store: introduce _matchtrackedpath() and use it to filter store files

This patch introduces a function to filter store files on the basis of the path
which they are tracking.

The function assumes that the entries can be of two types, 'meta/*' and 'data/*'
which means it will just work on revlog based storage and not with another
storage ways.

For the 'data/*' entries, we remove the 'data/' part and '.i/.d' part from the
beginning and the end then pass that to matcher.

For the 'meta/*' entries, we remove the 'meta/' and '/00manifest.(i/d)' part from
beginning and end then call matcher.visitdir() with it to make sure all the
parent directories are also downloaded.

Since the storage filtering for narrow stream clones is implemented with this
patch, we remove the un-implemented error message, add some more tests and add
the treemanifest case to tests too.

The tests demonstrate that it works correctly.

After this patch, we have now narrow stream clones working. Narrow stream clones
are a very important feature for large repositories who have good internet
connection because they use streamclones for cloning and if they do normal
narrow clone, that takes more time then a full streamclone. Also narrow-stream
clone will drastically speed up clone timings.

Differential Revision: https://phab.mercurial-scm.org/D5139

mercurial/store.py

@@ -1,591 +1,609
 # store.py - repository store handling for Mercurial
 #
 # Copyright 2008 Matt 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.
 
 from __future__ import absolute_import
 
 import errno
 import hashlib
 import os
 import stat
 
 from .i18n import _
 from . import (
     error,
     node,
     policy,
     pycompat,
     util,
     vfs as vfsmod,
 )
 
 parsers = policy.importmod(r'parsers')
 
+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('data/'):
+        return matcher(path[len('data/'):-len('.i')])
+    elif path.startswith('meta/'):
+        return matcher.visitdir(path[len('meta/'):-len('/00manifest.i')] or '.')
+
 # 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(".hg/", ".hg.hg/")
             .replace(".i/", ".i.hg/")
             .replace(".d/", ".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 ".hg/" not in path:
         return path
     return (path
             .replace(".d.hg/", ".d/")
             .replace(".i.hg/", ".i/")
             .replace(".hg.hg/", ".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 = '_'
     xchr = pycompat.bytechr
     asciistr = list(map(xchr, range(127)))
     capitals = list(range(ord("A"), ord("Z") + 1))
 
     cmap = dict((x, x) for x in asciistr)
     for x in _reserved():
         cmap[xchr(x)] = "~%02x" % x
     for x in capitals + [ord(e)]:
         cmap[xchr(x)] = e + xchr(x).lower()
 
     dmap = {}
     for k, v in cmap.iteritems():
         dmap[v] = k
     def decode(s):
         i = 0
         while i < len(s):
             for l in pycompat.xrange(1, 4):
                 try:
                     yield dmap[s[i:i + l]]
                     i += l
                     break
                 except KeyError:
                     pass
             else:
                 raise KeyError
     return (lambda s: ''.join([cmap[s[c:c + 1]]
                                for c in pycompat.xrange(len(s))]),
             lambda s: ''.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 = dict([(xchr(x), xchr(x)) for x in pycompat.xrange(127)])
     for x in _reserved():
         cmap[xchr(x)] = "~%02x" % x
     for x in range(ord("A"), ord("Z") + 1):
         cmap[xchr(x)] = xchr(x).lower()
     def lowerencode(s):
         return "".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 = ('aux', 'con', 'prn', 'nul') # length 3
 _winres4 = ('com', '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 '. ':
             n = "~%02x" % ord(n[0:1]) + n[1:]
             path[i] = n
         else:
             l = n.find('.')
             if l == -1:
                 l = len(n)
             if ((l == 3 and n[:3] in _winres3) or
                 (l == 4 and n[3:4] <= '9' and n[3:4] >= '1'
                         and n[:3] in _winres4)):
                 # encode third letter ('aux' -> 'au~78')
                 ec = "~%02x" % ord(n[2:3])
                 n = n[0:2] + ec + n[3:]
                 path[i] = n
         if n[-1] in '. ':
             # encode last period or space ('foo...' -> 'foo..~2e')
             path[i] = n[:-1] + "~%02x" % ord(n[-1:])
     return path
 
 _maxstorepathlen = 120
 _dirprefixlen = 8
 _maxshortdirslen = 8 * (_dirprefixlen + 1) - 4
 
 def _hashencode(path, dotencode):
     digest = node.hex(hashlib.sha1(path).digest())
     le = lowerencode(path[5:]).split('/') # 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 '. ':
             # Windows can't access dirs ending in period or space
             d = d[:-1] + '_'
         if sdirslen == 0:
             t = len(d)
         else:
             t = sdirslen + 1 + len(d)
             if t > _maxshortdirslen:
                 break
         sdirs.append(d)
         sdirslen = t
     dirs = '/'.join(sdirs)
     if len(dirs) > 0:
         dirs += '/'
     res = 'dh/' + dirs + digest + ext
     spaceleft = _maxstorepathlen - len(res)
     if spaceleft > 0:
         filler = basename[:spaceleft]
         res = '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('/')
     res = '/'.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('/')
     res = '/'.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 = ('narrowspec data meta 00manifest.d 00manifest.i'
          ' 00changelog.d 00changelog.i phaseroots obsstore')
 
 def isrevlog(f, kind, st):
     return kind == stat.S_IFREG and f[-2:] in ('.i', '.d')
 
 class basicstore(object):
     '''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 + '/' + encodedir(f)
 
     def _walk(self, relpath, recurse, filefilter=isrevlog):
         '''yields (unencoded, encoded, size)'''
         path = self.path
         if relpath:
             path += '/' + 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 + '/' + f
                     if filefilter(f, kind, st):
                         n = util.pconvert(fp[striplen:])
                         l.append((decodedir(n), n, st.st_size))
                     elif kind == stat.S_IFDIR and recurse:
                         visit.append(fp)
         l.sort()
         return l
 
     def datafiles(self, matcher=None):
         return self._walk('data', True) + self._walk('meta', True)
 
     def topfiles(self):
         # yield manifest before changelog
         return reversed(self._walk('', False))
 
     def walk(self, matcher=None):
         '''yields (unencoded, encoded, 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 ['requires'] + _data.split()
 
     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 = "/".join(("data", path))
         # file?
         if self.vfs.exists(path + ".i"):
             return True
         # dir?
         if not path.endswith("/"):
             path = path + "/"
         return self.vfs.exists(path)
 
 class encodedstore(basicstore):
     def __init__(self, path, vfstype):
         vfs = vfstype(path + '/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
 
     def datafiles(self, matcher=None):
         for a, b, size in super(encodedstore, self).datafiles():
+            if not _matchtrackedpath(a, matcher):
+                continue
             try:
                 a = decodefilename(a)
             except KeyError:
                 a = None
             yield a, b, size
 
     def join(self, f):
         return self.path + '/' + encodefilename(f)
 
     def copylist(self):
         return (['requires', '00changelog.i'] +
                 ['store/' + f for f in _data.split()])
 
 class fncache(object):
     # the filename used to be partially encoded
     # hence the encodedir/decodedir dance
     def __init__(self, vfs):
         self.vfs = vfs
         self.entries = None
         self._dirty = False
 
     def _load(self):
         '''fill the entries from the fncache file'''
         self._dirty = False
         try:
             fp = self.vfs('fncache', mode='rb')
         except IOError:
             # skip nonexistent file
             self.entries = set()
             return
         self.entries = set(decodedir(fp.read()).splitlines())
         if '' in self.entries:
             fp.seek(0)
             for n, line in enumerate(util.iterfile(fp)):
                 if not line.rstrip('\n'):
                     t = _('invalid entry in fncache, line %d') % (n + 1)
                     raise error.Abort(t)
         fp.close()
 
     def write(self, tr):
         if self._dirty:
             assert self.entries is not None
             tr.addbackup('fncache')
             fp = self.vfs('fncache', mode='wb', atomictemp=True)
             if self.entries:
                 fp.write(encodedir('\n'.join(self.entries) + '\n'))
             fp.close()
             self._dirty = False
 
     def add(self, fn):
         if self.entries is None:
             self._load()
         if fn not in self.entries:
             self._dirty = True
             self.entries.add(fn)
 
     def remove(self, fn):
         if self.entries is None:
             self._load()
         try:
             self.entries.remove(fn)
             self._dirty = True
         except KeyError:
             pass
 
     def __contains__(self, fn):
         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)
 
 class _fncachevfs(vfsmod.abstractvfs, vfsmod.proxyvfs):
     def __init__(self, vfs, fnc, encode):
         vfsmod.proxyvfs.__init__(self, vfs)
         self.fncache = fnc
         self.encode = encode
 
     def __call__(self, path, mode='r', *args, **kw):
         encoded = self.encode(path)
         if mode not in ('r', 'rb') and (path.startswith('data/') or
                                         path.startswith('meta/')):
             # 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 'a' 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)
 
 class fncachestore(basicstore):
     def __init__(self, path, vfstype, dotencode):
         if dotencode:
             encode = _pathencode
         else:
             encode = _plainhybridencode
         self.encode = encode
         vfs = vfstype(path + '/store')
         self.path = vfs.base
         self.pathsep = self.path + '/'
         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):
         for f in sorted(self.fncache):
+            if not _matchtrackedpath(f, matcher):
+                continue
             ef = self.encode(f)
             try:
                 yield f, ef, self.getsize(ef)
             except OSError as err:
                 if err.errno != errno.ENOENT:
                     raise
 
     def copylist(self):
         d = ('narrowspec data meta dh fncache phaseroots obsstore'
              ' 00manifest.d 00manifest.i 00changelog.d 00changelog.i')
         return (['requires', '00changelog.i'] +
                 ['store/' + f for f in d.split()])
 
     def write(self, tr):
         self.fncache.write(tr)
 
     def invalidatecaches(self):
         self.fncache.entries = None
 
     def markremoved(self, fn):
         self.fncache.remove(fn)
 
     def _exists(self, f):
         ef = self.encode(f)
         try:
             self.getsize(ef)
             return True
         except OSError as err:
             if err.errno != errno.ENOENT:
                 raise
             # nonexistent entry
             return False
 
     def __contains__(self, path):
         '''Checks if the store contains path'''
         path = "/".join(("data", path))
         # check for files (exact match)
         e = path + '.i'
         if e in self.fncache and self._exists(e):
             return True
         # now check for directories (prefix match)
         if not path.endswith('/'):
             path += '/'
         for e in self.fncache:
             if e.startswith(path) and self._exists(e):
                 return True
         return False

mercurial/streamclone.py

@@ -1,663 +1,659
 # 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.
 
 from __future__ import absolute_import
 
 import contextlib
 import os
 import struct
 
 from .i18n import _
 from . import (
     branchmap,
     cacheutil,
     error,
     narrowspec,
     phases,
     pycompat,
     repository,
     store,
     util,
 )
 
 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 'v2' in pullop.remotebundle2caps.get('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('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('stream'):
         requirements.add('revlogv1')
     else:
         streamreqs = remote.capable('streamreqs')
         # This is weird and shouldn't happen with modern servers.
         if not streamreqs:
             pullop.repo.ui.warn(_(
                 'warning: stream clone requested but server has them '
                 'disabled\n'))
             return False, None
 
         streamreqs = set(streamreqs.split(','))
         # Server requires something we don't support. Bail.
         missingreqs = streamreqs - repo.supportedformats
         if missingreqs:
             pullop.repo.ui.warn(_(
                 'warning: stream clone requested but client is missing '
                 'requirements: %s\n') % ', '.join(sorted(missingreqs)))
             pullop.repo.ui.warn(
                 _('(see https://www.mercurial-scm.org/wiki/MissingRequirement '
                   '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('branchmap'):
         with remote.commandexecutor() as e:
             rbranchmap = e.callcommand('branchmap', {}).result()
 
     repo.ui.status(_('streaming all changes\n'))
 
     with remote.commandexecutor() as e:
         fp = e.callcommand('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(
             _('unexpected response from remote server:'), l)
     if resp == 1:
         raise error.Abort(_('operation forbidden by server'))
     elif resp == 2:
         raise error.Abort(_('locking the remote repository failed'))
     elif resp != 0:
         raise error.Abort(_('the server sent an unknown error code'))
 
     l = fp.readline()
     try:
         filecount, bytecount = map(int, l.split(' ', 1))
     except (ValueError, TypeError):
         raise error.ResponseError(
             _('unexpected response from remote server:'), l)
 
     with repo.lock():
         consumev1(repo, fp, filecount, bytecount)
 
         # new requirements = old non-format requirements +
         #                    new format-related remote requirements
         # requirements from the streamed-in repository
         repo.requirements = requirements | (
                 repo.requirements - repo.supportedformats)
         repo.svfs.options = localrepo.resolvestorevfsoptions(
             repo.ui, repo.requirements, repo.features)
         repo._writerequirements()
 
         if rbranchmap:
             branchmap.replacecache(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('server', '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('server', '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('scanning\n')
         for name, ename, size in _walkstreamfiles(repo):
             if size:
                 entries.append((name, size))
                 total_bytes += size
 
     repo.ui.debug('%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('sending %s (%d bytes)\n' % (name, size))
             # partially encode name over the wire for backwards compat
             yield '%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, '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 '1\n'
         return
 
     try:
         filecount, bytecount, it = generatev1(repo)
     except error.LockError:
         yield '2\n'
         return
 
     # Indicates successful response.
     yield '0\n'
     yield '%d %d\n' % (filecount, bytecount)
     for chunk in it:
         yield chunk
 
 def generatebundlev1(repo, compression='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 != 'UN':
         raise ValueError('we do not support the compression argument yet')
 
     requirements = repo.requirements & repo.supportedformats
     requires = ','.join(sorted(requirements))
 
     def gen():
         yield 'HGS1'
         yield compression
 
         filecount, bytecount, it = generatev1(repo)
         repo.ui.status(_('writing %d bytes for %d files\n') %
                          (bytecount, filecount))
 
         yield struct.pack('>QQ', filecount, bytecount)
         yield struct.pack('>H', len(requires) + 1)
         yield requires + '\0'
 
         # This is where we'll add compression in the future.
         assert compression == 'UN'
 
         progress = repo.ui.makeprogress(_('bundle'), total=bytecount,
                                         unit=_('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(_('%d files to transfer, %s of data\n') %
                        (filecount, util.bytecount(bytecount)))
         progress = repo.ui.makeprogress(_('clone'), total=bytecount,
                                         unit=_('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('clone'):
             with repo.svfs.backgroundclosing(repo.ui, expectedcount=filecount):
                 for i in pycompat.xrange(filecount):
                     # XXX doesn't support '\n' or '\r' in filenames
                     l = fp.readline()
                     try:
                         name, size = l.split('\0', 1)
                         size = int(size)
                     except (ValueError, TypeError):
                         raise error.ResponseError(
                             _('unexpected response from remote server:'), l)
                     if repo.ui.debugflag:
                         repo.ui.debug('adding %s (%s)\n' %
                                       (name, util.bytecount(size)))
                     # for backwards compat, name was partially encoded
                     path = store.decodedir(name)
                     with repo.svfs(path, '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(_('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 != 'UN':
         raise error.Abort(_('only uncompressed stream clone bundles are '
             'supported; got %s') % compression)
 
     filecount, bytecount = struct.unpack('>QQ', fp.read(16))
     requireslen = struct.unpack('>H', fp.read(2))[0]
     requires = fp.read(requireslen)
 
     if not requires.endswith('\0'):
         raise error.Abort(_('malformed stream clone bundle: '
                             'requirements not properly encoded'))
 
     requirements = set(requires.rstrip('\0').split(','))
 
     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(_('cannot apply stream clone bundle on non-empty '
                             'repo'))
 
     filecount, bytecount, requirements = readbundle1header(fp)
     missingreqs = requirements - repo.supportedformats
     if missingreqs:
         raise error.Abort(_('unable to apply stream clone: '
                             'unsupported format: %s') %
                             ', '.join(sorted(missingreqs)))
 
     consumev1(repo, fp, filecount, bytecount)
 
 class streamcloneapplier(object):
     """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 = 's' # store (svfs)
 _srccache = '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('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 = []
     try:
         def copy(src):
             fd, dst = pycompat.mkstemp()
             os.close(fd)
             files.append(dst)
             util.copyfiles(src, dst, hardlink=True)
             return dst
         yield copy
     finally:
         for tmp in files:
             util.tryunlink(tmp)
 
 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)
     progress = repo.ui.makeprogress(_('bundle'), total=totalfilesize,
                                     unit=_('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
         seen = 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, 'rb')
                 size = util.fstat(fp).st_size
             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:
                     seen += len(chunk)
                     progress.update(seen)
                     yield chunk
             finally:
                 fp.close()
 
 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).
     """
 
-    # temporarily raise error until we add storage level logic
-    if includes or excludes:
-        raise error.Abort(_("server does not support narrow stream clones"))
-
     with repo.lock():
 
         entries = []
         totalfilesize = 0
 
         matcher = None
         if includes or excludes:
             matcher = narrowspec.match(repo.root, includes, excludes)
 
         repo.ui.debug('scanning\n')
         for name, ename, size in _walkstreamfiles(repo, matcher):
             if size:
                 entries.append((_srcstore, name, _fileappend, size))
                 totalfilesize += 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('obsstore'):
             totalfilesize += repo.svfs.lstat('obsstore').st_size
             entries.append((_srcstore, '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))
 
         chunks = _emit2(repo, entries, totalfilesize)
         first = next(chunks)
         assert first is None
 
     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(_('%d files to transfer, %s of data\n') %
                        (filecount, util.bytecount(filesize)))
 
         start = util.timer()
         progress = repo.ui.makeprogress(_('clone'), total=filesize,
                                         unit=_('bytes'))
         progress.update(0)
 
         vfsmap = _makemap(repo)
 
         with repo.transaction('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('adding [%s] %s (%s)\n' %
                                       (src, name, util.bytecount(datalen)))
 
                     with vfs(name, '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(_('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(_('unable to apply stream clone: '
                             'unsupported format: %s') %
                           ', '.join(sorted(missingreqs)))
 
     consumev2(repo, fp, filecount, filesize)
 
     # new requirements = old non-format requirements +
     #                    new format-related remote requirements
     # requirements from the streamed-in repository
     repo.requirements = set(requirements) | (
             repo.requirements - repo.supportedformats)
     repo.svfs.options = localrepo.resolvestorevfsoptions(
         repo.ui, repo.requirements, repo.features)
     repo._writerequirements()

tests/test-narrow-clone-stream.t

@@ -1,39 +1,86
+#testcases tree flat
+
 Tests narrow stream clones
 
   $ . "$TESTDIR/narrow-library.sh"
 
+#if tree
+  $ cat << EOF >> $HGRCPATH
+  > [experimental]
+  > treemanifest = 1
+  > EOF
+#endif
+
 Server setup
 
   $ hg init master
   $ cd master
   $ mkdir dir
   $ mkdir dir/src
   $ cd dir/src
   $ for x in `$TESTDIR/seq.py 20`; do echo $x > "f$x"; hg add "f$x"; hg commit -m "Commit src $x"; done
 
   $ cd ..
   $ mkdir tests
   $ cd tests
   $ for x in `$TESTDIR/seq.py 20`; do echo $x > "f$x"; hg add "f$x"; hg commit -m "Commit src $x"; done
   $ cd ../../..
 
 Trying to stream clone when the server does not support it
 
   $ hg clone --narrow ssh://user@dummy/master narrow --noupdate --include "dir/src/f10" --stream
   streaming all changes
   remote: abort: server does not support narrow stream clones
   abort: pull failed on remote
   [255]
 
 Enable stream clone on the server
 
-  $ echo "[server]" >> master/.hg/hgrc
+  $ echo "[experimental.server]" >> master/.hg/hgrc
   $ echo "stream-narrow-clones=True" >> master/.hg/hgrc
 
 Cloning a specific file when stream clone is supported
 
   $ hg clone --narrow ssh://user@dummy/master narrow --noupdate --include "dir/src/f10" --stream
   streaming all changes
-  remote: abort: server does not support narrow stream clones
-  abort: pull failed on remote
-  [255]
+  * files to transfer, * KB of data (glob)
+  transferred * KB in * seconds (* */sec) (glob)
+
+  $ cd narrow
+  $ ls
+  $ hg tracked
+  I path:dir/src/f10
+
+Making sure we have the correct set of requirements
+
+  $ cat .hg/requires
+  dotencode
+  fncache
+  generaldelta
+  narrowhg-experimental
+  revlogv1
+  store
+  treemanifest (tree !)
+
+Making sure store has the required files
+
+  $ ls .hg/store/
+  00changelog.i
+  00manifest.i
+  data
+  fncache
+  meta (tree !)
+  narrowspec
+  undo
+  undo.backupfiles
+  undo.phaseroots
+
+Checking that repository has all the required data and not broken
+
+  $ hg verify
+  checking changesets
+  checking manifests
+  checking directory manifests (tree !)
+  crosschecking files in changesets and manifests
+  checking files
+  checked 40 changesets with 1 changes to 1 files