to be copied with the source lock ?
     - `size`: the size of the file (or None)
     """
     assert repo._currentlock(repo._lockref) is not None
     entries = []
     totalfilesize = 0
 
     matcher = None
     if includes or excludes:
         matcher = narrowspec.match(repo.root, includes, excludes)
 
     for entry in _walkstreamfiles(repo, matcher):
         for f in entry.files():
-            if f.file_size:
+            file_size = f.file_size(repo.store.vfs)
+            if file_size:
                 ft = _fileappend
                 if f.is_volatile:
                     ft = _filefull
-                entries.append((_srcstore, f.unencoded_path, ft, f.file_size))
-                totalfilesize += f.file_size
+                entries.append((_srcstore, f.unencoded_path, ft, file_size))
+                totalfilesize += file_size
     for name in _walkstreamfullstorefiles(repo):
         if repo.svfs.exists(name):
             totalfilesize += repo.svfs.lstat(name).st_size
             entries.append((_srcstore, name, _filefull, None))
     if includeobsmarkers and repo.svfs.exists(b'obsstore'):
         totalfilesize += repo.svfs.lstat(b'obsstore').st_size
         entries.append((_srcstore, b'obsstore', _filefull, None))
     for name in cacheutil.cachetocopy(repo):
         if repo.cachevfs.exists(name):
             totalfilesize += repo.cachevfs.lstat(name).st_size
             entries.append((_srccache, name, _filefull, None))
     return entries, totalfilesize
 
 
 def generatev2(repo, includes, excludes, includeobsmarkers):
     """Emit content for version 2 of a streaming clone.
 
     the data stream consists the following entries:
     1) A char representing the file destination (eg: store or cache)
     2) A varint containing the length of the filename
     3) A varint containing the length of file data
     4) N bytes containing the filename (the internal, store-agnostic form)
     5) N bytes containing the file data
 
     Returns a 3-tuple of (file count, file size, data iterator).
     """
 
     with repo.lock():
 
         repo.ui.debug(b'scanning\n')
 
         entries, totalfilesize = _v2_walk(
             repo,
             includes=includes,
             excludes=excludes,
             includeobsmarkers=includeobsmarkers,
         )
 
         chunks = _emit2(repo, entries, totalfilesize)
         first = next(chunks)
         assert first is None
         _test_sync_point_walk_1(repo)
     _test_sync_point_walk_2(repo)
 
     return len(entries), totalfilesize, chunks
 
 
 @contextlib.contextmanager
 def nested(*ctxs):
     this = ctxs[0]
     rest = ctxs[1:]
     with this:
         if rest:
             with nested(*rest):
                 yield
         else:
             yield
 
 
 def consumev2(repo, fp, filecount, filesize):
     """Apply the contents from a version 2 streaming clone.
 
     Data is read from an object that only needs to provide a ``read(size)``
     method.
     """
     with repo.lock():
         repo.ui.status(
             _(b'%d files to transfer, %s of data\n')
             % (filecount, util.bytecount(filesize))
         )
 
         start = util.timer()
         progress = repo.ui.makeprogress(
             _(b'clone'), total=filesize, unit=_(b'bytes')
         )
         progress.update(0)
 
         vfsmap = _makemap(repo)
         # we keep repo.vfs out of the on purpose, ther are too many danger
         # there (eg: .hg/hgrc),
         #
         # this assert is duplicated (from _makemap) as author might think this
         # is fine, while this is really not fine.
         if repo.vfs in vfsmap.values():
             raise error.ProgrammingError(
                 b'repo.vfs must not be added to vfsmap for security reasons'
             )
 
         with repo.transaction(b'clone'):
             ctxs = (vfs.backgroundclosing(repo.ui) for vfs in vfsmap.values())
             with nested(*ctxs):
                 for i in range(filecount):
                     src = util.readexactly(fp, 1)
                     vfs = vfsmap[src]
                     namelen = util.uvarintdecodestream(fp)
                     datalen = util.uvarintdecodestream(fp)
 
                     name = util.readexactly(fp, namelen)
 
                     if repo.ui.debugflag:
                         repo.ui.debug(
                             b'adding [%s] %s (%s)\n'
                             % (src, name, util.bytecount(datalen))
                         )
 
                     with vfs(name, b'w') as ofp:
                         for chunk in util.filechunkiter(fp, limit=datalen):
                             progress.increment(step=len(chunk))
                             ofp.write(chunk)
 
             # force @filecache properties to be reloaded from
             # streamclone-ed file at next access
             repo.invalidate(clearfilecache=True)
 
         elapsed = util.timer() - start
         if elapsed <= 0:
             elapsed = 0.001
         repo.ui.status(
             _(b'transferred %s in %.1f seconds (%s/sec)\n')
             % (
                 util.bytecount(progress.pos),
                 elapsed,
                 util.bytecount(progress.pos / elapsed),
             )
         )
         progress.complete()
 
 
 def applybundlev2(repo, fp, filecount, filesize, requirements):
     from . import localrepo
 
     missingreqs = [r for r in requirements if r not in repo.supported]
     if missingreqs:
         raise error.Abort(
             _(b'unable to apply stream clone: unsupported format: %s')
             % b', '.join(sorted(missingreqs))
         )
 
     consumev2(repo, fp, filecount, filesize)
 
     repo.requirements = new_stream_clone_requirements(
         repo.requirements,
         requirements,
     )
     repo.svfs.options = localrepo.resolvestorevfsoptions(
         repo.ui, repo.requirements, repo.features
     )
     scmutil.writereporequirements(repo)
     nodemap.post_stream_cleanup(repo)
 
 
 def _copy_files(src_vfs_map, dst_vfs_map, entries, progress):
     hardlink = [True]
 
     def copy_used():
         hardlink[0] = False
         progress.topic = _(b'copying')
 
     for k, path, size in entries:
         src_vfs = src_vfs_map[k]
         dst_vfs = dst_vfs_map[k]
         src_path = src_vfs.join(path)
         dst_path = dst_vfs.join(path)
         # We cannot use dirname and makedirs of dst_vfs here because the store
         # encoding confuses them. See issue 6581 for details.
         dirname = os.path.dirname(dst_path)
         if not os.path.exists(dirname):
             util.makedirs(dirname)
         dst_vfs.register_file(path)
         # XXX we could use the #nb_bytes argument.
         util.copyfile(
             src_path,
             dst_path,
             hardlink=hardlink[0],
             no_hardlink_cb=copy_used,
             check_fs_hardlink=False,
         )
         progress.increment()
     return hardlink[0]
 
 
 def local_copy(src_repo, dest_repo):
     """copy all content from one local repository to another
 
     This is useful for local clone"""
     src_store_requirements = {
         r
         for r in src_repo.requirements
         if r not in requirementsmod.WORKING_DIR_REQUIREMENTS
     }
     dest_store_requirements = {
         r
         for r in dest_repo.requirements
         if r not in requirementsmod.WORKING_DIR_REQUIREMENTS
     }
     assert src_store_requirements == dest_store_requirements
 
     with dest_repo.lock():
         with src_repo.lock():
 
             # bookmark is not integrated to the streaming as it might use the
             # `repo.vfs` and they are too many sentitive data accessible
             # through `repo.vfs` to expose it to streaming clone.
             src_book_vfs = bookmarks.bookmarksvfs(src_repo)
             srcbookmarks = src_book_vfs.join(b'bookmarks')
             bm_count = 0
             if os.path.exists(srcbookmarks):
                 bm_count = 1
 
             entries, totalfilesize = _v2_walk(
                 src_repo,
                 includes=None,
                 excludes=None,
                 includeobsmarkers=True,
             )
             src_vfs_map = _makemap(src_repo)
             dest_vfs_map = _makemap(dest_repo)
             progress = src_repo.ui.makeprogress(
                 topic=_(b'linking'),
                 total=len(entries) + bm_count,
                 unit=_(b'files'),
             )
             # copy  files
             #
             # We could copy the full file while the source repository is locked
             # and the other one without the lock. However, in the linking case,
             # this would also requires checks that nobody is appending any data
             # to the files while we do the clone, so this is not done yet. We
             # could do this blindly when copying files.
             files = ((k, path, size) for k, path, ftype, size in entries)
             hardlink = _copy_files(src_vfs_map, dest_vfs_map, files, progress)
 
             # copy bookmarks over
             if bm_count:
                 dst_book_vfs = bookmarks.bookmarksvfs(dest_repo)
                 dstbookmarks = dst_book_vfs.join(b'bookmarks')
                 util.copyfile(srcbookmarks, dstbookmarks)
         progress.complete()
         if hardlink:
             msg = b'linked %d files\n'
         else:
             msg = b'copied %d files\n'
         src_repo.ui.debug(msg % (len(entries) + bm_count))
 
         with dest_repo.transaction(b"localclone") as tr:
             dest_repo.store.write(tr)
 
         # clean up transaction file as they do not make sense
         transaction.cleanup_undo_files(dest_repo.ui.warn, dest_repo.vfs_map)

mercurial/verify.py

@@ -1,627 +1,627 b''
 # verify.py - repository integrity checking for Mercurial
 #
 # Copyright 2006, 2007 Olivia Mackall <[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 os
 
 from .i18n import _
 from .node import short
 from .utils import stringutil
 
 from . import (
     error,
     pycompat,
     requirements,
     revlog,
     util,
 )
 
 VERIFY_DEFAULT = 0
 VERIFY_FULL = 1
 
 
 def verify(repo, level=None):
     with repo.lock():
         v = verifier(repo, level)
         return v.verify()
 
 
 def _normpath(f):
     # under hg < 2.4, convert didn't sanitize paths properly, so a
     # converted repo may contain repeated slashes
     while b'//' in f:
         f = f.replace(b'//', b'/')
     return f
 
 
 HINT_FNCACHE = _(
     b'hint: run "hg debugrebuildfncache" to recover from corrupt fncache\n'
 )
 
 WARN_PARENT_DIR_UNKNOWN_REV = _(
     b"parent-directory manifest refers to unknown revision %s"
 )
 
 WARN_UNKNOWN_COPY_SOURCE = _(
     b"warning: copy source of '%s' not in parents of %s"
 )
 
 WARN_NULLID_COPY_SOURCE = _(
     b"warning: %s@%s: copy source revision is nullid %s:%s\n"
 )
 
 
 class verifier:
     def __init__(self, repo, level=None):
         self.repo = repo.unfiltered()
         self.ui = repo.ui
         self.match = repo.narrowmatch()
         if level is None:
             level = VERIFY_DEFAULT
         self._level = level
         self.badrevs = set()
         self.errors = 0
         self.warnings = 0
         self.havecl = len(repo.changelog) > 0
         self.havemf = len(repo.manifestlog.getstorage(b'')) > 0
         self.revlogv1 = repo.changelog._format_version != revlog.REVLOGV0
         self.lrugetctx = util.lrucachefunc(repo.unfiltered().__getitem__)
         self.refersmf = False
         self.fncachewarned = False
         # developer config: verify.skipflags
         self.skipflags = repo.ui.configint(b'verify', b'skipflags')
         self.warnorphanstorefiles = True
 
     def _warn(self, msg):
         """record a "warning" level issue"""
         self.ui.warn(msg + b"\n")
         self.warnings += 1
 
     def _err(self, linkrev, msg, filename=None):
         """record a "error" level issue"""
         if linkrev is not None:
             self.badrevs.add(linkrev)
             linkrev = b"%d" % linkrev
         else:
             linkrev = b'?'
         msg = b"%s: %s" % (linkrev, msg)
         if filename:
             msg = b"%s@%s" % (filename, msg)
         self.ui.warn(b" " + msg + b"\n")
         self.errors += 1
 
     def _exc(self, linkrev, msg, inst, filename=None):
         """record exception raised during the verify process"""
         fmsg = stringutil.forcebytestr(inst)
         if not fmsg:
             fmsg = pycompat.byterepr(inst)
         self._err(linkrev, b"%s: %s" % (msg, fmsg), filename)
 
     def _checkrevlog(self, obj, name, linkrev):
         """verify high level property of a revlog
 
         - revlog is present,
         - revlog is non-empty,
         - sizes (index and data) are correct,
         - revlog's format version is correct.
         """
         if not len(obj) and (self.havecl or self.havemf):
             self._err(linkrev, _(b"empty or missing %s") % name)
             return
 
         d = obj.checksize()
         if d[0]:
             self._err(None, _(b"data length off by %d bytes") % d[0], name)
         if d[1]:
             self._err(None, _(b"index contains %d extra bytes") % d[1], name)
 
         if obj._format_version != revlog.REVLOGV0:
             if not self.revlogv1:
                 self._warn(_(b"warning: `%s' uses revlog format 1") % name)
         elif self.revlogv1:
             self._warn(_(b"warning: `%s' uses revlog format 0") % name)
 
     def _checkentry(self, obj, i, node, seen, linkrevs, f):
         """verify a single revlog entry
 
         arguments are:
         - obj:      the source revlog
         - i:        the revision number
         - node:     the revision node id
         - seen:     nodes previously seen for this revlog
         - linkrevs: [changelog-revisions] introducing "node"
         - f:        string label ("changelog", "manifest", or filename)
 
         Performs the following checks:
         - linkrev points to an existing changelog revision,
         - linkrev points to a changelog revision that introduces this revision,
         - linkrev points to the lowest of these changesets,
         - both parents exist in the revlog,
         - the revision is not duplicated.
 
         Return the linkrev of the revision (or None for changelog's revisions).
         """
         lr = obj.linkrev(obj.rev(node))
         if lr < 0 or (self.havecl and lr not in linkrevs):
             if lr < 0 or lr >= len(self.repo.changelog):
                 msg = _(b"rev %d points to nonexistent changeset %d")
             else:
                 msg = _(b"rev %d points to unexpected changeset %d")
             self._err(None, msg % (i, lr), f)
             if linkrevs:
                 if f and len(linkrevs) > 1:
                     try:
                         # attempt to filter down to real linkrevs
                         linkrevs = []
                         for lr in linkrevs:
                             if self.lrugetctx(lr)[f].filenode() == node:
                                 linkrevs.append(lr)
                     except Exception:
                         pass
                 msg = _(b" (expected %s)")
                 msg %= b" ".join(map(pycompat.bytestr, linkrevs))
                 self._warn(msg)
             lr = None  # can't be trusted
 
         try:
             p1, p2 = obj.parents(node)
             if p1 not in seen and p1 != self.repo.nullid:
                 msg = _(b"unknown parent 1 %s of %s") % (short(p1), short(node))
                 self._err(lr, msg, f)
             if p2 not in seen and p2 != self.repo.nullid:
                 msg = _(b"unknown parent 2 %s of %s") % (short(p2), short(node))
                 self._err(lr, msg, f)
         except Exception as inst:
             self._exc(lr, _(b"checking parents of %s") % short(node), inst, f)
 
         if node in seen:
             self._err(lr, _(b"duplicate revision %d (%d)") % (i, seen[node]), f)
         seen[node] = i
         return lr
 
     def verify(self):
         """verify the content of the Mercurial repository
 
         This method run all verifications, displaying issues as they are found.
 
         return 1 if any error have been encountered, 0 otherwise."""
         # initial validation and generic report
         repo = self.repo
         ui = repo.ui
         if not repo.url().startswith(b'file:'):
             raise error.Abort(_(b"cannot verify bundle or remote repos"))
 
         if os.path.exists(repo.sjoin(b"journal")):
             ui.warn(_(b"abandoned transaction found - run hg recover\n"))
 
         if ui.verbose or not self.revlogv1:
             ui.status(
                 _(b"repository uses revlog format %d\n")
                 % (self.revlogv1 and 1 or 0)
             )
 
         # data verification
         mflinkrevs, filelinkrevs = self._verifychangelog()
         filenodes = self._verifymanifest(mflinkrevs)
         del mflinkrevs
         self._crosscheckfiles(filelinkrevs, filenodes)
         totalfiles, filerevisions = self._verifyfiles(filenodes, filelinkrevs)
 
         if self.errors:
             ui.warn(_(b"not checking dirstate because of previous errors\n"))
             dirstate_errors = 0
         else:
             dirstate_errors = self._verify_dirstate()
 
         # final report
         ui.status(
             _(b"checked %d changesets with %d changes to %d files\n")
             % (len(repo.changelog), filerevisions, totalfiles)
         )
         if self.warnings:
             ui.warn(_(b"%d warnings encountered!\n") % self.warnings)
         if self.fncachewarned:
             ui.warn(HINT_FNCACHE)
         if self.errors:
             ui.warn(_(b"%d integrity errors encountered!\n") % self.errors)
             if self.badrevs:
                 msg = _(b"(first damaged changeset appears to be %d)\n")
                 msg %= min(self.badrevs)
                 ui.warn(msg)
             if dirstate_errors:
                 ui.warn(
                     _(b"dirstate inconsistent with current parent's manifest\n")
                 )
                 ui.warn(_(b"%d dirstate errors\n") % dirstate_errors)
             return 1
         return 0
 
     def _verifychangelog(self):
         """verify the changelog of a repository
 
         The following checks are performed:
         - all of `_checkrevlog` checks,
         - all of `_checkentry` checks (for each revisions),
         - each revision can be read.
 
         The function returns some of the data observed in the changesets as a
         (mflinkrevs, filelinkrevs) tuples:
         - mflinkrevs:   is a { manifest-node -> [changelog-rev] } mapping
         - filelinkrevs: is a { file-path -> [changelog-rev] } mapping
 
         If a matcher was specified, filelinkrevs will only contains matched
         files.
         """
         ui = self.ui
         repo = self.repo
         match = self.match
         cl = repo.changelog
 
         ui.status(_(b"checking changesets\n"))
         mflinkrevs = {}
         filelinkrevs = {}
         seen = {}
         self._checkrevlog(cl, b"changelog", 0)
         progress = ui.makeprogress(
             _(b'checking'), unit=_(b'changesets'), total=len(repo)
         )
         for i in repo:
             progress.update(i)
             n = cl.node(i)
             self._checkentry(cl, i, n, seen, [i], b"changelog")
 
             try:
                 changes = cl.read(n)
                 if changes[0] != self.repo.nullid:
                     mflinkrevs.setdefault(changes[0], []).append(i)
                     self.refersmf = True
                 for f in changes[3]:
                     if match(f):
                         filelinkrevs.setdefault(_normpath(f), []).append(i)
             except Exception as inst:
                 self.refersmf = True
                 self._exc(i, _(b"unpacking changeset %s") % short(n), inst)
         progress.complete()
         return mflinkrevs, filelinkrevs
 
     def _verifymanifest(
         self, mflinkrevs, dir=b"", storefiles=None, subdirprogress=None
     ):
         """verify the manifestlog content
 
         Inputs:
         - mflinkrevs:     a {manifest-node -> [changelog-revisions]} mapping
         - dir:            a subdirectory to check (for tree manifest repo)
         - storefiles:     set of currently "orphan" files.
         - subdirprogress: a progress object
 
         This function checks:
         * all of `_checkrevlog` checks (for all manifest related revlogs)
         * all of `_checkentry` checks (for all manifest related revisions)
         * nodes for subdirectory exists in the sub-directory manifest
         * each manifest entries have a file path
         * each manifest node refered in mflinkrevs exist in the manifest log
 
         If tree manifest is in use and a matchers is specified, only the
         sub-directories matching it will be verified.
 
         return a two level mapping:
             {"path" -> { filenode -> changelog-revision}}
 
         This mapping primarily contains entries for every files in the
         repository. In addition, when tree-manifest is used, it also contains
         sub-directory entries.
 
         If a matcher is provided, only matching paths will be included.
         """
         repo = self.repo
         ui = self.ui
         match = self.match
         mfl = self.repo.manifestlog
         mf = mfl.getstorage(dir)
 
         if not dir:
             self.ui.status(_(b"checking manifests\n"))
 
         filenodes = {}
         subdirnodes = {}
         seen = {}
         label = b"manifest"
         if dir:
             label = dir
             revlogfiles = mf.files()
             storefiles.difference_update(revlogfiles)
             if subdirprogress:  # should be true since we're in a subdirectory
                 subdirprogress.increment()
         if self.refersmf:
             # Do not check manifest if there are only changelog entries with
             # null manifests.
             self._checkrevlog(mf._revlog, label, 0)
         progress = ui.makeprogress(
             _(b'checking'), unit=_(b'manifests'), total=len(mf)
         )
         for i in mf:
             if not dir:
                 progress.update(i)
             n = mf.node(i)
             lr = self._checkentry(mf, i, n, seen, mflinkrevs.get(n, []), label)
             if n in mflinkrevs:
                 del mflinkrevs[n]
             elif dir:
                 msg = _(b"%s not in parent-directory manifest") % short(n)
                 self._err(lr, msg, label)
             else:
                 self._err(lr, _(b"%s not in changesets") % short(n), label)
 
             try:
                 mfdelta = mfl.get(dir, n).readdelta(shallow=True)
                 for f, fn, fl in mfdelta.iterentries():
                     if not f:
                         self._err(lr, _(b"entry without name in manifest"))
                     elif f == b"/dev/null":  # ignore this in very old repos
                         continue
                     fullpath = dir + _normpath(f)
                     if fl == b't':
                         if not match.visitdir(fullpath):
                             continue
                         sdn = subdirnodes.setdefault(fullpath + b'/', {})
                         sdn.setdefault(fn, []).append(lr)
                     else:
                         if not match(fullpath):
                             continue
                         filenodes.setdefault(fullpath, {}).setdefault(fn, lr)
             except Exception as inst:
                 self._exc(lr, _(b"reading delta %s") % short(n), inst, label)
             if self._level >= VERIFY_FULL:
                 try:
                     # Various issues can affect manifest. So we read each full
                     # text from storage. This triggers the checks from the core
                     # code (eg: hash verification, filename are ordered, etc.)
                     mfdelta = mfl.get(dir, n).read()
                 except Exception as inst:
                     msg = _(b"reading full manifest %s") % short(n)
                     self._exc(lr, msg, inst, label)
 
         if not dir:
             progress.complete()
 
         if self.havemf:
             # since we delete entry in `mflinkrevs` during iteration, any
             # remaining entries are "missing". We need to issue errors for them.
             changesetpairs = [(c, m) for m in mflinkrevs for c in mflinkrevs[m]]
             for c, m in sorted(changesetpairs):
                 if dir:
                     self._err(c, WARN_PARENT_DIR_UNKNOWN_REV % short(m), label)
                 else:
                     msg = _(b"changeset refers to unknown revision %s")
                     msg %= short(m)
                     self._err(c, msg, label)
 
         if not dir and subdirnodes:
             self.ui.status(_(b"checking directory manifests\n"))
             storefiles = set()
             subdirs = set()
             revlogv1 = self.revlogv1
             undecodable = []
             for entry in repo.store.datafiles(undecodable=undecodable):
                 for file_ in entry.files():
                     f = file_.unencoded_path
-                    size = file_.file_size
+                    size = file_.file_size(repo.store.vfs)
                     if (size > 0 or not revlogv1) and f.startswith(b'meta/'):
                         storefiles.add(_normpath(f))
                         subdirs.add(os.path.dirname(f))
             for f in undecodable:
                 self._err(None, _(b"cannot decode filename '%s'") % f)
             subdirprogress = ui.makeprogress(
                 _(b'checking'), unit=_(b'manifests'), total=len(subdirs)
             )
 
         for subdir, linkrevs in subdirnodes.items():
             subdirfilenodes = self._verifymanifest(
                 linkrevs, subdir, storefiles, subdirprogress
             )
             for f, onefilenodes in subdirfilenodes.items():
                 filenodes.setdefault(f, {}).update(onefilenodes)
 
         if not dir and subdirnodes:
             assert subdirprogress is not None  # help pytype
             subdirprogress.complete()
             if self.warnorphanstorefiles:
                 for f in sorted(storefiles):
                     self._warn(_(b"warning: orphan data file '%s'") % f)
 
         return filenodes
 
     def _crosscheckfiles(self, filelinkrevs, filenodes):
         repo = self.repo
         ui = self.ui
         ui.status(_(b"crosschecking files in changesets and manifests\n"))
 
         total = len(filelinkrevs) + len(filenodes)
         progress = ui.makeprogress(
             _(b'crosschecking'), unit=_(b'files'), total=total
         )
         if self.havemf:
             for f in sorted(filelinkrevs):
                 progress.increment()
                 if f not in filenodes:
                     lr = filelinkrevs[f][0]
                     self._err(lr, _(b"in changeset but not in manifest"), f)
 
         if self.havecl:
             for f in sorted(filenodes):
                 progress.increment()
                 if f not in filelinkrevs:
                     try:
                         fl = repo.file(f)
                         lr = min([fl.linkrev(fl.rev(n)) for n in filenodes[f]])
                     except Exception:
                         lr = None
                     self._err(lr, _(b"in manifest but not in changeset"), f)
 
         progress.complete()
 
     def _verifyfiles(self, filenodes, filelinkrevs):
         repo = self.repo
         ui = self.ui
         lrugetctx = self.lrugetctx
         revlogv1 = self.revlogv1
         havemf = self.havemf
         ui.status(_(b"checking files\n"))
 
         storefiles = set()
         undecodable = []
         for entry in repo.store.datafiles(undecodable=undecodable):
             for file_ in entry.files():
-                size = file_.file_size
+                size = file_.file_size(repo.store.vfs)
                 f = file_.unencoded_path
                 if (size > 0 or not revlogv1) and f.startswith(b'data/'):
                     storefiles.add(_normpath(f))
         for f in undecodable:
             self._err(None, _(b"cannot decode filename '%s'") % f)
 
         state = {
             # TODO this assumes revlog storage for changelog.
             b'expectedversion': self.repo.changelog._format_version,
             b'skipflags': self.skipflags,
             # experimental config: censor.policy
             b'erroroncensored': ui.config(b'censor', b'policy') == b'abort',
         }
 
         files = sorted(set(filenodes) | set(filelinkrevs))
         revisions = 0
         progress = ui.makeprogress(
             _(b'checking'), unit=_(b'files'), total=len(files)
         )
         for i, f in enumerate(files):
             progress.update(i, item=f)
             try:
                 linkrevs = filelinkrevs[f]
             except KeyError:
                 # in manifest but not in changelog
                 linkrevs = []
 
             if linkrevs:
                 lr = linkrevs[0]
             else:
                 lr = None
 
             try:
                 fl = repo.file(f)
             except error.StorageError as e:
                 self._err(lr, _(b"broken revlog! (%s)") % e, f)
                 continue
 
             for ff in fl.files():
                 try:
                     storefiles.remove(ff)
                 except KeyError:
                     if self.warnorphanstorefiles:
                         msg = _(b" warning: revlog '%s' not in fncache!")
                         self._warn(msg % ff)
                         self.fncachewarned = True
 
             if not len(fl) and (self.havecl or self.havemf):
                 self._err(lr, _(b"empty or missing %s") % f)
             else:
                 # Guard against implementations not setting this.
                 state[b'skipread'] = set()
                 state[b'safe_renamed'] = set()
 
                 for problem in fl.verifyintegrity(state):
                     if problem.node is not None:
                         linkrev = fl.linkrev(fl.rev(problem.node))
                     else:
                         linkrev = None
 
                     if problem.warning:
                         self._warn(problem.warning)
                     elif problem.error:
                         linkrev_msg = linkrev if linkrev is not None else lr
                         self._err(linkrev_msg, problem.error, f)
                     else:
                         raise error.ProgrammingError(
                             b'problem instance does not set warning or error '
                             b'attribute: %s' % problem.msg
                         )
 
             seen = {}
             for i in fl:
                 revisions += 1
                 n = fl.node(i)
                 lr = self._checkentry(fl, i, n, seen, linkrevs, f)
                 if f in filenodes:
                     if havemf and n not in filenodes[f]:
                         self._err(lr, _(b"%s not in manifests") % (short(n)), f)
                     else:
                         del filenodes[f][n]
 
                 if n in state[b'skipread'] and n not in state[b'safe_renamed']:
                     continue
 
                 # check renames
                 try:
                     # This requires resolving fulltext (at least on revlogs,
                     # though not with LFS revisions). We may want
                     # ``verifyintegrity()`` to pass a set of nodes with
                     # rename metadata as an optimization.
                     rp = fl.renamed(n)
                     if rp:
                         if lr is not None and ui.verbose:
                             ctx = lrugetctx(lr)
                             if not any(rp[0] in pctx for pctx in ctx.parents()):
                                 self._warn(WARN_UNKNOWN_COPY_SOURCE % (f, ctx))
                         fl2 = repo.file(rp[0])
                         if not len(fl2):
                             m = _(b"empty or missing copy source revlog %s:%s")
                             self._err(lr, m % (rp[0], short(rp[1])), f)
                         elif rp[1] == self.repo.nullid:
                             msg = WARN_NULLID_COPY_SOURCE
                             msg %= (f, lr, rp[0], short(rp[1]))
                             ui.note(msg)
                         else:
                             fl2.rev(rp[1])
                 except Exception as inst:
                     self._exc(
                         lr, _(b"checking rename of %s") % short(n), inst, f
                     )
 
             # cross-check
             if f in filenodes:
                 fns = [(v, k) for k, v in filenodes[f].items()]
                 for lr, node in sorted(fns):
                     msg = _(b"manifest refers to unknown revision %s")
                     self._err(lr, msg % short(node), f)
         progress.complete()
 
         if self.warnorphanstorefiles:
             for f in sorted(storefiles):
                 self._warn(_(b"warning: orphan data file '%s'") % f)
 
         return len(files), revisions
 
     def _verify_dirstate(self):
         """Check that the dirstate is consistent with the parent's manifest"""
         repo = self.repo
         ui = self.ui
         ui.status(_(b"checking dirstate\n"))
 
         parent1, parent2 = repo.dirstate.parents()
         m1 = repo[parent1].manifest()
         m2 = repo[parent2].manifest()
         dirstate_errors = 0
 
         is_narrow = requirements.NARROW_REQUIREMENT in repo.requirements
         narrow_matcher = repo.narrowmatch() if is_narrow else None
 
         for err in repo.dirstate.verify(m1, m2, parent1, narrow_matcher):
             ui.error(err)
             dirstate_errors += 1
 
         if dirstate_errors:
             self.errors += dirstate_errors
         return dirstate_errors