match: delete unused root and cwd arguments from {always,never,exact}() (API)

Differential Revision: https://phab.mercurial-scm.org/D5930

hgext/fsmonitor/__init__.py

@@ -1,828 +1,828 b''
 # __init__.py - fsmonitor initialization and overrides
 #
 # Copyright 2013-2016 Facebook, Inc.
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 '''Faster status operations with the Watchman file monitor (EXPERIMENTAL)
 
 Integrates the file-watching program Watchman with Mercurial to produce faster
 status results.
 
 On a particular Linux system, for a real-world repository with over 400,000
 files hosted on ext4, vanilla `hg status` takes 1.3 seconds. On the same
 system, with fsmonitor it takes about 0.3 seconds.
 
 fsmonitor requires no configuration -- it will tell Watchman about your
 repository as necessary. You'll need to install Watchman from
 https://facebook.github.io/watchman/ and make sure it is in your PATH.
 
 fsmonitor is incompatible with the largefiles and eol extensions, and
 will disable itself if any of those are active.
 
 The following configuration options exist:
 
 ::
 
     [fsmonitor]
     mode = {off, on, paranoid}
 
 When `mode = off`, fsmonitor will disable itself (similar to not loading the
 extension at all). When `mode = on`, fsmonitor will be enabled (the default).
 When `mode = paranoid`, fsmonitor will query both Watchman and the filesystem,
 and ensure that the results are consistent.
 
 ::
 
     [fsmonitor]
     timeout = (float)
 
 A value, in seconds, that determines how long fsmonitor will wait for Watchman
 to return results. Defaults to `2.0`.
 
 ::
 
     [fsmonitor]
     blacklistusers = (list of userids)
 
 A list of usernames for which fsmonitor will disable itself altogether.
 
 ::
 
     [fsmonitor]
     walk_on_invalidate = (boolean)
 
 Whether or not to walk the whole repo ourselves when our cached state has been
 invalidated, for example when Watchman has been restarted or .hgignore rules
 have been changed. Walking the repo in that case can result in competing for
 I/O with Watchman. For large repos it is recommended to set this value to
 false. You may wish to set this to true if you have a very fast filesystem
 that can outpace the IPC overhead of getting the result data for the full repo
 from Watchman. Defaults to false.
 
 ::
 
     [fsmonitor]
     warn_when_unused = (boolean)
 
 Whether to print a warning during certain operations when fsmonitor would be
 beneficial to performance but isn't enabled.
 
 ::
 
     [fsmonitor]
     warn_update_file_count = (integer)
 
 If ``warn_when_unused`` is set and fsmonitor isn't enabled, a warning will
 be printed during working directory updates if this many files will be
 created.
 '''
 
 # Platforms Supported
 # ===================
 #
 # **Linux:** *Stable*. Watchman and fsmonitor are both known to work reliably,
 #   even under severe loads.
 #
 # **Mac OS X:** *Stable*. The Mercurial test suite passes with fsmonitor
 #   turned on, on case-insensitive HFS+. There has been a reasonable amount of
 #   user testing under normal loads.
 #
 # **Solaris, BSD:** *Alpha*. watchman and fsmonitor are believed to work, but
 #   very little testing has been done.
 #
 # **Windows:** *Alpha*. Not in a release version of watchman or fsmonitor yet.
 #
 # Known Issues
 # ============
 #
 # * fsmonitor will disable itself if any of the following extensions are
 #   enabled: largefiles, inotify, eol; or if the repository has subrepos.
 # * fsmonitor will produce incorrect results if nested repos that are not
 #   subrepos exist. *Workaround*: add nested repo paths to your `.hgignore`.
 #
 # The issues related to nested repos and subrepos are probably not fundamental
 # ones. Patches to fix them are welcome.
 
 from __future__ import absolute_import
 
 import codecs
 import hashlib
 import os
 import stat
 import sys
 import weakref
 
 from mercurial.i18n import _
 from mercurial.node import (
     hex,
 )
 
 from mercurial import (
     context,
     encoding,
     error,
     extensions,
     localrepo,
     merge,
     pathutil,
     pycompat,
     registrar,
     scmutil,
     util,
 )
 from mercurial import match as matchmod
 
 from . import (
     pywatchman,
     state,
     watchmanclient,
 )
 
 # Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
 # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
 # be specifying the version(s) of Mercurial they are tested with, or
 # leave the attribute unspecified.
 testedwith = 'ships-with-hg-core'
 
 configtable = {}
 configitem = registrar.configitem(configtable)
 
 configitem('fsmonitor', 'mode',
     default='on',
 )
 configitem('fsmonitor', 'walk_on_invalidate',
     default=False,
 )
 configitem('fsmonitor', 'timeout',
     default='2',
 )
 configitem('fsmonitor', 'blacklistusers',
     default=list,
 )
 configitem('fsmonitor', 'verbose',
     default=True,
 )
 configitem('experimental', 'fsmonitor.transaction_notify',
     default=False,
 )
 
 # This extension is incompatible with the following blacklisted extensions
 # and will disable itself when encountering one of these:
 _blacklist = ['largefiles', 'eol']
 
 def _handleunavailable(ui, state, ex):
     """Exception handler for Watchman interaction exceptions"""
     if isinstance(ex, watchmanclient.Unavailable):
         # experimental config: fsmonitor.verbose
         if ex.warn and ui.configbool('fsmonitor', 'verbose'):
             ui.warn(str(ex) + '\n')
         if ex.invalidate:
             state.invalidate()
         # experimental config: fsmonitor.verbose
         if ui.configbool('fsmonitor', 'verbose'):
             ui.log('fsmonitor', 'Watchman unavailable: %s\n', ex.msg)
     else:
         ui.log('fsmonitor', 'Watchman exception: %s\n', ex)
 
 def _hashignore(ignore):
     """Calculate hash for ignore patterns and filenames
 
     If this information changes between Mercurial invocations, we can't
     rely on Watchman information anymore and have to re-scan the working
     copy.
 
     """
     sha1 = hashlib.sha1()
     sha1.update(repr(ignore))
     return sha1.hexdigest()
 
 _watchmanencoding = pywatchman.encoding.get_local_encoding()
 _fsencoding = sys.getfilesystemencoding() or sys.getdefaultencoding()
 _fixencoding = codecs.lookup(_watchmanencoding) != codecs.lookup(_fsencoding)
 
 def _watchmantofsencoding(path):
     """Fix path to match watchman and local filesystem encoding
 
     watchman's paths encoding can differ from filesystem encoding. For example,
     on Windows, it's always utf-8.
     """
     try:
         decoded = path.decode(_watchmanencoding)
     except UnicodeDecodeError as e:
         raise error.Abort(str(e), hint='watchman encoding error')
 
     try:
         encoded = decoded.encode(_fsencoding, 'strict')
     except UnicodeEncodeError as e:
         raise error.Abort(str(e))
 
     return encoded
 
 def overridewalk(orig, self, match, subrepos, unknown, ignored, full=True):
     '''Replacement for dirstate.walk, hooking into Watchman.
 
     Whenever full is False, ignored is False, and the Watchman client is
     available, use Watchman combined with saved state to possibly return only a
     subset of files.'''
     def bail(reason):
         self._ui.debug('fsmonitor: fallback to core status, %s\n' % reason)
         return orig(match, subrepos, unknown, ignored, full=True)
 
     if full:
         return bail('full rewalk requested')
     if ignored:
         return bail('listing ignored files')
     if not self._watchmanclient.available():
         return bail('client unavailable')
     state = self._fsmonitorstate
     clock, ignorehash, notefiles = state.get()
     if not clock:
         if state.walk_on_invalidate:
             return bail('no clock')
         # Initial NULL clock value, see
         # https://facebook.github.io/watchman/docs/clockspec.html
         clock = 'c:0:0'
         notefiles = []
 
     ignore = self._ignore
     dirignore = self._dirignore
     if unknown:
         if _hashignore(ignore) != ignorehash and clock != 'c:0:0':
             # ignore list changed -- can't rely on Watchman state any more
             if state.walk_on_invalidate:
                 return bail('ignore rules changed')
             notefiles = []
             clock = 'c:0:0'
     else:
         # always ignore
         ignore = util.always
         dirignore = util.always
 
     matchfn = match.matchfn
     matchalways = match.always()
     dmap = self._map
     if util.safehasattr(dmap, '_map'):
         # for better performance, directly access the inner dirstate map if the
         # standard dirstate implementation is in use.
         dmap = dmap._map
     nonnormalset = self._map.nonnormalset
 
     copymap = self._map.copymap
     getkind = stat.S_IFMT
     dirkind = stat.S_IFDIR
     regkind = stat.S_IFREG
     lnkkind = stat.S_IFLNK
     join = self._join
     normcase = util.normcase
     fresh_instance = False
 
     exact = skipstep3 = False
     if match.isexact():  # match.exact
         exact = True
         dirignore = util.always  # skip step 2
     elif match.prefix():  # match.match, no patterns
         skipstep3 = True
 
     if not exact and self._checkcase:
         # note that even though we could receive directory entries, we're only
         # interested in checking if a file with the same name exists. So only
         # normalize files if possible.
         normalize = self._normalizefile
         skipstep3 = False
     else:
         normalize = None
 
     # step 1: find all explicit files
     results, work, dirsnotfound = self._walkexplicit(match, subrepos)
 
     skipstep3 = skipstep3 and not (work or dirsnotfound)
     work = [d for d in work if not dirignore(d[0])]
 
     if not work and (exact or skipstep3):
         for s in subrepos:
             del results[s]
         del results['.hg']
         return results
 
     # step 2: query Watchman
     try:
         # Use the user-configured timeout for the query.
         # Add a little slack over the top of the user query to allow for
         # overheads while transferring the data
         self._watchmanclient.settimeout(state.timeout + 0.1)
         result = self._watchmanclient.command('query', {
             'fields': ['mode', 'mtime', 'size', 'exists', 'name'],
             'since': clock,
             'expression': [
                 'not', [
                     'anyof', ['dirname', '.hg'],
                     ['name', '.hg', 'wholename']
                 ]
             ],
             'sync_timeout': int(state.timeout * 1000),
             'empty_on_fresh_instance': state.walk_on_invalidate,
         })
     except Exception as ex:
         _handleunavailable(self._ui, state, ex)
         self._watchmanclient.clearconnection()
         return bail('exception during run')
     else:
         # We need to propagate the last observed clock up so that we
         # can use it for our next query
         state.setlastclock(result['clock'])
         if result['is_fresh_instance']:
             if state.walk_on_invalidate:
                 state.invalidate()
                 return bail('fresh instance')
             fresh_instance = True
             # Ignore any prior noteable files from the state info
             notefiles = []
 
     # for file paths which require normalization and we encounter a case
     # collision, we store our own foldmap
     if normalize:
         foldmap = dict((normcase(k), k) for k in results)
 
     switch_slashes = pycompat.ossep == '\\'
     # The order of the results is, strictly speaking, undefined.
     # For case changes on a case insensitive filesystem we may receive
     # two entries, one with exists=True and another with exists=False.
     # The exists=True entries in the same response should be interpreted
     # as being happens-after the exists=False entries due to the way that
     # Watchman tracks files.  We use this property to reconcile deletes
     # for name case changes.
     for entry in result['files']:
         fname = entry['name']
         if _fixencoding:
             fname = _watchmantofsencoding(fname)
         if switch_slashes:
             fname = fname.replace('\\', '/')
         if normalize:
             normed = normcase(fname)
             fname = normalize(fname, True, True)
             foldmap[normed] = fname
         fmode = entry['mode']
         fexists = entry['exists']
         kind = getkind(fmode)
 
         if '/.hg/' in fname or fname.endswith('/.hg'):
             return bail('nested-repo-detected')
 
         if not fexists:
             # if marked as deleted and we don't already have a change
             # record, mark it as deleted.  If we already have an entry
             # for fname then it was either part of walkexplicit or was
             # an earlier result that was a case change
             if fname not in results and fname in dmap and (
                     matchalways or matchfn(fname)):
                 results[fname] = None
         elif kind == dirkind:
             if fname in dmap and (matchalways or matchfn(fname)):
                 results[fname] = None
         elif kind == regkind or kind == lnkkind:
             if fname in dmap:
                 if matchalways or matchfn(fname):
                     results[fname] = entry
             elif (matchalways or matchfn(fname)) and not ignore(fname):
                 results[fname] = entry
         elif fname in dmap and (matchalways or matchfn(fname)):
             results[fname] = None
 
     # step 3: query notable files we don't already know about
     # XXX try not to iterate over the entire dmap
     if normalize:
         # any notable files that have changed case will already be handled
         # above, so just check membership in the foldmap
         notefiles = set((normalize(f, True, True) for f in notefiles
                          if normcase(f) not in foldmap))
     visit = set((f for f in notefiles if (f not in results and matchfn(f)
                                           and (f in dmap or not ignore(f)))))
 
     if not fresh_instance:
         if matchalways:
             visit.update(f for f in nonnormalset if f not in results)
             visit.update(f for f in copymap if f not in results)
         else:
             visit.update(f for f in nonnormalset
                          if f not in results and matchfn(f))
             visit.update(f for f in copymap
                          if f not in results and matchfn(f))
     else:
         if matchalways:
             visit.update(f for f, st in dmap.iteritems() if f not in results)
             visit.update(f for f in copymap if f not in results)
         else:
             visit.update(f for f, st in dmap.iteritems()
                          if f not in results and matchfn(f))
             visit.update(f for f in copymap
                          if f not in results and matchfn(f))
 
     audit = pathutil.pathauditor(self._root, cached=True).check
     auditpass = [f for f in visit if audit(f)]
     auditpass.sort()
     auditfail = visit.difference(auditpass)
     for f in auditfail:
         results[f] = None
 
     nf = iter(auditpass).next
     for st in util.statfiles([join(f) for f in auditpass]):
         f = nf()
         if st or f in dmap:
             results[f] = st
 
     for s in subrepos:
         del results[s]
     del results['.hg']
     return results
 
 def overridestatus(
         orig, self, node1='.', node2=None, match=None, ignored=False,
         clean=False, unknown=False, listsubrepos=False):
     listignored = ignored
     listclean = clean
     listunknown = unknown
 
     def _cmpsets(l1, l2):
         try:
             if 'FSMONITOR_LOG_FILE' in encoding.environ:
                 fn = encoding.environ['FSMONITOR_LOG_FILE']
                 f = open(fn, 'wb')
             else:
                 fn = 'fsmonitorfail.log'
                 f = self.vfs.open(fn, 'wb')
         except (IOError, OSError):
             self.ui.warn(_('warning: unable to write to %s\n') % fn)
             return
 
         try:
             for i, (s1, s2) in enumerate(zip(l1, l2)):
                 if set(s1) != set(s2):
                     f.write('sets at position %d are unequal\n' % i)
                     f.write('watchman returned: %s\n' % s1)
                     f.write('stat returned: %s\n' % s2)
         finally:
             f.close()
 
     if isinstance(node1, context.changectx):
         ctx1 = node1
     else:
         ctx1 = self[node1]
     if isinstance(node2, context.changectx):
         ctx2 = node2
     else:
         ctx2 = self[node2]
 
     working = ctx2.rev() is None
     parentworking = working and ctx1 == self['.']
-    match = match or matchmod.always(self.root, self.getcwd())
+    match = match or matchmod.always()
 
     # Maybe we can use this opportunity to update Watchman's state.
     # Mercurial uses workingcommitctx and/or memctx to represent the part of
     # the workingctx that is to be committed. So don't update the state in
     # that case.
     # HG_PENDING is set in the environment when the dirstate is being updated
     # in the middle of a transaction; we must not update our state in that
     # case, or we risk forgetting about changes in the working copy.
     updatestate = (parentworking and match.always() and
                    not isinstance(ctx2, (context.workingcommitctx,
                                          context.memctx)) and
                    'HG_PENDING' not in encoding.environ)
 
     try:
         if self._fsmonitorstate.walk_on_invalidate:
             # Use a short timeout to query the current clock.  If that
             # takes too long then we assume that the service will be slow
             # to answer our query.
             # walk_on_invalidate indicates that we prefer to walk the
             # tree ourselves because we can ignore portions that Watchman
             # cannot and we tend to be faster in the warmer buffer cache
             # cases.
             self._watchmanclient.settimeout(0.1)
         else:
             # Give Watchman more time to potentially complete its walk
             # and return the initial clock.  In this mode we assume that
             # the filesystem will be slower than parsing a potentially
             # very large Watchman result set.
             self._watchmanclient.settimeout(
                 self._fsmonitorstate.timeout + 0.1)
         startclock = self._watchmanclient.getcurrentclock()
     except Exception as ex:
         self._watchmanclient.clearconnection()
         _handleunavailable(self.ui, self._fsmonitorstate, ex)
         # boo, Watchman failed. bail
         return orig(node1, node2, match, listignored, listclean,
                     listunknown, listsubrepos)
 
     if updatestate:
         # We need info about unknown files. This may make things slower the
         # first time, but whatever.
         stateunknown = True
     else:
         stateunknown = listunknown
 
     if updatestate:
         ps = poststatus(startclock)
         self.addpostdsstatus(ps)
 
     r = orig(node1, node2, match, listignored, listclean, stateunknown,
              listsubrepos)
     modified, added, removed, deleted, unknown, ignored, clean = r
 
     if not listunknown:
         unknown = []
 
     # don't do paranoid checks if we're not going to query Watchman anyway
     full = listclean or match.traversedir is not None
     if self._fsmonitorstate.mode == 'paranoid' and not full:
         # run status again and fall back to the old walk this time
         self.dirstate._fsmonitordisable = True
 
         # shut the UI up
         quiet = self.ui.quiet
         self.ui.quiet = True
         fout, ferr = self.ui.fout, self.ui.ferr
         self.ui.fout = self.ui.ferr = open(os.devnull, 'wb')
 
         try:
             rv2 = orig(
                 node1, node2, match, listignored, listclean, listunknown,
                 listsubrepos)
         finally:
             self.dirstate._fsmonitordisable = False
             self.ui.quiet = quiet
             self.ui.fout, self.ui.ferr = fout, ferr
 
         # clean isn't tested since it's set to True above
         with self.wlock():
             _cmpsets(
                 [modified, added, removed, deleted, unknown, ignored, clean],
                 rv2)
         modified, added, removed, deleted, unknown, ignored, clean = rv2
 
     return scmutil.status(
         modified, added, removed, deleted, unknown, ignored, clean)
 
 class poststatus(object):
     def __init__(self, startclock):
         self._startclock = startclock
 
     def __call__(self, wctx, status):
         clock = wctx.repo()._fsmonitorstate.getlastclock() or self._startclock
         hashignore = _hashignore(wctx.repo().dirstate._ignore)
         notefiles = (status.modified + status.added + status.removed +
                      status.deleted + status.unknown)
         wctx.repo()._fsmonitorstate.set(clock, hashignore, notefiles)
 
 def makedirstate(repo, dirstate):
     class fsmonitordirstate(dirstate.__class__):
         def _fsmonitorinit(self, repo):
             # _fsmonitordisable is used in paranoid mode
             self._fsmonitordisable = False
             self._fsmonitorstate = repo._fsmonitorstate
             self._watchmanclient = repo._watchmanclient
             self._repo = weakref.proxy(repo)
 
         def walk(self, *args, **kwargs):
             orig = super(fsmonitordirstate, self).walk
             if self._fsmonitordisable:
                 return orig(*args, **kwargs)
             return overridewalk(orig, self, *args, **kwargs)
 
         def rebuild(self, *args, **kwargs):
             self._fsmonitorstate.invalidate()
             return super(fsmonitordirstate, self).rebuild(*args, **kwargs)
 
         def invalidate(self, *args, **kwargs):
             self._fsmonitorstate.invalidate()
             return super(fsmonitordirstate, self).invalidate(*args, **kwargs)
 
     dirstate.__class__ = fsmonitordirstate
     dirstate._fsmonitorinit(repo)
 
 def wrapdirstate(orig, self):
     ds = orig(self)
     # only override the dirstate when Watchman is available for the repo
     if util.safehasattr(self, '_fsmonitorstate'):
         makedirstate(self, ds)
     return ds
 
 def extsetup(ui):
     extensions.wrapfilecache(
         localrepo.localrepository, 'dirstate', wrapdirstate)
     if pycompat.isdarwin:
         # An assist for avoiding the dangling-symlink fsevents bug
         extensions.wrapfunction(os, 'symlink', wrapsymlink)
 
     extensions.wrapfunction(merge, 'update', wrapupdate)
 
 def wrapsymlink(orig, source, link_name):
     ''' if we create a dangling symlink, also touch the parent dir
     to encourage fsevents notifications to work more correctly '''
     try:
         return orig(source, link_name)
     finally:
         try:
             os.utime(os.path.dirname(link_name), None)
         except OSError:
             pass
 
 class state_update(object):
     ''' This context manager is responsible for dispatching the state-enter
         and state-leave signals to the watchman service. The enter and leave
         methods can be invoked manually (for scenarios where context manager
         semantics are not possible). If parameters oldnode and newnode are None,
         they will be populated based on current working copy in enter and
         leave, respectively. Similarly, if the distance is none, it will be
         calculated based on the oldnode and newnode in the leave method.'''
 
     def __init__(self, repo, name, oldnode=None, newnode=None, distance=None,
                  partial=False):
         self.repo = repo.unfiltered()
         self.name = name
         self.oldnode = oldnode
         self.newnode = newnode
         self.distance = distance
         self.partial = partial
         self._lock = None
         self.need_leave = False
 
     def __enter__(self):
         self.enter()
 
     def enter(self):
         # Make sure we have a wlock prior to sending notifications to watchman.
         # We don't want to race with other actors. In the update case,
         # merge.update is going to take the wlock almost immediately. We are
         # effectively extending the lock around several short sanity checks.
         if self.oldnode is None:
             self.oldnode = self.repo['.'].node()
 
         if self.repo.currentwlock() is None:
             if util.safehasattr(self.repo, 'wlocknostateupdate'):
                 self._lock = self.repo.wlocknostateupdate()
             else:
                 self._lock = self.repo.wlock()
         self.need_leave = self._state(
             'state-enter',
             hex(self.oldnode))
         return self
 
     def __exit__(self, type_, value, tb):
         abort = True if type_ else False
         self.exit(abort=abort)
 
     def exit(self, abort=False):
         try:
             if self.need_leave:
                 status = 'failed' if abort else 'ok'
                 if self.newnode is None:
                     self.newnode = self.repo['.'].node()
                 if self.distance is None:
                     self.distance = calcdistance(
                         self.repo, self.oldnode, self.newnode)
                 self._state(
                     'state-leave',
                     hex(self.newnode),
                     status=status)
         finally:
             self.need_leave = False
             if self._lock:
                 self._lock.release()
 
     def _state(self, cmd, commithash, status='ok'):
         if not util.safehasattr(self.repo, '_watchmanclient'):
             return False
         try:
             self.repo._watchmanclient.command(cmd, {
                 'name': self.name,
                 'metadata': {
                     # the target revision
                     'rev': commithash,
                     # approximate number of commits between current and target
                     'distance': self.distance if self.distance else 0,
                     # success/failure (only really meaningful for state-leave)
                     'status': status,
                     # whether the working copy parent is changing
                     'partial': self.partial,
             }})
             return True
         except Exception as e:
             # Swallow any errors; fire and forget
             self.repo.ui.log(
                 'watchman', 'Exception %s while running %s\n', e, cmd)
             return False
 
 # Estimate the distance between two nodes
 def calcdistance(repo, oldnode, newnode):
     anc = repo.changelog.ancestor(oldnode, newnode)
     ancrev = repo[anc].rev()
     distance = (abs(repo[oldnode].rev() - ancrev)
         + abs(repo[newnode].rev() - ancrev))
     return distance
 
 # Bracket working copy updates with calls to the watchman state-enter
 # and state-leave commands.  This allows clients to perform more intelligent
 # settling during bulk file change scenarios
 # https://facebook.github.io/watchman/docs/cmd/subscribe.html#advanced-settling
 def wrapupdate(orig, repo, node, branchmerge, force, ancestor=None,
                mergeancestor=False, labels=None, matcher=None, **kwargs):
 
     distance = 0
     partial = True
     oldnode = repo['.'].node()
     newnode = repo[node].node()
     if matcher is None or matcher.always():
         partial = False
         distance = calcdistance(repo.unfiltered(), oldnode, newnode)
 
     with state_update(repo, name="hg.update", oldnode=oldnode, newnode=newnode,
                       distance=distance, partial=partial):
         return orig(
             repo, node, branchmerge, force, ancestor, mergeancestor,
             labels, matcher, **kwargs)
 
 def repo_has_depth_one_nested_repo(repo):
     for f in repo.wvfs.listdir():
         if os.path.isdir(os.path.join(repo.root, f, '.hg')):
             msg = 'fsmonitor: sub-repository %r detected, fsmonitor disabled\n'
             repo.ui.debug(msg % f)
             return True
     return False
 
 def reposetup(ui, repo):
     # We don't work with largefiles or inotify
     exts = extensions.enabled()
     for ext in _blacklist:
         if ext in exts:
             ui.warn(_('The fsmonitor extension is incompatible with the %s '
                       'extension and has been disabled.\n') % ext)
             return
 
     if repo.local():
         # We don't work with subrepos either.
         #
         # if repo[None].substate can cause a dirstate parse, which is too
         # slow. Instead, look for a file called hgsubstate,
         if repo.wvfs.exists('.hgsubstate') or repo.wvfs.exists('.hgsub'):
             return
 
         if repo_has_depth_one_nested_repo(repo):
             return
 
         fsmonitorstate = state.state(repo)
         if fsmonitorstate.mode == 'off':
             return
 
         try:
             client = watchmanclient.client(repo)
         except Exception as ex:
             _handleunavailable(ui, fsmonitorstate, ex)
             return
 
         repo._fsmonitorstate = fsmonitorstate
         repo._watchmanclient = client
 
         dirstate, cached = localrepo.isfilecached(repo, 'dirstate')
         if cached:
             # at this point since fsmonitorstate wasn't present,
             # repo.dirstate is not a fsmonitordirstate
             makedirstate(repo, dirstate)
 
         class fsmonitorrepo(repo.__class__):
             def status(self, *args, **kwargs):
                 orig = super(fsmonitorrepo, self).status
                 return overridestatus(orig, self, *args, **kwargs)
 
             def wlocknostateupdate(self, *args, **kwargs):
                 return super(fsmonitorrepo, self).wlock(*args, **kwargs)
 
             def wlock(self, *args, **kwargs):
                 l = super(fsmonitorrepo, self).wlock(*args, **kwargs)
                 if not ui.configbool(
                     "experimental", "fsmonitor.transaction_notify"):
                     return l
                 if l.held != 1:
                     return l
                 origrelease = l.releasefn
 
                 def staterelease():
                     if origrelease:
                         origrelease()
                     if l.stateupdate:
                         l.stateupdate.exit()
                         l.stateupdate = None
 
                 try:
                     l.stateupdate = None
                     l.stateupdate = state_update(self, name="hg.transaction")
                     l.stateupdate.enter()
                     l.releasefn = staterelease
                 except Exception as e:
                     # Swallow any errors; fire and forget
                     self.ui.log(
                         'watchman', 'Exception in state update %s\n', e)
                 return l
 
         repo.__class__ = fsmonitorrepo

hgext/gpg.py

@@ -1,341 +1,341 b''
 # Copyright 2005, 2006 Benoit Boissinot <[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.
 
 '''commands to sign and verify changesets'''
 
 from __future__ import absolute_import
 
 import binascii
 import os
 
 from mercurial.i18n import _
 from mercurial import (
     cmdutil,
     error,
     help,
     match,
     node as hgnode,
     pycompat,
     registrar,
 )
 from mercurial.utils import (
     dateutil,
     procutil,
 )
 
 cmdtable = {}
 command = registrar.command(cmdtable)
 # Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
 # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
 # be specifying the version(s) of Mercurial they are tested with, or
 # leave the attribute unspecified.
 testedwith = 'ships-with-hg-core'
 
 configtable = {}
 configitem = registrar.configitem(configtable)
 
 configitem('gpg', 'cmd',
     default='gpg',
 )
 configitem('gpg', 'key',
     default=None,
 )
 configitem('gpg', '.*',
     default=None,
     generic=True,
 )
 
 # Custom help category
 _HELP_CATEGORY = 'gpg'
 
 class gpg(object):
     def __init__(self, path, key=None):
         self.path = path
         self.key = (key and " --local-user \"%s\"" % key) or ""
 
     def sign(self, data):
         gpgcmd = "%s --sign --detach-sign%s" % (self.path, self.key)
         return procutil.filter(data, gpgcmd)
 
     def verify(self, data, sig):
         """ returns of the good and bad signatures"""
         sigfile = datafile = None
         try:
             # create temporary files
             fd, sigfile = pycompat.mkstemp(prefix="hg-gpg-", suffix=".sig")
             fp = os.fdopen(fd, r'wb')
             fp.write(sig)
             fp.close()
             fd, datafile = pycompat.mkstemp(prefix="hg-gpg-", suffix=".txt")
             fp = os.fdopen(fd, r'wb')
             fp.write(data)
             fp.close()
             gpgcmd = ("%s --logger-fd 1 --status-fd 1 --verify "
                       "\"%s\" \"%s\"" % (self.path, sigfile, datafile))
             ret = procutil.filter("", gpgcmd)
         finally:
             for f in (sigfile, datafile):
                 try:
                     if f:
                         os.unlink(f)
                 except OSError:
                     pass
         keys = []
         key, fingerprint = None, None
         for l in ret.splitlines():
             # see DETAILS in the gnupg documentation
             # filter the logger output
             if not l.startswith("[GNUPG:]"):
                 continue
             l = l[9:]
             if l.startswith("VALIDSIG"):
                 # fingerprint of the primary key
                 fingerprint = l.split()[10]
             elif l.startswith("ERRSIG"):
                 key = l.split(" ", 3)[:2]
                 key.append("")
                 fingerprint = None
             elif (l.startswith("GOODSIG") or
                   l.startswith("EXPSIG") or
                   l.startswith("EXPKEYSIG") or
                   l.startswith("BADSIG")):
                 if key is not None:
                     keys.append(key + [fingerprint])
                 key = l.split(" ", 2)
                 fingerprint = None
         if key is not None:
             keys.append(key + [fingerprint])
         return keys
 
 def newgpg(ui, **opts):
     """create a new gpg instance"""
     gpgpath = ui.config("gpg", "cmd")
     gpgkey = opts.get(r'key')
     if not gpgkey:
         gpgkey = ui.config("gpg", "key")
     return gpg(gpgpath, gpgkey)
 
 def sigwalk(repo):
     """
     walk over every sigs, yields a couple
     ((node, version, sig), (filename, linenumber))
     """
     def parsefile(fileiter, context):
         ln = 1
         for l in fileiter:
             if not l:
                 continue
             yield (l.split(" ", 2), (context, ln))
             ln += 1
 
     # read the heads
     fl = repo.file(".hgsigs")
     for r in reversed(fl.heads()):
         fn = ".hgsigs|%s" % hgnode.short(r)
         for item in parsefile(fl.read(r).splitlines(), fn):
             yield item
     try:
         # read local signatures
         fn = "localsigs"
         for item in parsefile(repo.vfs(fn), fn):
             yield item
     except IOError:
         pass
 
 def getkeys(ui, repo, mygpg, sigdata, context):
     """get the keys who signed a data"""
     fn, ln = context
     node, version, sig = sigdata
     prefix = "%s:%d" % (fn, ln)
     node = hgnode.bin(node)
 
     data = node2txt(repo, node, version)
     sig = binascii.a2b_base64(sig)
     keys = mygpg.verify(data, sig)
 
     validkeys = []
     # warn for expired key and/or sigs
     for key in keys:
         if key[0] == "ERRSIG":
             ui.write(_("%s Unknown key ID \"%s\"\n") % (prefix, key[1]))
             continue
         if key[0] == "BADSIG":
             ui.write(_("%s Bad signature from \"%s\"\n") % (prefix, key[2]))
             continue
         if key[0] == "EXPSIG":
             ui.write(_("%s Note: Signature has expired"
                        " (signed by: \"%s\")\n") % (prefix, key[2]))
         elif key[0] == "EXPKEYSIG":
             ui.write(_("%s Note: This key has expired"
                        " (signed by: \"%s\")\n") % (prefix, key[2]))
         validkeys.append((key[1], key[2], key[3]))
     return validkeys
 
 @command("sigs", [], _('hg sigs'), helpcategory=_HELP_CATEGORY)
 def sigs(ui, repo):
     """list signed changesets"""
     mygpg = newgpg(ui)
     revs = {}
 
     for data, context in sigwalk(repo):
         node, version, sig = data
         fn, ln = context
         try:
             n = repo.lookup(node)
         except KeyError:
             ui.warn(_("%s:%d node does not exist\n") % (fn, ln))
             continue
         r = repo.changelog.rev(n)
         keys = getkeys(ui, repo, mygpg, data, context)
         if not keys:
             continue
         revs.setdefault(r, [])
         revs[r].extend(keys)
     for rev in sorted(revs, reverse=True):
         for k in revs[rev]:
             r = "%5d:%s" % (rev, hgnode.hex(repo.changelog.node(rev)))
             ui.write("%-30s %s\n" % (keystr(ui, k), r))
 
 @command("sigcheck", [], _('hg sigcheck REV'), helpcategory=_HELP_CATEGORY)
 def sigcheck(ui, repo, rev):
     """verify all the signatures there may be for a particular revision"""
     mygpg = newgpg(ui)
     rev = repo.lookup(rev)
     hexrev = hgnode.hex(rev)
     keys = []
 
     for data, context in sigwalk(repo):
         node, version, sig = data
         if node == hexrev:
             k = getkeys(ui, repo, mygpg, data, context)
             if k:
                 keys.extend(k)
 
     if not keys:
         ui.write(_("no valid signature for %s\n") % hgnode.short(rev))
         return
 
     # print summary
     ui.write(_("%s is signed by:\n") % hgnode.short(rev))
     for key in keys:
         ui.write(" %s\n" % keystr(ui, key))
 
 def keystr(ui, key):
     """associate a string to a key (username, comment)"""
     keyid, user, fingerprint = key
     comment = ui.config("gpg", fingerprint)
     if comment:
         return "%s (%s)" % (user, comment)
     else:
         return user
 
 @command("sign",
          [('l', 'local', None, _('make the signature local')),
           ('f', 'force', None, _('sign even if the sigfile is modified')),
           ('', 'no-commit', None, _('do not commit the sigfile after signing')),
           ('k', 'key', '',
            _('the key id to sign with'), _('ID')),
           ('m', 'message', '',
            _('use text as commit message'), _('TEXT')),
           ('e', 'edit', False, _('invoke editor on commit messages')),
          ] + cmdutil.commitopts2,
          _('hg sign [OPTION]... [REV]...'),
          helpcategory=_HELP_CATEGORY)
 def sign(ui, repo, *revs, **opts):
     """add a signature for the current or given revision
 
     If no revision is given, the parent of the working directory is used,
     or tip if no revision is checked out.
 
     The ``gpg.cmd`` config setting can be used to specify the command
     to run. A default key can be specified with ``gpg.key``.
 
     See :hg:`help dates` for a list of formats valid for -d/--date.
     """
     with repo.wlock():
         return _dosign(ui, repo, *revs, **opts)
 
 def _dosign(ui, repo, *revs, **opts):
     mygpg = newgpg(ui, **opts)
     opts = pycompat.byteskwargs(opts)
     sigver = "0"
     sigmessage = ""
 
     date = opts.get('date')
     if date:
         opts['date'] = dateutil.parsedate(date)
 
     if revs:
         nodes = [repo.lookup(n) for n in revs]
     else:
         nodes = [node for node in repo.dirstate.parents()
                  if node != hgnode.nullid]
         if len(nodes) > 1:
             raise error.Abort(_('uncommitted merge - please provide a '
                                'specific revision'))
         if not nodes:
             nodes = [repo.changelog.tip()]
 
     for n in nodes:
         hexnode = hgnode.hex(n)
         ui.write(_("signing %d:%s\n") % (repo.changelog.rev(n),
                                          hgnode.short(n)))
         # build data
         data = node2txt(repo, n, sigver)
         sig = mygpg.sign(data)
         if not sig:
             raise error.Abort(_("error while signing"))
         sig = binascii.b2a_base64(sig)
         sig = sig.replace("\n", "")
         sigmessage += "%s %s %s\n" % (hexnode, sigver, sig)
 
     # write it
     if opts['local']:
         repo.vfs.append("localsigs", sigmessage)
         return
 
     if not opts["force"]:
-        msigs = match.exact(repo.root, '', ['.hgsigs'])
+        msigs = match.exact(['.hgsigs'])
         if any(repo.status(match=msigs, unknown=True, ignored=True)):
             raise error.Abort(_("working copy of .hgsigs is changed "),
                              hint=_("please commit .hgsigs manually"))
 
     sigsfile = repo.wvfs(".hgsigs", "ab")
     sigsfile.write(sigmessage)
     sigsfile.close()
 
     if '.hgsigs' not in repo.dirstate:
         repo[None].add([".hgsigs"])
 
     if opts["no_commit"]:
         return
 
     message = opts['message']
     if not message:
         # we don't translate commit messages
         message = "\n".join(["Added signature for changeset %s"
                              % hgnode.short(n)
                              for n in nodes])
     try:
         editor = cmdutil.getcommiteditor(editform='gpg.sign',
                                          **pycompat.strkwargs(opts))
         repo.commit(message, opts['user'], opts['date'], match=msigs,
                     editor=editor)
     except ValueError as inst:
         raise error.Abort(pycompat.bytestr(inst))
 
 def node2txt(repo, node, ver):
     """map a manifest into some text"""
     if ver == "0":
         return "%s\n" % hgnode.hex(node)
     else:
         raise error.Abort(_("unknown signature version"))
 
 def extsetup(ui):
     # Add our category before "Repository maintenance".
     help.CATEGORY_ORDER.insert(
         help.CATEGORY_ORDER.index(command.CATEGORY_MAINTENANCE),
         _HELP_CATEGORY)
     help.CATEGORY_NAMES[_HELP_CATEGORY] = 'GPG signing'

hgext/largefiles/lfutil.py

@@ -1,675 +1,675 b''
 # Copyright 2009-2010 Gregory P. Ward
 # Copyright 2009-2010 Intelerad Medical Systems Incorporated
 # Copyright 2010-2011 Fog Creek Software
 # Copyright 2010-2011 Unity Technologies
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 '''largefiles utility code: must not import other modules in this package.'''
 from __future__ import absolute_import
 
 import copy
 import hashlib
 import os
 import stat
 
 from mercurial.i18n import _
 from mercurial.node import hex
 
 from mercurial import (
     dirstate,
     encoding,
     error,
     httpconnection,
     match as matchmod,
     node,
     pycompat,
     scmutil,
     sparse,
     util,
     vfs as vfsmod,
 )
 
 shortname = '.hglf'
 shortnameslash = shortname + '/'
 longname = 'largefiles'
 
 # -- Private worker functions ------------------------------------------
 
 def getminsize(ui, assumelfiles, opt, default=10):
     lfsize = opt
     if not lfsize and assumelfiles:
         lfsize = ui.config(longname, 'minsize', default=default)
     if lfsize:
         try:
             lfsize = float(lfsize)
         except ValueError:
             raise error.Abort(_('largefiles: size must be number (not %s)\n')
                              % lfsize)
     if lfsize is None:
         raise error.Abort(_('minimum size for largefiles must be specified'))
     return lfsize
 
 def link(src, dest):
     """Try to create hardlink - if that fails, efficiently make a copy."""
     util.makedirs(os.path.dirname(dest))
     try:
         util.oslink(src, dest)
     except OSError:
         # if hardlinks fail, fallback on atomic copy
         with open(src, 'rb') as srcf, util.atomictempfile(dest) as dstf:
             for chunk in util.filechunkiter(srcf):
                 dstf.write(chunk)
         os.chmod(dest, os.stat(src).st_mode)
 
 def usercachepath(ui, hash):
     '''Return the correct location in the "global" largefiles cache for a file
     with the given hash.
     This cache is used for sharing of largefiles across repositories - both
     to preserve download bandwidth and storage space.'''
     return os.path.join(_usercachedir(ui), hash)
 
 def _usercachedir(ui, name=longname):
     '''Return the location of the "global" largefiles cache.'''
     path = ui.configpath(name, 'usercache')
     if path:
         return path
     if pycompat.iswindows:
         appdata = encoding.environ.get('LOCALAPPDATA',\
                         encoding.environ.get('APPDATA'))
         if appdata:
             return os.path.join(appdata, name)
     elif pycompat.isdarwin:
         home = encoding.environ.get('HOME')
         if home:
             return os.path.join(home, 'Library', 'Caches', name)
     elif pycompat.isposix:
         path = encoding.environ.get('XDG_CACHE_HOME')
         if path:
             return os.path.join(path, name)
         home = encoding.environ.get('HOME')
         if home:
             return os.path.join(home, '.cache', name)
     else:
         raise error.Abort(_('unknown operating system: %s\n')
                           % pycompat.osname)
     raise error.Abort(_('unknown %s usercache location') % name)
 
 def inusercache(ui, hash):
     path = usercachepath(ui, hash)
     return os.path.exists(path)
 
 def findfile(repo, hash):
     '''Return store path of the largefile with the specified hash.
     As a side effect, the file might be linked from user cache.
     Return None if the file can't be found locally.'''
     path, exists = findstorepath(repo, hash)
     if exists:
         repo.ui.note(_('found %s in store\n') % hash)
         return path
     elif inusercache(repo.ui, hash):
         repo.ui.note(_('found %s in system cache\n') % hash)
         path = storepath(repo, hash)
         link(usercachepath(repo.ui, hash), path)
         return path
     return None
 
 class largefilesdirstate(dirstate.dirstate):
     def __getitem__(self, key):
         return super(largefilesdirstate, self).__getitem__(unixpath(key))
     def normal(self, f):
         return super(largefilesdirstate, self).normal(unixpath(f))
     def remove(self, f):
         return super(largefilesdirstate, self).remove(unixpath(f))
     def add(self, f):
         return super(largefilesdirstate, self).add(unixpath(f))
     def drop(self, f):
         return super(largefilesdirstate, self).drop(unixpath(f))
     def forget(self, f):
         return super(largefilesdirstate, self).forget(unixpath(f))
     def normallookup(self, f):
         return super(largefilesdirstate, self).normallookup(unixpath(f))
     def _ignore(self, f):
         return False
     def write(self, tr=False):
         # (1) disable PENDING mode always
         #     (lfdirstate isn't yet managed as a part of the transaction)
         # (2) avoid develwarn 'use dirstate.write with ....'
         super(largefilesdirstate, self).write(None)
 
 def openlfdirstate(ui, repo, create=True):
     '''
     Return a dirstate object that tracks largefiles: i.e. its root is
     the repo root, but it is saved in .hg/largefiles/dirstate.
     '''
     vfs = repo.vfs
     lfstoredir = longname
     opener = vfsmod.vfs(vfs.join(lfstoredir))
     lfdirstate = largefilesdirstate(opener, ui, repo.root,
                                     repo.dirstate._validate,
                                     lambda: sparse.matcher(repo))
 
     # If the largefiles dirstate does not exist, populate and create
     # it. This ensures that we create it on the first meaningful
     # largefiles operation in a new clone.
     if create and not vfs.exists(vfs.join(lfstoredir, 'dirstate')):
         matcher = getstandinmatcher(repo)
         standins = repo.dirstate.walk(matcher, subrepos=[], unknown=False,
                                       ignored=False)
 
         if len(standins) > 0:
             vfs.makedirs(lfstoredir)
 
         for standin in standins:
             lfile = splitstandin(standin)
             lfdirstate.normallookup(lfile)
     return lfdirstate
 
 def lfdirstatestatus(lfdirstate, repo):
     pctx = repo['.']
-    match = matchmod.always(repo.root, repo.getcwd())
+    match = matchmod.always()
     unsure, s = lfdirstate.status(match, subrepos=[], ignored=False,
                                   clean=False, unknown=False)
     modified, clean = s.modified, s.clean
     for lfile in unsure:
         try:
             fctx = pctx[standin(lfile)]
         except LookupError:
             fctx = None
         if not fctx or readasstandin(fctx) != hashfile(repo.wjoin(lfile)):
             modified.append(lfile)
         else:
             clean.append(lfile)
             lfdirstate.normal(lfile)
     return s
 
 def listlfiles(repo, rev=None, matcher=None):
     '''return a list of largefiles in the working copy or the
     specified changeset'''
 
     if matcher is None:
         matcher = getstandinmatcher(repo)
 
     # ignore unknown files in working directory
     return [splitstandin(f)
             for f in repo[rev].walk(matcher)
             if rev is not None or repo.dirstate[f] != '?']
 
 def instore(repo, hash, forcelocal=False):
     '''Return true if a largefile with the given hash exists in the store'''
     return os.path.exists(storepath(repo, hash, forcelocal))
 
 def storepath(repo, hash, forcelocal=False):
     '''Return the correct location in the repository largefiles store for a
     file with the given hash.'''
     if not forcelocal and repo.shared():
         return repo.vfs.reljoin(repo.sharedpath, longname, hash)
     return repo.vfs.join(longname, hash)
 
 def findstorepath(repo, hash):
     '''Search through the local store path(s) to find the file for the given
     hash.  If the file is not found, its path in the primary store is returned.
     The return value is a tuple of (path, exists(path)).
     '''
     # For shared repos, the primary store is in the share source.  But for
     # backward compatibility, force a lookup in the local store if it wasn't
     # found in the share source.
     path = storepath(repo, hash, False)
 
     if instore(repo, hash):
         return (path, True)
     elif repo.shared() and instore(repo, hash, True):
         return storepath(repo, hash, True), True
 
     return (path, False)
 
 def copyfromcache(repo, hash, filename):
     '''Copy the specified largefile from the repo or system cache to
     filename in the repository. Return true on success or false if the
     file was not found in either cache (which should not happened:
     this is meant to be called only after ensuring that the needed
     largefile exists in the cache).'''
     wvfs = repo.wvfs
     path = findfile(repo, hash)
     if path is None:
         return False
     wvfs.makedirs(wvfs.dirname(wvfs.join(filename)))
     # The write may fail before the file is fully written, but we
     # don't use atomic writes in the working copy.
     with open(path, 'rb') as srcfd, wvfs(filename, 'wb') as destfd:
         gothash = copyandhash(
             util.filechunkiter(srcfd), destfd)
     if gothash != hash:
         repo.ui.warn(_('%s: data corruption in %s with hash %s\n')
                      % (filename, path, gothash))
         wvfs.unlink(filename)
         return False
     return True
 
 def copytostore(repo, ctx, file, fstandin):
     wvfs = repo.wvfs
     hash = readasstandin(ctx[fstandin])
     if instore(repo, hash):
         return
     if wvfs.exists(file):
         copytostoreabsolute(repo, wvfs.join(file), hash)
     else:
         repo.ui.warn(_("%s: largefile %s not available from local store\n") %
                      (file, hash))
 
 def copyalltostore(repo, node):
     '''Copy all largefiles in a given revision to the store'''
 
     ctx = repo[node]
     for filename in ctx.files():
         realfile = splitstandin(filename)
         if realfile is not None and filename in ctx.manifest():
             copytostore(repo, ctx, realfile, filename)
 
 def copytostoreabsolute(repo, file, hash):
     if inusercache(repo.ui, hash):
         link(usercachepath(repo.ui, hash), storepath(repo, hash))
     else:
         util.makedirs(os.path.dirname(storepath(repo, hash)))
         with open(file, 'rb') as srcf:
             with util.atomictempfile(storepath(repo, hash),
                                      createmode=repo.store.createmode) as dstf:
                 for chunk in util.filechunkiter(srcf):
                     dstf.write(chunk)
         linktousercache(repo, hash)
 
 def linktousercache(repo, hash):
     '''Link / copy the largefile with the specified hash from the store
     to the cache.'''
     path = usercachepath(repo.ui, hash)
     link(storepath(repo, hash), path)
 
 def getstandinmatcher(repo, rmatcher=None):
     '''Return a match object that applies rmatcher to the standin directory'''
     wvfs = repo.wvfs
     standindir = shortname
 
     # no warnings about missing files or directories
     badfn = lambda f, msg: None
 
     if rmatcher and not rmatcher.always():
         pats = [wvfs.join(standindir, pat) for pat in rmatcher.files()]
         if not pats:
             pats = [wvfs.join(standindir)]
         match = scmutil.match(repo[None], pats, badfn=badfn)
     else:
         # no patterns: relative to repo root
         match = scmutil.match(repo[None], [wvfs.join(standindir)], badfn=badfn)
     return match
 
 def composestandinmatcher(repo, rmatcher):
     '''Return a matcher that accepts standins corresponding to the
     files accepted by rmatcher. Pass the list of files in the matcher
     as the paths specified by the user.'''
     smatcher = getstandinmatcher(repo, rmatcher)
     isstandin = smatcher.matchfn
     def composedmatchfn(f):
         return isstandin(f) and rmatcher.matchfn(splitstandin(f))
     smatcher.matchfn = composedmatchfn
 
     return smatcher
 
 def standin(filename):
     '''Return the repo-relative path to the standin for the specified big
     file.'''
     # Notes:
     # 1) Some callers want an absolute path, but for instance addlargefiles
     #    needs it repo-relative so it can be passed to repo[None].add().  So
     #    leave it up to the caller to use repo.wjoin() to get an absolute path.
     # 2) Join with '/' because that's what dirstate always uses, even on
     #    Windows. Change existing separator to '/' first in case we are
     #    passed filenames from an external source (like the command line).
     return shortnameslash + util.pconvert(filename)
 
 def isstandin(filename):
     '''Return true if filename is a big file standin. filename must be
     in Mercurial's internal form (slash-separated).'''
     return filename.startswith(shortnameslash)
 
 def splitstandin(filename):
     # Split on / because that's what dirstate always uses, even on Windows.
     # Change local separator to / first just in case we are passed filenames
     # from an external source (like the command line).
     bits = util.pconvert(filename).split('/', 1)
     if len(bits) == 2 and bits[0] == shortname:
         return bits[1]
     else:
         return None
 
 def updatestandin(repo, lfile, standin):
     """Re-calculate hash value of lfile and write it into standin
 
     This assumes that "lfutil.standin(lfile) == standin", for efficiency.
     """
     file = repo.wjoin(lfile)
     if repo.wvfs.exists(lfile):
         hash = hashfile(file)
         executable = getexecutable(file)
         writestandin(repo, standin, hash, executable)
     else:
         raise error.Abort(_('%s: file not found!') % lfile)
 
 def readasstandin(fctx):
     '''read hex hash from given filectx of standin file
 
     This encapsulates how "standin" data is stored into storage layer.'''
     return fctx.data().strip()
 
 def writestandin(repo, standin, hash, executable):
     '''write hash to <repo.root>/<standin>'''
     repo.wwrite(standin, hash + '\n', executable and 'x' or '')
 
 def copyandhash(instream, outfile):
     '''Read bytes from instream (iterable) and write them to outfile,
     computing the SHA-1 hash of the data along the way. Return the hash.'''
     hasher = hashlib.sha1('')
     for data in instream:
         hasher.update(data)
         outfile.write(data)
     return hex(hasher.digest())
 
 def hashfile(file):
     if not os.path.exists(file):
         return ''
     with open(file, 'rb') as fd:
         return hexsha1(fd)
 
 def getexecutable(filename):
     mode = os.stat(filename).st_mode
     return ((mode & stat.S_IXUSR) and
             (mode & stat.S_IXGRP) and
             (mode & stat.S_IXOTH))
 
 def urljoin(first, second, *arg):
     def join(left, right):
         if not left.endswith('/'):
             left += '/'
         if right.startswith('/'):
             right = right[1:]
         return left + right
 
     url = join(first, second)
     for a in arg:
         url = join(url, a)
     return url
 
 def hexsha1(fileobj):
     """hexsha1 returns the hex-encoded sha1 sum of the data in the file-like
     object data"""
     h = hashlib.sha1()
     for chunk in util.filechunkiter(fileobj):
         h.update(chunk)
     return hex(h.digest())
 
 def httpsendfile(ui, filename):
     return httpconnection.httpsendfile(ui, filename, 'rb')
 
 def unixpath(path):
     '''Return a version of path normalized for use with the lfdirstate.'''
     return util.pconvert(os.path.normpath(path))
 
 def islfilesrepo(repo):
     '''Return true if the repo is a largefile repo.'''
     if ('largefiles' in repo.requirements and
             any(shortnameslash in f[0] for f in repo.store.datafiles())):
         return True
 
     return any(openlfdirstate(repo.ui, repo, False))
 
 class storeprotonotcapable(Exception):
     def __init__(self, storetypes):
         self.storetypes = storetypes
 
 def getstandinsstate(repo):
     standins = []
     matcher = getstandinmatcher(repo)
     wctx = repo[None]
     for standin in repo.dirstate.walk(matcher, subrepos=[], unknown=False,
                                       ignored=False):
         lfile = splitstandin(standin)
         try:
             hash = readasstandin(wctx[standin])
         except IOError:
             hash = None
         standins.append((lfile, hash))
     return standins
 
 def synclfdirstate(repo, lfdirstate, lfile, normallookup):
     lfstandin = standin(lfile)
     if lfstandin in repo.dirstate:
         stat = repo.dirstate._map[lfstandin]
         state, mtime = stat[0], stat[3]
     else:
         state, mtime = '?', -1
     if state == 'n':
         if (normallookup or mtime < 0 or
             not repo.wvfs.exists(lfile)):
             # state 'n' doesn't ensure 'clean' in this case
             lfdirstate.normallookup(lfile)
         else:
             lfdirstate.normal(lfile)
     elif state == 'm':
         lfdirstate.normallookup(lfile)
     elif state == 'r':
         lfdirstate.remove(lfile)
     elif state == 'a':
         lfdirstate.add(lfile)
     elif state == '?':
         lfdirstate.drop(lfile)
 
 def markcommitted(orig, ctx, node):
     repo = ctx.repo()
 
     orig(node)
 
     # ATTENTION: "ctx.files()" may differ from "repo[node].files()"
     # because files coming from the 2nd parent are omitted in the latter.
     #
     # The former should be used to get targets of "synclfdirstate",
     # because such files:
     # - are marked as "a" by "patch.patch()" (e.g. via transplant), and
     # - have to be marked as "n" after commit, but
     # - aren't listed in "repo[node].files()"
 
     lfdirstate = openlfdirstate(repo.ui, repo)
     for f in ctx.files():
         lfile = splitstandin(f)
         if lfile is not None:
             synclfdirstate(repo, lfdirstate, lfile, False)
     lfdirstate.write()
 
     # As part of committing, copy all of the largefiles into the cache.
     #
     # Using "node" instead of "ctx" implies additional "repo[node]"
     # lookup while copyalltostore(), but can omit redundant check for
     # files comming from the 2nd parent, which should exist in store
     # at merging.
     copyalltostore(repo, node)
 
 def getlfilestoupdate(oldstandins, newstandins):
     changedstandins = set(oldstandins).symmetric_difference(set(newstandins))
     filelist = []
     for f in changedstandins:
         if f[0] not in filelist:
             filelist.append(f[0])
     return filelist
 
 def getlfilestoupload(repo, missing, addfunc):
     makeprogress = repo.ui.makeprogress
     with makeprogress(_('finding outgoing largefiles'),
                       unit=_('revisions'), total=len(missing)) as progress:
         for i, n in enumerate(missing):
             progress.update(i)
             parents = [p for p in repo[n].parents() if p != node.nullid]
 
             oldlfstatus = repo.lfstatus
             repo.lfstatus = False
             try:
                 ctx = repo[n]
             finally:
                 repo.lfstatus = oldlfstatus
 
             files = set(ctx.files())
             if len(parents) == 2:
                 mc = ctx.manifest()
                 mp1 = ctx.p1().manifest()
                 mp2 = ctx.p2().manifest()
                 for f in mp1:
                     if f not in mc:
                         files.add(f)
                 for f in mp2:
                     if f not in mc:
                         files.add(f)
                 for f in mc:
                     if mc[f] != mp1.get(f, None) or mc[f] != mp2.get(f, None):
                         files.add(f)
             for fn in files:
                 if isstandin(fn) and fn in ctx:
                     addfunc(fn, readasstandin(ctx[fn]))
 
 def updatestandinsbymatch(repo, match):
     '''Update standins in the working directory according to specified match
 
     This returns (possibly modified) ``match`` object to be used for
     subsequent commit process.
     '''
 
     ui = repo.ui
 
     # Case 1: user calls commit with no specific files or
     # include/exclude patterns: refresh and commit all files that
     # are "dirty".
     if match is None or match.always():
         # Spend a bit of time here to get a list of files we know
         # are modified so we can compare only against those.
         # It can cost a lot of time (several seconds)
         # otherwise to update all standins if the largefiles are
         # large.
         lfdirstate = openlfdirstate(ui, repo)
-        dirtymatch = matchmod.always(repo.root, repo.getcwd())
+        dirtymatch = matchmod.always()
         unsure, s = lfdirstate.status(dirtymatch, subrepos=[], ignored=False,
                                       clean=False, unknown=False)
         modifiedfiles = unsure + s.modified + s.added + s.removed
         lfiles = listlfiles(repo)
         # this only loops through largefiles that exist (not
         # removed/renamed)
         for lfile in lfiles:
             if lfile in modifiedfiles:
                 fstandin = standin(lfile)
                 if repo.wvfs.exists(fstandin):
                     # this handles the case where a rebase is being
                     # performed and the working copy is not updated
                     # yet.
                     if repo.wvfs.exists(lfile):
                         updatestandin(repo, lfile, fstandin)
 
         return match
 
     lfiles = listlfiles(repo)
     match._files = repo._subdirlfs(match.files(), lfiles)
 
     # Case 2: user calls commit with specified patterns: refresh
     # any matching big files.
     smatcher = composestandinmatcher(repo, match)
     standins = repo.dirstate.walk(smatcher, subrepos=[], unknown=False,
                                   ignored=False)
 
     # No matching big files: get out of the way and pass control to
     # the usual commit() method.
     if not standins:
         return match
 
     # Refresh all matching big files.  It's possible that the
     # commit will end up failing, in which case the big files will
     # stay refreshed.  No harm done: the user modified them and
     # asked to commit them, so sooner or later we're going to
     # refresh the standins.  Might as well leave them refreshed.
     lfdirstate = openlfdirstate(ui, repo)
     for fstandin in standins:
         lfile = splitstandin(fstandin)
         if lfdirstate[lfile] != 'r':
             updatestandin(repo, lfile, fstandin)
 
     # Cook up a new matcher that only matches regular files or
     # standins corresponding to the big files requested by the
     # user.  Have to modify _files to prevent commit() from
     # complaining "not tracked" for big files.
     match = copy.copy(match)
     origmatchfn = match.matchfn
 
     # Check both the list of largefiles and the list of
     # standins because if a largefile was removed, it
     # won't be in the list of largefiles at this point
     match._files += sorted(standins)
 
     actualfiles = []
     for f in match._files:
         fstandin = standin(f)
 
         # For largefiles, only one of the normal and standin should be
         # committed (except if one of them is a remove).  In the case of a
         # standin removal, drop the normal file if it is unknown to dirstate.
         # Thus, skip plain largefile names but keep the standin.
         if f in lfiles or fstandin in standins:
             if repo.dirstate[fstandin] != 'r':
                 if repo.dirstate[f] != 'r':
                     continue
             elif repo.dirstate[f] == '?':
                 continue
 
         actualfiles.append(f)
     match._files = actualfiles
 
     def matchfn(f):
         if origmatchfn(f):
             return f not in lfiles
         else:
             return f in standins
 
     match.matchfn = matchfn
 
     return match
 
 class automatedcommithook(object):
     '''Stateful hook to update standins at the 1st commit of resuming
 
     For efficiency, updating standins in the working directory should
     be avoided while automated committing (like rebase, transplant and
     so on), because they should be updated before committing.
 
     But the 1st commit of resuming automated committing (e.g. ``rebase
     --continue``) should update them, because largefiles may be
     modified manually.
     '''
     def __init__(self, resuming):
         self.resuming = resuming
 
     def __call__(self, repo, match):
         if self.resuming:
             self.resuming = False # avoids updating at subsequent commits
             return updatestandinsbymatch(repo, match)
         else:
             return match
 
 def getstatuswriter(ui, repo, forcibly=None):
     '''Return the function to write largefiles specific status out
 
     If ``forcibly`` is ``None``, this returns the last element of
     ``repo._lfstatuswriters`` as "default" writer function.
 
     Otherwise, this returns the function to always write out (or
     ignore if ``not forcibly``) status.
     '''
     if forcibly is None and util.safehasattr(repo, '_largefilesenabled'):
         return repo._lfstatuswriters[-1]
     else:
         if forcibly:
             return ui.status # forcibly WRITE OUT
         else:
             return lambda *msg, **opts: None # forcibly IGNORE

hgext/largefiles/overrides.py

@@ -1,1506 +1,1503 b''
 # Copyright 2009-2010 Gregory P. Ward
 # Copyright 2009-2010 Intelerad Medical Systems Incorporated
 # Copyright 2010-2011 Fog Creek Software
 # Copyright 2010-2011 Unity Technologies
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 '''Overridden Mercurial commands and functions for the largefiles extension'''
 from __future__ import absolute_import
 
 import copy
 import os
 
 from mercurial.i18n import _
 
 from mercurial.hgweb import (
     webcommands,
 )
 
 from mercurial import (
     archival,
     cmdutil,
     copies as copiesmod,
     error,
     exchange,
     extensions,
     exthelper,
     filemerge,
     hg,
     logcmdutil,
     match as matchmod,
     merge,
     pathutil,
     pycompat,
     scmutil,
     smartset,
     subrepo,
     upgrade,
     url as urlmod,
     util,
 )
 
 from . import (
     lfcommands,
     lfutil,
     storefactory,
 )
 
 eh = exthelper.exthelper()
 
 # -- Utility functions: commonly/repeatedly needed functionality ---------------
 
 def composelargefilematcher(match, manifest):
     '''create a matcher that matches only the largefiles in the original
     matcher'''
     m = copy.copy(match)
     lfile = lambda f: lfutil.standin(f) in manifest
     m._files = [lf for lf in m._files if lfile(lf)]
     m._fileset = set(m._files)
     m.always = lambda: False
     origmatchfn = m.matchfn
     m.matchfn = lambda f: lfile(f) and origmatchfn(f)
     return m
 
 def composenormalfilematcher(match, manifest, exclude=None):
     excluded = set()
     if exclude is not None:
         excluded.update(exclude)
 
     m = copy.copy(match)
     notlfile = lambda f: not (lfutil.isstandin(f) or lfutil.standin(f) in
             manifest or f in excluded)
     m._files = [lf for lf in m._files if notlfile(lf)]
     m._fileset = set(m._files)
     m.always = lambda: False
     origmatchfn = m.matchfn
     m.matchfn = lambda f: notlfile(f) and origmatchfn(f)
     return m
 
 def addlargefiles(ui, repo, isaddremove, matcher, uipathfn, **opts):
     large = opts.get(r'large')
     lfsize = lfutil.getminsize(
         ui, lfutil.islfilesrepo(repo), opts.get(r'lfsize'))
 
     lfmatcher = None
     if lfutil.islfilesrepo(repo):
         lfpats = ui.configlist(lfutil.longname, 'patterns')
         if lfpats:
             lfmatcher = matchmod.match(repo.root, '', list(lfpats))
 
     lfnames = []
     m = matcher
 
     wctx = repo[None]
     for f in wctx.walk(matchmod.badmatch(m, lambda x, y: None)):
         exact = m.exact(f)
         lfile = lfutil.standin(f) in wctx
         nfile = f in wctx
         exists = lfile or nfile
 
         # Don't warn the user when they attempt to add a normal tracked file.
         # The normal add code will do that for us.
         if exact and exists:
             if lfile:
                 ui.warn(_('%s already a largefile\n') % uipathfn(f))
             continue
 
         if (exact or not exists) and not lfutil.isstandin(f):
             # In case the file was removed previously, but not committed
             # (issue3507)
             if not repo.wvfs.exists(f):
                 continue
 
             abovemin = (lfsize and
                         repo.wvfs.lstat(f).st_size >= lfsize * 1024 * 1024)
             if large or abovemin or (lfmatcher and lfmatcher(f)):
                 lfnames.append(f)
                 if ui.verbose or not exact:
                     ui.status(_('adding %s as a largefile\n') % uipathfn(f))
 
     bad = []
 
     # Need to lock, otherwise there could be a race condition between
     # when standins are created and added to the repo.
     with repo.wlock():
         if not opts.get(r'dry_run'):
             standins = []
             lfdirstate = lfutil.openlfdirstate(ui, repo)
             for f in lfnames:
                 standinname = lfutil.standin(f)
                 lfutil.writestandin(repo, standinname, hash='',
                     executable=lfutil.getexecutable(repo.wjoin(f)))
                 standins.append(standinname)
                 if lfdirstate[f] == 'r':
                     lfdirstate.normallookup(f)
                 else:
                     lfdirstate.add(f)
             lfdirstate.write()
             bad += [lfutil.splitstandin(f)
                     for f in repo[None].add(standins)
                     if f in m.files()]
 
         added = [f for f in lfnames if f not in bad]
     return added, bad
 
 def removelargefiles(ui, repo, isaddremove, matcher, uipathfn, dryrun, **opts):
     after = opts.get(r'after')
     m = composelargefilematcher(matcher, repo[None].manifest())
     try:
         repo.lfstatus = True
         s = repo.status(match=m, clean=not isaddremove)
     finally:
         repo.lfstatus = False
     manifest = repo[None].manifest()
     modified, added, deleted, clean = [[f for f in list
                                         if lfutil.standin(f) in manifest]
                                        for list in (s.modified, s.added,
                                                     s.deleted, s.clean)]
 
     def warn(files, msg):
         for f in files:
             ui.warn(msg % uipathfn(f))
         return int(len(files) > 0)
 
     if after:
         remove = deleted
         result = warn(modified + added + clean,
                       _('not removing %s: file still exists\n'))
     else:
         remove = deleted + clean
         result = warn(modified, _('not removing %s: file is modified (use -f'
                                   ' to force removal)\n'))
         result = warn(added, _('not removing %s: file has been marked for add'
                                ' (use forget to undo)\n')) or result
 
     # Need to lock because standin files are deleted then removed from the
     # repository and we could race in-between.
     with repo.wlock():
         lfdirstate = lfutil.openlfdirstate(ui, repo)
         for f in sorted(remove):
             if ui.verbose or not m.exact(f):
                 ui.status(_('removing %s\n') % uipathfn(f))
 
             if not dryrun:
                 if not after:
                     repo.wvfs.unlinkpath(f, ignoremissing=True)
 
         if dryrun:
             return result
 
         remove = [lfutil.standin(f) for f in remove]
         # If this is being called by addremove, let the original addremove
         # function handle this.
         if not isaddremove:
             for f in remove:
                 repo.wvfs.unlinkpath(f, ignoremissing=True)
         repo[None].forget(remove)
 
         for f in remove:
             lfutil.synclfdirstate(repo, lfdirstate, lfutil.splitstandin(f),
                                   False)
 
         lfdirstate.write()
 
     return result
 
 # For overriding mercurial.hgweb.webcommands so that largefiles will
 # appear at their right place in the manifests.
 @eh.wrapfunction(webcommands, 'decodepath')
 def decodepath(orig, path):
     return lfutil.splitstandin(path) or path
 
 # -- Wrappers: modify existing commands --------------------------------
 
 @eh.wrapcommand('add',
     opts=[('', 'large', None, _('add as largefile')),
           ('', 'normal', None, _('add as normal file')),
           ('', 'lfsize', '', _('add all files above this size (in megabytes) '
                                'as largefiles (default: 10)'))])
 def overrideadd(orig, ui, repo, *pats, **opts):
     if opts.get(r'normal') and opts.get(r'large'):
         raise error.Abort(_('--normal cannot be used with --large'))
     return orig(ui, repo, *pats, **opts)
 
 @eh.wrapfunction(cmdutil, 'add')
 def cmdutiladd(orig, ui, repo, matcher, prefix, uipathfn, explicitonly, **opts):
     # The --normal flag short circuits this override
     if opts.get(r'normal'):
         return orig(ui, repo, matcher, prefix, uipathfn, explicitonly, **opts)
 
     ladded, lbad = addlargefiles(ui, repo, False, matcher, uipathfn, **opts)
     normalmatcher = composenormalfilematcher(matcher, repo[None].manifest(),
                                              ladded)
     bad = orig(ui, repo, normalmatcher, prefix, uipathfn, explicitonly, **opts)
 
     bad.extend(f for f in lbad)
     return bad
 
 @eh.wrapfunction(cmdutil, 'remove')
 def cmdutilremove(orig, ui, repo, matcher, prefix, uipathfn, after, force,
                   subrepos, dryrun):
     normalmatcher = composenormalfilematcher(matcher, repo[None].manifest())
     result = orig(ui, repo, normalmatcher, prefix, uipathfn, after, force,
                   subrepos, dryrun)
     return removelargefiles(ui, repo, False, matcher, uipathfn, dryrun,
                             after=after, force=force) or result
 
 @eh.wrapfunction(subrepo.hgsubrepo, 'status')
 def overridestatusfn(orig, repo, rev2, **opts):
     try:
         repo._repo.lfstatus = True
         return orig(repo, rev2, **opts)
     finally:
         repo._repo.lfstatus = False
 
 @eh.wrapcommand('status')
 def overridestatus(orig, ui, repo, *pats, **opts):
     try:
         repo.lfstatus = True
         return orig(ui, repo, *pats, **opts)
     finally:
         repo.lfstatus = False
 
 @eh.wrapfunction(subrepo.hgsubrepo, 'dirty')
 def overridedirty(orig, repo, ignoreupdate=False, missing=False):
     try:
         repo._repo.lfstatus = True
         return orig(repo, ignoreupdate=ignoreupdate, missing=missing)
     finally:
         repo._repo.lfstatus = False
 
 @eh.wrapcommand('log')
 def overridelog(orig, ui, repo, *pats, **opts):
     def overridematchandpats(orig, ctx, pats=(), opts=None, globbed=False,
             default='relpath', badfn=None):
         """Matcher that merges root directory with .hglf, suitable for log.
         It is still possible to match .hglf directly.
         For any listed files run log on the standin too.
         matchfn tries both the given filename and with .hglf stripped.
         """
         if opts is None:
             opts = {}
         matchandpats = orig(ctx, pats, opts, globbed, default, badfn=badfn)
         m, p = copy.copy(matchandpats)
 
         if m.always():
             # We want to match everything anyway, so there's no benefit trying
             # to add standins.
             return matchandpats
 
         pats = set(p)
 
         def fixpats(pat, tostandin=lfutil.standin):
             if pat.startswith('set:'):
                 return pat
 
             kindpat = matchmod._patsplit(pat, None)
 
             if kindpat[0] is not None:
                 return kindpat[0] + ':' + tostandin(kindpat[1])
             return tostandin(kindpat[1])
 
         cwd = repo.getcwd()
         if cwd:
             hglf = lfutil.shortname
             back = util.pconvert(repo.pathto(hglf)[:-len(hglf)])
 
             def tostandin(f):
                 # The file may already be a standin, so truncate the back
                 # prefix and test before mangling it.  This avoids turning
                 # 'glob:../.hglf/foo*' into 'glob:../.hglf/../.hglf/foo*'.
                 if f.startswith(back) and lfutil.splitstandin(f[len(back):]):
                     return f
 
                 # An absolute path is from outside the repo, so truncate the
                 # path to the root before building the standin.  Otherwise cwd
                 # is somewhere in the repo, relative to root, and needs to be
                 # prepended before building the standin.
                 if os.path.isabs(cwd):
                     f = f[len(back):]
                 else:
                     f = cwd + '/' + f
                 return back + lfutil.standin(f)
         else:
             def tostandin(f):
                 if lfutil.isstandin(f):
                     return f
                 return lfutil.standin(f)
         pats.update(fixpats(f, tostandin) for f in p)
 
         for i in range(0, len(m._files)):
             # Don't add '.hglf' to m.files, since that is already covered by '.'
             if m._files[i] == '.':
                 continue
             standin = lfutil.standin(m._files[i])
             # If the "standin" is a directory, append instead of replace to
             # support naming a directory on the command line with only
             # largefiles.  The original directory is kept to support normal
             # files.
             if standin in ctx:
                 m._files[i] = standin
             elif m._files[i] not in ctx and repo.wvfs.isdir(standin):
                 m._files.append(standin)
 
         m._fileset = set(m._files)
         m.always = lambda: False
         origmatchfn = m.matchfn
         def lfmatchfn(f):
             lf = lfutil.splitstandin(f)
             if lf is not None and origmatchfn(lf):
                 return True
             r = origmatchfn(f)
             return r
         m.matchfn = lfmatchfn
 
         ui.debug('updated patterns: %s\n' % ', '.join(sorted(pats)))
         return m, pats
 
     # For hg log --patch, the match object is used in two different senses:
     # (1) to determine what revisions should be printed out, and
     # (2) to determine what files to print out diffs for.
     # The magic matchandpats override should be used for case (1) but not for
     # case (2).
     oldmatchandpats = scmutil.matchandpats
     def overridemakefilematcher(orig, repo, pats, opts, badfn=None):
         wctx = repo[None]
         match, pats = oldmatchandpats(wctx, pats, opts, badfn=badfn)
         return lambda ctx: match
 
     wrappedmatchandpats = extensions.wrappedfunction(scmutil, 'matchandpats',
                                                      overridematchandpats)
     wrappedmakefilematcher = extensions.wrappedfunction(
         logcmdutil, '_makenofollowfilematcher', overridemakefilematcher)
     with wrappedmatchandpats, wrappedmakefilematcher:
         return orig(ui, repo, *pats, **opts)
 
 @eh.wrapcommand('verify',
     opts=[('', 'large', None,
                 _('verify that all largefiles in current revision exists')),
           ('', 'lfa', None,
                 _('verify largefiles in all revisions, not just current')),
           ('', 'lfc', None,
                 _('verify local largefile contents, not just existence'))])
 def overrideverify(orig, ui, repo, *pats, **opts):
     large = opts.pop(r'large', False)
     all = opts.pop(r'lfa', False)
     contents = opts.pop(r'lfc', False)
 
     result = orig(ui, repo, *pats, **opts)
     if large or all or contents:
         result = result or lfcommands.verifylfiles(ui, repo, all, contents)
     return result
 
 @eh.wrapcommand('debugstate',
     opts=[('', 'large', None, _('display largefiles dirstate'))])
 def overridedebugstate(orig, ui, repo, *pats, **opts):
     large = opts.pop(r'large', False)
     if large:
         class fakerepo(object):
             dirstate = lfutil.openlfdirstate(ui, repo)
         orig(ui, fakerepo, *pats, **opts)
     else:
         orig(ui, repo, *pats, **opts)
 
 # Before starting the manifest merge, merge.updates will call
 # _checkunknownfile to check if there are any files in the merged-in
 # changeset that collide with unknown files in the working copy.
 #
 # The largefiles are seen as unknown, so this prevents us from merging
 # in a file 'foo' if we already have a largefile with the same name.
 #
 # The overridden function filters the unknown files by removing any
 # largefiles. This makes the merge proceed and we can then handle this
 # case further in the overridden calculateupdates function below.
 @eh.wrapfunction(merge, '_checkunknownfile')
 def overridecheckunknownfile(origfn, repo, wctx, mctx, f, f2=None):
     if lfutil.standin(repo.dirstate.normalize(f)) in wctx:
         return False
     return origfn(repo, wctx, mctx, f, f2)
 
 # The manifest merge handles conflicts on the manifest level. We want
 # to handle changes in largefile-ness of files at this level too.
 #
 # The strategy is to run the original calculateupdates and then process
 # the action list it outputs. There are two cases we need to deal with:
 #
 # 1. Normal file in p1, largefile in p2. Here the largefile is
 #    detected via its standin file, which will enter the working copy
 #    with a "get" action. It is not "merge" since the standin is all
 #    Mercurial is concerned with at this level -- the link to the
 #    existing normal file is not relevant here.
 #
 # 2. Largefile in p1, normal file in p2. Here we get a "merge" action
 #    since the largefile will be present in the working copy and
 #    different from the normal file in p2. Mercurial therefore
 #    triggers a merge action.
 #
 # In both cases, we prompt the user and emit new actions to either
 # remove the standin (if the normal file was kept) or to remove the
 # normal file and get the standin (if the largefile was kept). The
 # default prompt answer is to use the largefile version since it was
 # presumably changed on purpose.
 #
 # Finally, the merge.applyupdates function will then take care of
 # writing the files into the working copy and lfcommands.updatelfiles
 # will update the largefiles.
 @eh.wrapfunction(merge, 'calculateupdates')
 def overridecalculateupdates(origfn, repo, p1, p2, pas, branchmerge, force,
                              acceptremote, *args, **kwargs):
     overwrite = force and not branchmerge
     actions, diverge, renamedelete = origfn(
         repo, p1, p2, pas, branchmerge, force, acceptremote, *args, **kwargs)
 
     if overwrite:
         return actions, diverge, renamedelete
 
     # Convert to dictionary with filename as key and action as value.
     lfiles = set()
     for f in actions:
         splitstandin = lfutil.splitstandin(f)
         if splitstandin in p1:
             lfiles.add(splitstandin)
         elif lfutil.standin(f) in p1:
             lfiles.add(f)
 
     for lfile in sorted(lfiles):
         standin = lfutil.standin(lfile)
         (lm, largs, lmsg) = actions.get(lfile, (None, None, None))
         (sm, sargs, smsg) = actions.get(standin, (None, None, None))
         if sm in ('g', 'dc') and lm != 'r':
             if sm == 'dc':
                 f1, f2, fa, move, anc = sargs
                 sargs = (p2[f2].flags(), False)
             # Case 1: normal file in the working copy, largefile in
             # the second parent
             usermsg = _('remote turned local normal file %s into a largefile\n'
                         'use (l)argefile or keep (n)ormal file?'
                         '$$ &Largefile $$ &Normal file') % lfile
             if repo.ui.promptchoice(usermsg, 0) == 0: # pick remote largefile
                 actions[lfile] = ('r', None, 'replaced by standin')
                 actions[standin] = ('g', sargs, 'replaces standin')
             else: # keep local normal file
                 actions[lfile] = ('k', None, 'replaces standin')
                 if branchmerge:
                     actions[standin] = ('k', None, 'replaced by non-standin')
                 else:
                     actions[standin] = ('r', None, 'replaced by non-standin')
         elif lm in ('g', 'dc') and sm != 'r':
             if lm == 'dc':
                 f1, f2, fa, move, anc = largs
                 largs = (p2[f2].flags(), False)
             # Case 2: largefile in the working copy, normal file in
             # the second parent
             usermsg = _('remote turned local largefile %s into a normal file\n'
                     'keep (l)argefile or use (n)ormal file?'
                     '$$ &Largefile $$ &Normal file') % lfile
             if repo.ui.promptchoice(usermsg, 0) == 0: # keep local largefile
                 if branchmerge:
                     # largefile can be restored from standin safely
                     actions[lfile] = ('k', None, 'replaced by standin')
                     actions[standin] = ('k', None, 'replaces standin')
                 else:
                     # "lfile" should be marked as "removed" without
                     # removal of itself
                     actions[lfile] = ('lfmr', None,
                                       'forget non-standin largefile')
 
                     # linear-merge should treat this largefile as 're-added'
                     actions[standin] = ('a', None, 'keep standin')
             else: # pick remote normal file
                 actions[lfile] = ('g', largs, 'replaces standin')
                 actions[standin] = ('r', None, 'replaced by non-standin')
 
     return actions, diverge, renamedelete
 
 @eh.wrapfunction(merge, 'recordupdates')
 def mergerecordupdates(orig, repo, actions, branchmerge):
     if 'lfmr' in actions:
         lfdirstate = lfutil.openlfdirstate(repo.ui, repo)
         for lfile, args, msg in actions['lfmr']:
             # this should be executed before 'orig', to execute 'remove'
             # before all other actions
             repo.dirstate.remove(lfile)
             # make sure lfile doesn't get synclfdirstate'd as normal
             lfdirstate.add(lfile)
         lfdirstate.write()
 
     return orig(repo, actions, branchmerge)
 
 # Override filemerge to prompt the user about how they wish to merge
 # largefiles. This will handle identical edits without prompting the user.
 @eh.wrapfunction(filemerge, '_filemerge')
 def overridefilemerge(origfn, premerge, repo, wctx, mynode, orig, fcd, fco, fca,
                       labels=None):
     if not lfutil.isstandin(orig) or fcd.isabsent() or fco.isabsent():
         return origfn(premerge, repo, wctx, mynode, orig, fcd, fco, fca,
                       labels=labels)
 
     ahash = lfutil.readasstandin(fca).lower()
     dhash = lfutil.readasstandin(fcd).lower()
     ohash = lfutil.readasstandin(fco).lower()
     if (ohash != ahash and
         ohash != dhash and
         (dhash == ahash or
          repo.ui.promptchoice(
              _('largefile %s has a merge conflict\nancestor was %s\n'
                'keep (l)ocal %s or\ntake (o)ther %s?'
                '$$ &Local $$ &Other') %
                (lfutil.splitstandin(orig), ahash, dhash, ohash),
              0) == 1)):
         repo.wwrite(fcd.path(), fco.data(), fco.flags())
     return True, 0, False
 
 @eh.wrapfunction(copiesmod, 'pathcopies')
 def copiespathcopies(orig, ctx1, ctx2, match=None):
     copies = orig(ctx1, ctx2, match=match)
     updated = {}
 
     for k, v in copies.iteritems():
         updated[lfutil.splitstandin(k) or k] = lfutil.splitstandin(v) or v
 
     return updated
 
 # Copy first changes the matchers to match standins instead of
 # largefiles.  Then it overrides util.copyfile in that function it
 # checks if the destination largefile already exists. It also keeps a
 # list of copied files so that the largefiles can be copied and the
 # dirstate updated.
 @eh.wrapfunction(cmdutil, 'copy')
 def overridecopy(orig, ui, repo, pats, opts, rename=False):
     # doesn't remove largefile on rename
     if len(pats) < 2:
         # this isn't legal, let the original function deal with it
         return orig(ui, repo, pats, opts, rename)
 
     # This could copy both lfiles and normal files in one command,
     # but we don't want to do that. First replace their matcher to
     # only match normal files and run it, then replace it to just
     # match largefiles and run it again.
     nonormalfiles = False
     nolfiles = False
     manifest = repo[None].manifest()
     def normalfilesmatchfn(orig, ctx, pats=(), opts=None, globbed=False,
         default='relpath', badfn=None):
         if opts is None:
             opts = {}
         match = orig(ctx, pats, opts, globbed, default, badfn=badfn)
         return composenormalfilematcher(match, manifest)
     with extensions.wrappedfunction(scmutil, 'match', normalfilesmatchfn):
         try:
             result = orig(ui, repo, pats, opts, rename)
         except error.Abort as e:
             if pycompat.bytestr(e) != _('no files to copy'):
                 raise e
             else:
                 nonormalfiles = True
             result = 0
 
     # The first rename can cause our current working directory to be removed.
     # In that case there is nothing left to copy/rename so just quit.
     try:
         repo.getcwd()
     except OSError:
         return result
 
     def makestandin(relpath):
         path = pathutil.canonpath(repo.root, repo.getcwd(), relpath)
         return repo.wvfs.join(lfutil.standin(path))
 
     fullpats = scmutil.expandpats(pats)
     dest = fullpats[-1]
 
     if os.path.isdir(dest):
         if not os.path.isdir(makestandin(dest)):
             os.makedirs(makestandin(dest))
 
     try:
         # When we call orig below it creates the standins but we don't add
         # them to the dir state until later so lock during that time.
         wlock = repo.wlock()
 
         manifest = repo[None].manifest()
         def overridematch(orig, ctx, pats=(), opts=None, globbed=False,
                 default='relpath', badfn=None):
             if opts is None:
                 opts = {}
             newpats = []
             # The patterns were previously mangled to add the standin
             # directory; we need to remove that now
             for pat in pats:
                 if matchmod.patkind(pat) is None and lfutil.shortname in pat:
                     newpats.append(pat.replace(lfutil.shortname, ''))
                 else:
                     newpats.append(pat)
             match = orig(ctx, newpats, opts, globbed, default, badfn=badfn)
             m = copy.copy(match)
             lfile = lambda f: lfutil.standin(f) in manifest
             m._files = [lfutil.standin(f) for f in m._files if lfile(f)]
             m._fileset = set(m._files)
             origmatchfn = m.matchfn
             def matchfn(f):
                 lfile = lfutil.splitstandin(f)
                 return (lfile is not None and
                         (f in manifest) and
                         origmatchfn(lfile) or
                         None)
             m.matchfn = matchfn
             return m
         listpats = []
         for pat in pats:
             if matchmod.patkind(pat) is not None:
                 listpats.append(pat)
             else:
                 listpats.append(makestandin(pat))
 
         copiedfiles = []
         def overridecopyfile(orig, src, dest, *args, **kwargs):
             if (lfutil.shortname in src and
                 dest.startswith(repo.wjoin(lfutil.shortname))):
                 destlfile = dest.replace(lfutil.shortname, '')
                 if not opts['force'] and os.path.exists(destlfile):
                     raise IOError('',
                                   _('destination largefile already exists'))
             copiedfiles.append((src, dest))
             orig(src, dest, *args, **kwargs)
         with extensions.wrappedfunction(util, 'copyfile', overridecopyfile), \
              extensions.wrappedfunction(scmutil, 'match', overridematch):
             result += orig(ui, repo, listpats, opts, rename)
 
         lfdirstate = lfutil.openlfdirstate(ui, repo)
         for (src, dest) in copiedfiles:
             if (lfutil.shortname in src and
                 dest.startswith(repo.wjoin(lfutil.shortname))):
                 srclfile = src.replace(repo.wjoin(lfutil.standin('')), '')
                 destlfile = dest.replace(repo.wjoin(lfutil.standin('')), '')
                 destlfiledir = repo.wvfs.dirname(repo.wjoin(destlfile)) or '.'
                 if not os.path.isdir(destlfiledir):
                     os.makedirs(destlfiledir)
                 if rename:
                     os.rename(repo.wjoin(srclfile), repo.wjoin(destlfile))
 
                     # The file is gone, but this deletes any empty parent
                     # directories as a side-effect.
                     repo.wvfs.unlinkpath(srclfile, ignoremissing=True)
                     lfdirstate.remove(srclfile)
                 else:
                     util.copyfile(repo.wjoin(srclfile),
                                   repo.wjoin(destlfile))
 
                 lfdirstate.add(destlfile)
         lfdirstate.write()
     except error.Abort as e:
         if pycompat.bytestr(e) != _('no files to copy'):
             raise e
         else:
             nolfiles = True
     finally:
         wlock.release()
 
     if nolfiles and nonormalfiles:
         raise error.Abort(_('no files to copy'))
 
     return result
 
 # When the user calls revert, we have to be careful to not revert any
 # changes to other largefiles accidentally. This means we have to keep
 # track of the largefiles that are being reverted so we only pull down
 # the necessary largefiles.
 #
 # Standins are only updated (to match the hash of largefiles) before
 # commits. Update the standins then run the original revert, changing
 # the matcher to hit standins instead of largefiles. Based on the
 # resulting standins update the largefiles.
 @eh.wrapfunction(cmdutil, 'revert')
 def overriderevert(orig, ui, repo, ctx, parents, *pats, **opts):
     # Because we put the standins in a bad state (by updating them)
     # and then return them to a correct state we need to lock to
     # prevent others from changing them in their incorrect state.
     with repo.wlock():
         lfdirstate = lfutil.openlfdirstate(ui, repo)
         s = lfutil.lfdirstatestatus(lfdirstate, repo)
         lfdirstate.write()
         for lfile in s.modified:
             lfutil.updatestandin(repo, lfile, lfutil.standin(lfile))
         for lfile in s.deleted:
             fstandin = lfutil.standin(lfile)
             if (repo.wvfs.exists(fstandin)):
                 repo.wvfs.unlink(fstandin)
 
         oldstandins = lfutil.getstandinsstate(repo)
 
         def overridematch(orig, mctx, pats=(), opts=None, globbed=False,
                 default='relpath', badfn=None):
             if opts is None:
                 opts = {}
             match = orig(mctx, pats, opts, globbed, default, badfn=badfn)
             m = copy.copy(match)
 
             # revert supports recursing into subrepos, and though largefiles
             # currently doesn't work correctly in that case, this match is
             # called, so the lfdirstate above may not be the correct one for
             # this invocation of match.
             lfdirstate = lfutil.openlfdirstate(mctx.repo().ui, mctx.repo(),
                                                False)
 
             wctx = repo[None]
             matchfiles = []
             for f in m._files:
                 standin = lfutil.standin(f)
                 if standin in ctx or standin in mctx:
                     matchfiles.append(standin)
                 elif standin in wctx or lfdirstate[f] == 'r':
                     continue
                 else:
                     matchfiles.append(f)
             m._files = matchfiles
             m._fileset = set(m._files)
             origmatchfn = m.matchfn
             def matchfn(f):
                 lfile = lfutil.splitstandin(f)
                 if lfile is not None:
                     return (origmatchfn(lfile) and
                             (f in ctx or f in mctx))
                 return origmatchfn(f)
             m.matchfn = matchfn
             return m
         with extensions.wrappedfunction(scmutil, 'match', overridematch):
             orig(ui, repo, ctx, parents, *pats, **opts)
 
         newstandins = lfutil.getstandinsstate(repo)
         filelist = lfutil.getlfilestoupdate(oldstandins, newstandins)
         # lfdirstate should be 'normallookup'-ed for updated files,
         # because reverting doesn't touch dirstate for 'normal' files
         # when target revision is explicitly specified: in such case,
         # 'n' and valid timestamp in dirstate doesn't ensure 'clean'
         # of target (standin) file.
         lfcommands.updatelfiles(ui, repo, filelist, printmessage=False,
                                 normallookup=True)
 
 # after pulling changesets, we need to take some extra care to get
 # largefiles updated remotely
 @eh.wrapcommand('pull',
     opts=[('', 'all-largefiles', None,
                 _('download all pulled versions of largefiles (DEPRECATED)')),
           ('', 'lfrev', [],
                 _('download largefiles for these revisions'), _('REV'))])
 def overridepull(orig, ui, repo, source=None, **opts):
     revsprepull = len(repo)
     if not source:
         source = 'default'
     repo.lfpullsource = source
     result = orig(ui, repo, source, **opts)
     revspostpull = len(repo)
     lfrevs = opts.get(r'lfrev', [])
     if opts.get(r'all_largefiles'):
         lfrevs.append('pulled()')
     if lfrevs and revspostpull > revsprepull:
         numcached = 0
         repo.firstpulled = revsprepull # for pulled() revset expression
         try:
             for rev in scmutil.revrange(repo, lfrevs):
                 ui.note(_('pulling largefiles for revision %d\n') % rev)
                 (cached, missing) = lfcommands.cachelfiles(ui, repo, rev)
                 numcached += len(cached)
         finally:
             del repo.firstpulled
         ui.status(_("%d largefiles cached\n") % numcached)
     return result
 
 @eh.wrapcommand('push',
     opts=[('', 'lfrev', [],
                _('upload largefiles for these revisions'), _('REV'))])
 def overridepush(orig, ui, repo, *args, **kwargs):
     """Override push command and store --lfrev parameters in opargs"""
     lfrevs = kwargs.pop(r'lfrev', None)
     if lfrevs:
         opargs = kwargs.setdefault(r'opargs', {})
         opargs['lfrevs'] = scmutil.revrange(repo, lfrevs)
     return orig(ui, repo, *args, **kwargs)
 
 @eh.wrapfunction(exchange, 'pushoperation')
 def exchangepushoperation(orig, *args, **kwargs):
     """Override pushoperation constructor and store lfrevs parameter"""
     lfrevs = kwargs.pop(r'lfrevs', None)
     pushop = orig(*args, **kwargs)
     pushop.lfrevs = lfrevs
     return pushop
 
 @eh.revsetpredicate('pulled()')
 def pulledrevsetsymbol(repo, subset, x):
     """Changesets that just has been pulled.
 
     Only available with largefiles from pull --lfrev expressions.
 
     .. container:: verbose
 
       Some examples:
 
       - pull largefiles for all new changesets::
 
           hg pull -lfrev "pulled()"
 
       - pull largefiles for all new branch heads::
 
           hg pull -lfrev "head(pulled()) and not closed()"
 
     """
 
     try:
         firstpulled = repo.firstpulled
     except AttributeError:
         raise error.Abort(_("pulled() only available in --lfrev"))
     return smartset.baseset([r for r in subset if r >= firstpulled])
 
 @eh.wrapcommand('clone',
     opts=[('', 'all-largefiles', None,
                _('download all versions of all largefiles'))])
 def overrideclone(orig, ui, source, dest=None, **opts):
     d = dest
     if d is None:
         d = hg.defaultdest(source)
     if opts.get(r'all_largefiles') and not hg.islocal(d):
             raise error.Abort(_(
             '--all-largefiles is incompatible with non-local destination %s') %
             d)
 
     return orig(ui, source, dest, **opts)
 
 @eh.wrapfunction(hg, 'clone')
 def hgclone(orig, ui, opts, *args, **kwargs):
     result = orig(ui, opts, *args, **kwargs)
 
     if result is not None:
         sourcerepo, destrepo = result
         repo = destrepo.local()
 
         # When cloning to a remote repo (like through SSH), no repo is available
         # from the peer.   Therefore the largefiles can't be downloaded and the
         # hgrc can't be updated.
         if not repo:
             return result
 
         # Caching is implicitly limited to 'rev' option, since the dest repo was
         # truncated at that point.  The user may expect a download count with
         # this option, so attempt whether or not this is a largefile repo.
         if opts.get('all_largefiles'):
             success, missing = lfcommands.downloadlfiles(ui, repo, None)
 
             if missing != 0:
                 return None
 
     return result
 
 @eh.wrapcommand('rebase', extension='rebase')
 def overriderebase(orig, ui, repo, **opts):
     if not util.safehasattr(repo, '_largefilesenabled'):
         return orig(ui, repo, **opts)
 
     resuming = opts.get(r'continue')
     repo._lfcommithooks.append(lfutil.automatedcommithook(resuming))
     repo._lfstatuswriters.append(lambda *msg, **opts: None)
     try:
         return orig(ui, repo, **opts)
     finally:
         repo._lfstatuswriters.pop()
         repo._lfcommithooks.pop()
 
 @eh.wrapcommand('archive')
 def overridearchivecmd(orig, ui, repo, dest, **opts):
     repo.unfiltered().lfstatus = True
 
     try:
         return orig(ui, repo.unfiltered(), dest, **opts)
     finally:
         repo.unfiltered().lfstatus = False
 
 @eh.wrapfunction(webcommands, 'archive')
 def hgwebarchive(orig, web):
     web.repo.lfstatus = True
 
     try:
         return orig(web)
     finally:
         web.repo.lfstatus = False
 
 @eh.wrapfunction(archival, 'archive')
 def overridearchive(orig, repo, dest, node, kind, decode=True, match=None,
             prefix='', mtime=None, subrepos=None):
     # For some reason setting repo.lfstatus in hgwebarchive only changes the
     # unfiltered repo's attr, so check that as well.
     if not repo.lfstatus and not repo.unfiltered().lfstatus:
         return orig(repo, dest, node, kind, decode, match, prefix, mtime,
                     subrepos)
 
     # No need to lock because we are only reading history and
     # largefile caches, neither of which are modified.
     if node is not None:
         lfcommands.cachelfiles(repo.ui, repo, node)
 
     if kind not in archival.archivers:
         raise error.Abort(_("unknown archive type '%s'") % kind)
 
     ctx = repo[node]
 
     if kind == 'files':
         if prefix:
             raise error.Abort(
                 _('cannot give prefix when archiving to files'))
     else:
         prefix = archival.tidyprefix(dest, kind, prefix)
 
     def write(name, mode, islink, getdata):
         if match and not match(name):
             return
         data = getdata()
         if decode:
             data = repo.wwritedata(name, data)
         archiver.addfile(prefix + name, mode, islink, data)
 
     archiver = archival.archivers[kind](dest, mtime or ctx.date()[0])
 
     if repo.ui.configbool("ui", "archivemeta"):
         write('.hg_archival.txt', 0o644, False,
               lambda: archival.buildmetadata(ctx))
 
     for f in ctx:
         ff = ctx.flags(f)
         getdata = ctx[f].data
         lfile = lfutil.splitstandin(f)
         if lfile is not None:
             if node is not None:
                 path = lfutil.findfile(repo, getdata().strip())
 
                 if path is None:
                     raise error.Abort(
                        _('largefile %s not found in repo store or system cache')
                        % lfile)
             else:
                 path = lfile
 
             f = lfile
 
             getdata = lambda: util.readfile(path)
         write(f, 'x' in ff and 0o755 or 0o644, 'l' in ff, getdata)
 
     if subrepos:
         for subpath in sorted(ctx.substate):
             sub = ctx.workingsub(subpath)
             submatch = matchmod.subdirmatcher(subpath, match)
             subprefix = prefix + subpath + '/'
             sub._repo.lfstatus = True
             sub.archive(archiver, subprefix, submatch)
 
     archiver.done()
 
 @eh.wrapfunction(subrepo.hgsubrepo, 'archive')
 def hgsubrepoarchive(orig, repo, archiver, prefix, match=None, decode=True):
     lfenabled = util.safehasattr(repo._repo, '_largefilesenabled')
     if not lfenabled or not repo._repo.lfstatus:
         return orig(repo, archiver, prefix, match, decode)
 
     repo._get(repo._state + ('hg',))
     rev = repo._state[1]
     ctx = repo._repo[rev]
 
     if ctx.node() is not None:
         lfcommands.cachelfiles(repo.ui, repo._repo, ctx.node())
 
     def write(name, mode, islink, getdata):
         # At this point, the standin has been replaced with the largefile name,
         # so the normal matcher works here without the lfutil variants.
         if match and not match(f):
             return
         data = getdata()
         if decode:
             data = repo._repo.wwritedata(name, data)
 
         archiver.addfile(prefix + name, mode, islink, data)
 
     for f in ctx:
         ff = ctx.flags(f)
         getdata = ctx[f].data
         lfile = lfutil.splitstandin(f)
         if lfile is not None:
             if ctx.node() is not None:
                 path = lfutil.findfile(repo._repo, getdata().strip())
 
                 if path is None:
                     raise error.Abort(
                        _('largefile %s not found in repo store or system cache')
                        % lfile)
             else:
                 path = lfile
 
             f = lfile
 
             getdata = lambda: util.readfile(os.path.join(prefix, path))
 
         write(f, 'x' in ff and 0o755 or 0o644, 'l' in ff, getdata)
 
     for subpath in sorted(ctx.substate):
         sub = ctx.workingsub(subpath)
         submatch = matchmod.subdirmatcher(subpath, match)
         subprefix = prefix + subpath + '/'
         sub._repo.lfstatus = True
         sub.archive(archiver, subprefix, submatch, decode)
 
 # If a largefile is modified, the change is not reflected in its
 # standin until a commit. cmdutil.bailifchanged() raises an exception
 # if the repo has uncommitted changes. Wrap it to also check if
 # largefiles were changed. This is used by bisect, backout and fetch.
 @eh.wrapfunction(cmdutil, 'bailifchanged')
 def overridebailifchanged(orig, repo, *args, **kwargs):
     orig(repo, *args, **kwargs)
     repo.lfstatus = True
     s = repo.status()
     repo.lfstatus = False
     if s.modified or s.added or s.removed or s.deleted:
         raise error.Abort(_('uncommitted changes'))
 
 @eh.wrapfunction(cmdutil, 'postcommitstatus')
 def postcommitstatus(orig, repo, *args, **kwargs):
     repo.lfstatus = True
     try:
         return orig(repo, *args, **kwargs)
     finally:
         repo.lfstatus = False
 
 @eh.wrapfunction(cmdutil, 'forget')
 def cmdutilforget(orig, ui, repo, match, prefix, uipathfn, explicitonly, dryrun,
                   interactive):
     normalmatcher = composenormalfilematcher(match, repo[None].manifest())
     bad, forgot = orig(ui, repo, normalmatcher, prefix, uipathfn, explicitonly,
                        dryrun, interactive)
     m = composelargefilematcher(match, repo[None].manifest())
 
     try:
         repo.lfstatus = True
         s = repo.status(match=m, clean=True)
     finally:
         repo.lfstatus = False
     manifest = repo[None].manifest()
     forget = sorted(s.modified + s.added + s.deleted + s.clean)
     forget = [f for f in forget if lfutil.standin(f) in manifest]
 
     for f in forget:
         fstandin = lfutil.standin(f)
         if fstandin not in repo.dirstate and not repo.wvfs.isdir(fstandin):
             ui.warn(_('not removing %s: file is already untracked\n')
                     % uipathfn(f))
             bad.append(f)
 
     for f in forget:
         if ui.verbose or not m.exact(f):
             ui.status(_('removing %s\n') % uipathfn(f))
 
     # Need to lock because standin files are deleted then removed from the
     # repository and we could race in-between.
     with repo.wlock():
         lfdirstate = lfutil.openlfdirstate(ui, repo)
         for f in forget:
             if lfdirstate[f] == 'a':
                 lfdirstate.drop(f)
             else:
                 lfdirstate.remove(f)
         lfdirstate.write()
         standins = [lfutil.standin(f) for f in forget]
         for f in standins:
             repo.wvfs.unlinkpath(f, ignoremissing=True)
         rejected = repo[None].forget(standins)
 
     bad.extend(f for f in rejected if f in m.files())
     forgot.extend(f for f in forget if f not in rejected)
     return bad, forgot
 
 def _getoutgoings(repo, other, missing, addfunc):
     """get pairs of filename and largefile hash in outgoing revisions
     in 'missing'.
 
     largefiles already existing on 'other' repository are ignored.
 
     'addfunc' is invoked with each unique pairs of filename and
     largefile hash value.
     """
     knowns = set()
     lfhashes = set()
     def dedup(fn, lfhash):
         k = (fn, lfhash)
         if k not in knowns:
             knowns.add(k)
             lfhashes.add(lfhash)
     lfutil.getlfilestoupload(repo, missing, dedup)
     if lfhashes:
         lfexists = storefactory.openstore(repo, other).exists(lfhashes)
         for fn, lfhash in knowns:
             if not lfexists[lfhash]: # lfhash doesn't exist on "other"
                 addfunc(fn, lfhash)
 
 def outgoinghook(ui, repo, other, opts, missing):
     if opts.pop('large', None):
         lfhashes = set()
         if ui.debugflag:
             toupload = {}
             def addfunc(fn, lfhash):
                 if fn not in toupload:
                     toupload[fn] = []
                 toupload[fn].append(lfhash)
                 lfhashes.add(lfhash)
             def showhashes(fn):
                 for lfhash in sorted(toupload[fn]):
                     ui.debug('    %s\n' % (lfhash))
         else:
             toupload = set()
             def addfunc(fn, lfhash):
                 toupload.add(fn)
                 lfhashes.add(lfhash)
             def showhashes(fn):
                 pass
         _getoutgoings(repo, other, missing, addfunc)
 
         if not toupload:
             ui.status(_('largefiles: no files to upload\n'))
         else:
             ui.status(_('largefiles to upload (%d entities):\n')
                       % (len(lfhashes)))
             for file in sorted(toupload):
                 ui.status(lfutil.splitstandin(file) + '\n')
                 showhashes(file)
             ui.status('\n')
 
 @eh.wrapcommand('outgoing',
     opts=[('', 'large', None, _('display outgoing largefiles'))])
 def _outgoingcmd(orig, *args, **kwargs):
     # Nothing to do here other than add the extra help option- the hook above
     # processes it.
     return orig(*args, **kwargs)
 
 def summaryremotehook(ui, repo, opts, changes):
     largeopt = opts.get('large', False)
     if changes is None:
         if largeopt:
             return (False, True) # only outgoing check is needed
         else:
             return (False, False)
     elif largeopt:
         url, branch, peer, outgoing = changes[1]
         if peer is None:
             # i18n: column positioning for "hg summary"
             ui.status(_('largefiles: (no remote repo)\n'))
             return
 
         toupload = set()
         lfhashes = set()
         def addfunc(fn, lfhash):
             toupload.add(fn)
             lfhashes.add(lfhash)
         _getoutgoings(repo, peer, outgoing.missing, addfunc)
 
         if not toupload:
             # i18n: column positioning for "hg summary"
             ui.status(_('largefiles: (no files to upload)\n'))
         else:
             # i18n: column positioning for "hg summary"
             ui.status(_('largefiles: %d entities for %d files to upload\n')
                       % (len(lfhashes), len(toupload)))
 
 @eh.wrapcommand('summary',
     opts=[('', 'large', None, _('display outgoing largefiles'))])
 def overridesummary(orig, ui, repo, *pats, **opts):
     try:
         repo.lfstatus = True
         orig(ui, repo, *pats, **opts)
     finally:
         repo.lfstatus = False
 
 @eh.wrapfunction(scmutil, 'addremove')
 def scmutiladdremove(orig, repo, matcher, prefix, uipathfn, opts=None):
     if opts is None:
         opts = {}
     if not lfutil.islfilesrepo(repo):
         return orig(repo, matcher, prefix, uipathfn, opts)
     # Get the list of missing largefiles so we can remove them
     lfdirstate = lfutil.openlfdirstate(repo.ui, repo)
-    unsure, s = lfdirstate.status(matchmod.always(repo.root, repo.getcwd()),
-                                  subrepos=[], ignored=False, clean=False,
-                                  unknown=False)
+    unsure, s = lfdirstate.status(matchmod.always(), subrepos=[],
+                                  ignored=False, clean=False, unknown=False)
 
     # Call into the normal remove code, but the removing of the standin, we want
     # to have handled by original addremove.  Monkey patching here makes sure
     # we don't remove the standin in the largefiles code, preventing a very
     # confused state later.
     if s.deleted:
         m = copy.copy(matcher)
 
         # The m._files and m._map attributes are not changed to the deleted list
         # because that affects the m.exact() test, which in turn governs whether
         # or not the file name is printed, and how.  Simply limit the original
         # matches to those in the deleted status list.
         matchfn = m.matchfn
         m.matchfn = lambda f: f in s.deleted and matchfn(f)
 
         removelargefiles(repo.ui, repo, True, m, uipathfn, opts.get('dry_run'),
                          **pycompat.strkwargs(opts))
     # Call into the normal add code, and any files that *should* be added as
     # largefiles will be
     added, bad = addlargefiles(repo.ui, repo, True, matcher, uipathfn,
                                **pycompat.strkwargs(opts))
     # Now that we've handled largefiles, hand off to the original addremove
     # function to take care of the rest.  Make sure it doesn't do anything with
     # largefiles by passing a matcher that will ignore them.
     matcher = composenormalfilematcher(matcher, repo[None].manifest(), added)
     return orig(repo, matcher, prefix, uipathfn, opts)
 
 # Calling purge with --all will cause the largefiles to be deleted.
 # Override repo.status to prevent this from happening.
 @eh.wrapcommand('purge', extension='purge')
 def overridepurge(orig, ui, repo, *dirs, **opts):
     # XXX Monkey patching a repoview will not work. The assigned attribute will
     # be set on the unfiltered repo, but we will only lookup attributes in the
     # unfiltered repo if the lookup in the repoview object itself fails. As the
     # monkey patched method exists on the repoview class the lookup will not
     # fail. As a result, the original version will shadow the monkey patched
     # one, defeating the monkey patch.
     #
     # As a work around we use an unfiltered repo here. We should do something
     # cleaner instead.
     repo = repo.unfiltered()
     oldstatus = repo.status
     def overridestatus(node1='.', node2=None, match=None, ignored=False,
                         clean=False, unknown=False, listsubrepos=False):
         r = oldstatus(node1, node2, match, ignored, clean, unknown,
                       listsubrepos)
         lfdirstate = lfutil.openlfdirstate(ui, repo)
         unknown = [f for f in r.unknown if lfdirstate[f] == '?']
         ignored = [f for f in r.ignored if lfdirstate[f] == '?']
         return scmutil.status(r.modified, r.added, r.removed, r.deleted,
                               unknown, ignored, r.clean)
     repo.status = overridestatus
     orig(ui, repo, *dirs, **opts)
     repo.status = oldstatus
 
 @eh.wrapcommand('rollback')
 def overriderollback(orig, ui, repo, **opts):
     with repo.wlock():
         before = repo.dirstate.parents()
         orphans = set(f for f in repo.dirstate
                       if lfutil.isstandin(f) and repo.dirstate[f] != 'r')
         result = orig(ui, repo, **opts)
         after = repo.dirstate.parents()
         if before == after:
             return result # no need to restore standins
 
         pctx = repo['.']
         for f in repo.dirstate:
             if lfutil.isstandin(f):
                 orphans.discard(f)
                 if repo.dirstate[f] == 'r':
                     repo.wvfs.unlinkpath(f, ignoremissing=True)
                 elif f in pctx:
                     fctx = pctx[f]
                     repo.wwrite(f, fctx.data(), fctx.flags())
                 else:
                     # content of standin is not so important in 'a',
                     # 'm' or 'n' (coming from the 2nd parent) cases
                     lfutil.writestandin(repo, f, '', False)
         for standin in orphans:
             repo.wvfs.unlinkpath(standin, ignoremissing=True)
 
         lfdirstate = lfutil.openlfdirstate(ui, repo)
         orphans = set(lfdirstate)
         lfiles = lfutil.listlfiles(repo)
         for file in lfiles:
             lfutil.synclfdirstate(repo, lfdirstate, file, True)
             orphans.discard(file)
         for lfile in orphans:
             lfdirstate.drop(lfile)
         lfdirstate.write()
     return result
 
 @eh.wrapcommand('transplant', extension='transplant')
 def overridetransplant(orig, ui, repo, *revs, **opts):
     resuming = opts.get(r'continue')
     repo._lfcommithooks.append(lfutil.automatedcommithook(resuming))
     repo._lfstatuswriters.append(lambda *msg, **opts: None)
     try:
         result = orig(ui, repo, *revs, **opts)
     finally:
         repo._lfstatuswriters.pop()
         repo._lfcommithooks.pop()
     return result
 
 @eh.wrapcommand('cat')
 def overridecat(orig, ui, repo, file1, *pats, **opts):
     opts = pycompat.byteskwargs(opts)
     ctx = scmutil.revsingle(repo, opts.get('rev'))
     err = 1
     notbad = set()
     m = scmutil.match(ctx, (file1,) + pats, opts)
     origmatchfn = m.matchfn
     def lfmatchfn(f):
         if origmatchfn(f):
             return True
         lf = lfutil.splitstandin(f)
         if lf is None:
             return False
         notbad.add(lf)
         return origmatchfn(lf)
     m.matchfn = lfmatchfn
     origbadfn = m.bad
     def lfbadfn(f, msg):
         if not f in notbad:
             origbadfn(f, msg)
     m.bad = lfbadfn
 
     origvisitdirfn = m.visitdir
     def lfvisitdirfn(dir):
         if dir == lfutil.shortname:
             return True
         ret = origvisitdirfn(dir)
         if ret:
             return ret
         lf = lfutil.splitstandin(dir)
         if lf is None:
             return False
         return origvisitdirfn(lf)
     m.visitdir = lfvisitdirfn
 
     for f in ctx.walk(m):
         with cmdutil.makefileobj(ctx, opts.get('output'), pathname=f) as fp:
             lf = lfutil.splitstandin(f)
             if lf is None or origmatchfn(f):
                 # duplicating unreachable code from commands.cat
                 data = ctx[f].data()
                 if opts.get('decode'):
                     data = repo.wwritedata(f, data)
                 fp.write(data)
             else:
                 hash = lfutil.readasstandin(ctx[f])
                 if not lfutil.inusercache(repo.ui, hash):
                     store = storefactory.openstore(repo)
                     success, missing = store.get([(lf, hash)])
                     if len(success) != 1:
                         raise error.Abort(
                             _('largefile %s is not in cache and could not be '
                               'downloaded')  % lf)
                 path = lfutil.usercachepath(repo.ui, hash)
                 with open(path, "rb") as fpin:
                     for chunk in util.filechunkiter(fpin):
                         fp.write(chunk)
         err = 0
     return err
 
 @eh.wrapfunction(merge, 'update')
 def mergeupdate(orig, repo, node, branchmerge, force,
                 *args, **kwargs):
     matcher = kwargs.get(r'matcher', None)
     # note if this is a partial update
     partial = matcher and not matcher.always()
     with repo.wlock():
         # branch |       |         |
         #  merge | force | partial | action
         # -------+-------+---------+--------------
         #    x   |   x   |    x    | linear-merge
         #    o   |   x   |    x    | branch-merge
         #    x   |   o   |    x    | overwrite (as clean update)
         #    o   |   o   |    x    | force-branch-merge (*1)
         #    x   |   x   |    o    |   (*)
         #    o   |   x   |    o    |   (*)
         #    x   |   o   |    o    | overwrite (as revert)
         #    o   |   o   |    o    |   (*)
         #
         # (*) don't care
         # (*1) deprecated, but used internally (e.g: "rebase --collapse")
 
         lfdirstate = lfutil.openlfdirstate(repo.ui, repo)
-        unsure, s = lfdirstate.status(matchmod.always(repo.root,
-                                                    repo.getcwd()),
-                                      subrepos=[], ignored=False,
-                                      clean=True, unknown=False)
+        unsure, s = lfdirstate.status(matchmod.always(), subrepos=[],
+                                      ignored=False, clean=True, unknown=False)
         oldclean = set(s.clean)
         pctx = repo['.']
         dctx = repo[node]
         for lfile in unsure + s.modified:
             lfileabs = repo.wvfs.join(lfile)
             if not repo.wvfs.exists(lfileabs):
                 continue
             lfhash = lfutil.hashfile(lfileabs)
             standin = lfutil.standin(lfile)
             lfutil.writestandin(repo, standin, lfhash,
                                 lfutil.getexecutable(lfileabs))
             if (standin in pctx and
                 lfhash == lfutil.readasstandin(pctx[standin])):
                 oldclean.add(lfile)
         for lfile in s.added:
             fstandin = lfutil.standin(lfile)
             if fstandin not in dctx:
                 # in this case, content of standin file is meaningless
                 # (in dctx, lfile is unknown, or normal file)
                 continue
             lfutil.updatestandin(repo, lfile, fstandin)
         # mark all clean largefiles as dirty, just in case the update gets
         # interrupted before largefiles and lfdirstate are synchronized
         for lfile in oldclean:
             lfdirstate.normallookup(lfile)
         lfdirstate.write()
 
         oldstandins = lfutil.getstandinsstate(repo)
         # Make sure the merge runs on disk, not in-memory. largefiles is not a
         # good candidate for in-memory merge (large files, custom dirstate,
         # matcher usage).
         kwargs[r'wc'] = repo[None]
         result = orig(repo, node, branchmerge, force, *args, **kwargs)
 
         newstandins = lfutil.getstandinsstate(repo)
         filelist = lfutil.getlfilestoupdate(oldstandins, newstandins)
 
         # to avoid leaving all largefiles as dirty and thus rehash them, mark
         # all the ones that didn't change as clean
         for lfile in oldclean.difference(filelist):
             lfdirstate.normal(lfile)
         lfdirstate.write()
 
         if branchmerge or force or partial:
             filelist.extend(s.deleted + s.removed)
 
         lfcommands.updatelfiles(repo.ui, repo, filelist=filelist,
                                 normallookup=partial)
 
         return result
 
 @eh.wrapfunction(scmutil, 'marktouched')
 def scmutilmarktouched(orig, repo, files, *args, **kwargs):
     result = orig(repo, files, *args, **kwargs)
 
     filelist = []
     for f in files:
         lf = lfutil.splitstandin(f)
         if lf is not None:
             filelist.append(lf)
     if filelist:
         lfcommands.updatelfiles(repo.ui, repo, filelist=filelist,
                                 printmessage=False, normallookup=True)
 
     return result
 
 @eh.wrapfunction(upgrade, 'preservedrequirements')
 @eh.wrapfunction(upgrade, 'supporteddestrequirements')
 def upgraderequirements(orig, repo):
     reqs = orig(repo)
     if 'largefiles' in repo.requirements:
         reqs.add('largefiles')
     return reqs
 
 _lfscheme = 'largefile://'
 
 @eh.wrapfunction(urlmod, 'open')
 def openlargefile(orig, ui, url_, data=None):
     if url_.startswith(_lfscheme):
         if data:
             msg = "cannot use data on a 'largefile://' url"
             raise error.ProgrammingError(msg)
         lfid = url_[len(_lfscheme):]
         return storefactory.getlfile(ui, lfid)
     else:
         return orig(ui, url_, data=data)

hgext/largefiles/reposetup.py

@@ -1,393 +1,393 b''
 # Copyright 2009-2010 Gregory P. Ward
 # Copyright 2009-2010 Intelerad Medical Systems Incorporated
 # Copyright 2010-2011 Fog Creek Software
 # Copyright 2010-2011 Unity Technologies
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 '''setup for largefiles repositories: reposetup'''
 from __future__ import absolute_import
 
 import copy
 
 from mercurial.i18n import _
 
 from mercurial import (
     error,
     localrepo,
     match as matchmod,
     scmutil,
 )
 
 from . import (
     lfcommands,
     lfutil,
 )
 
 def reposetup(ui, repo):
     # wire repositories should be given new wireproto functions
     # by "proto.wirereposetup()" via "hg.wirepeersetupfuncs"
     if not repo.local():
         return
 
     class lfilesrepo(repo.__class__):
         # the mark to examine whether "repo" object enables largefiles or not
         _largefilesenabled = True
 
         lfstatus = False
         def status_nolfiles(self, *args, **kwargs):
             return super(lfilesrepo, self).status(*args, **kwargs)
 
         # When lfstatus is set, return a context that gives the names
         # of largefiles instead of their corresponding standins and
         # identifies the largefiles as always binary, regardless of
         # their actual contents.
         def __getitem__(self, changeid):
             ctx = super(lfilesrepo, self).__getitem__(changeid)
             if self.lfstatus:
                 class lfilesctx(ctx.__class__):
                     def files(self):
                         filenames = super(lfilesctx, self).files()
                         return [lfutil.splitstandin(f) or f for f in filenames]
                     def manifest(self):
                         man1 = super(lfilesctx, self).manifest()
                         class lfilesmanifest(man1.__class__):
                             def __contains__(self, filename):
                                 orig = super(lfilesmanifest, self).__contains__
                                 return (orig(filename) or
                                         orig(lfutil.standin(filename)))
                         man1.__class__ = lfilesmanifest
                         return man1
                     def filectx(self, path, fileid=None, filelog=None):
                         orig = super(lfilesctx, self).filectx
                         try:
                             if filelog is not None:
                                 result = orig(path, fileid, filelog)
                             else:
                                 result = orig(path, fileid)
                         except error.LookupError:
                             # Adding a null character will cause Mercurial to
                             # identify this as a binary file.
                             if filelog is not None:
                                 result = orig(lfutil.standin(path), fileid,
                                               filelog)
                             else:
                                 result = orig(lfutil.standin(path), fileid)
                             olddata = result.data
                             result.data = lambda: olddata() + '\0'
                         return result
                 ctx.__class__ = lfilesctx
             return ctx
 
         # Figure out the status of big files and insert them into the
         # appropriate list in the result. Also removes standin files
         # from the listing. Revert to the original status if
         # self.lfstatus is False.
         # XXX large file status is buggy when used on repo proxy.
         # XXX this needs to be investigated.
         @localrepo.unfilteredmethod
         def status(self, node1='.', node2=None, match=None, ignored=False,
                 clean=False, unknown=False, listsubrepos=False):
             listignored, listclean, listunknown = ignored, clean, unknown
             orig = super(lfilesrepo, self).status
             if not self.lfstatus:
                 return orig(node1, node2, match, listignored, listclean,
                             listunknown, listsubrepos)
 
             # some calls in this function rely on the old version of status
             self.lfstatus = False
             ctx1 = self[node1]
             ctx2 = self[node2]
             working = ctx2.rev() is None
             parentworking = working and ctx1 == self['.']
 
             if match is None:
-                match = matchmod.always(self.root, self.getcwd())
+                match = matchmod.always()
 
             wlock = None
             try:
                 try:
                     # updating the dirstate is optional
                     # so we don't wait on the lock
                     wlock = self.wlock(False)
                 except error.LockError:
                     pass
 
                 # First check if paths or patterns were specified on the
                 # command line.  If there were, and they don't match any
                 # largefiles, we should just bail here and let super
                 # handle it -- thus gaining a big performance boost.
                 lfdirstate = lfutil.openlfdirstate(ui, self)
                 if not match.always():
                     for f in lfdirstate:
                         if match(f):
                             break
                     else:
                         return orig(node1, node2, match, listignored, listclean,
                                     listunknown, listsubrepos)
 
                 # Create a copy of match that matches standins instead
                 # of largefiles.
                 def tostandins(files):
                     if not working:
                         return files
                     newfiles = []
                     dirstate = self.dirstate
                     for f in files:
                         sf = lfutil.standin(f)
                         if sf in dirstate:
                             newfiles.append(sf)
                         elif dirstate.hasdir(sf):
                             # Directory entries could be regular or
                             # standin, check both
                             newfiles.extend((f, sf))
                         else:
                             newfiles.append(f)
                     return newfiles
 
                 m = copy.copy(match)
                 m._files = tostandins(m._files)
 
                 result = orig(node1, node2, m, ignored, clean, unknown,
                               listsubrepos)
                 if working:
 
                     def sfindirstate(f):
                         sf = lfutil.standin(f)
                         dirstate = self.dirstate
                         return sf in dirstate or dirstate.hasdir(sf)
 
                     match._files = [f for f in match._files
                                     if sfindirstate(f)]
                     # Don't waste time getting the ignored and unknown
                     # files from lfdirstate
                     unsure, s = lfdirstate.status(match, subrepos=[],
                                                   ignored=False,
                                                   clean=listclean,
                                                   unknown=False)
                     (modified, added, removed, deleted, clean) = (
                         s.modified, s.added, s.removed, s.deleted, s.clean)
                     if parentworking:
                         for lfile in unsure:
                             standin = lfutil.standin(lfile)
                             if standin not in ctx1:
                                 # from second parent
                                 modified.append(lfile)
                             elif lfutil.readasstandin(ctx1[standin]) \
                                     != lfutil.hashfile(self.wjoin(lfile)):
                                 modified.append(lfile)
                             else:
                                 if listclean:
                                     clean.append(lfile)
                                 lfdirstate.normal(lfile)
                     else:
                         tocheck = unsure + modified + added + clean
                         modified, added, clean = [], [], []
                         checkexec = self.dirstate._checkexec
 
                         for lfile in tocheck:
                             standin = lfutil.standin(lfile)
                             if standin in ctx1:
                                 abslfile = self.wjoin(lfile)
                                 if ((lfutil.readasstandin(ctx1[standin]) !=
                                      lfutil.hashfile(abslfile)) or
                                     (checkexec and
                                      ('x' in ctx1.flags(standin)) !=
                                      bool(lfutil.getexecutable(abslfile)))):
                                     modified.append(lfile)
                                 elif listclean:
                                     clean.append(lfile)
                             else:
                                 added.append(lfile)
 
                         # at this point, 'removed' contains largefiles
                         # marked as 'R' in the working context.
                         # then, largefiles not managed also in the target
                         # context should be excluded from 'removed'.
                         removed = [lfile for lfile in removed
                                    if lfutil.standin(lfile) in ctx1]
 
                     # Standins no longer found in lfdirstate have been deleted
                     for standin in ctx1.walk(lfutil.getstandinmatcher(self)):
                         lfile = lfutil.splitstandin(standin)
                         if not match(lfile):
                             continue
                         if lfile not in lfdirstate:
                             deleted.append(lfile)
                             # Sync "largefile has been removed" back to the
                             # standin. Removing a file as a side effect of
                             # running status is gross, but the alternatives (if
                             # any) are worse.
                             self.wvfs.unlinkpath(standin, ignoremissing=True)
 
                     # Filter result lists
                     result = list(result)
 
                     # Largefiles are not really removed when they're
                     # still in the normal dirstate. Likewise, normal
                     # files are not really removed if they are still in
                     # lfdirstate. This happens in merges where files
                     # change type.
                     removed = [f for f in removed
                                if f not in self.dirstate]
                     result[2] = [f for f in result[2]
                                  if f not in lfdirstate]
 
                     lfiles = set(lfdirstate._map)
                     # Unknown files
                     result[4] = set(result[4]).difference(lfiles)
                     # Ignored files
                     result[5] = set(result[5]).difference(lfiles)
                     # combine normal files and largefiles
                     normals = [[fn for fn in filelist
                                 if not lfutil.isstandin(fn)]
                                for filelist in result]
                     lfstatus = (modified, added, removed, deleted, [], [],
                                 clean)
                     result = [sorted(list1 + list2)
                               for (list1, list2) in zip(normals, lfstatus)]
                 else: # not against working directory
                     result = [[lfutil.splitstandin(f) or f for f in items]
                               for items in result]
 
                 if wlock:
                     lfdirstate.write()
 
             finally:
                 if wlock:
                     wlock.release()
 
             self.lfstatus = True
             return scmutil.status(*result)
 
         def commitctx(self, ctx, *args, **kwargs):
             node = super(lfilesrepo, self).commitctx(ctx, *args, **kwargs)
             class lfilesctx(ctx.__class__):
                 def markcommitted(self, node):
                     orig = super(lfilesctx, self).markcommitted
                     return lfutil.markcommitted(orig, self, node)
             ctx.__class__ = lfilesctx
             return node
 
         # Before commit, largefile standins have not had their
         # contents updated to reflect the hash of their largefile.
         # Do that here.
         def commit(self, text="", user=None, date=None, match=None,
                 force=False, editor=False, extra=None):
             if extra is None:
                 extra = {}
             orig = super(lfilesrepo, self).commit
 
             with self.wlock():
                 lfcommithook = self._lfcommithooks[-1]
                 match = lfcommithook(self, match)
                 result = orig(text=text, user=user, date=date, match=match,
                                 force=force, editor=editor, extra=extra)
                 return result
 
         def push(self, remote, force=False, revs=None, newbranch=False):
             if remote.local():
                 missing = set(self.requirements) - remote.local().supported
                 if missing:
                     msg = _("required features are not"
                             " supported in the destination:"
                             " %s") % (', '.join(sorted(missing)))
                     raise error.Abort(msg)
             return super(lfilesrepo, self).push(remote, force=force, revs=revs,
                 newbranch=newbranch)
 
         # TODO: _subdirlfs should be moved into "lfutil.py", because
         # it is referred only from "lfutil.updatestandinsbymatch"
         def _subdirlfs(self, files, lfiles):
             '''
             Adjust matched file list
             If we pass a directory to commit whose only committable files
             are largefiles, the core commit code aborts before finding
             the largefiles.
             So we do the following:
             For directories that only have largefiles as matches,
             we explicitly add the largefiles to the match list and remove
             the directory.
             In other cases, we leave the match list unmodified.
             '''
             actualfiles = []
             dirs = []
             regulars = []
 
             for f in files:
                 if lfutil.isstandin(f + '/'):
                     raise error.Abort(
                         _('file "%s" is a largefile standin') % f,
                         hint=('commit the largefile itself instead'))
                 # Scan directories
                 if self.wvfs.isdir(f):
                     dirs.append(f)
                 else:
                     regulars.append(f)
 
             for f in dirs:
                 matcheddir = False
                 d = self.dirstate.normalize(f) + '/'
                 # Check for matched normal files
                 for mf in regulars:
                     if self.dirstate.normalize(mf).startswith(d):
                         actualfiles.append(f)
                         matcheddir = True
                         break
                 if not matcheddir:
                     # If no normal match, manually append
                     # any matching largefiles
                     for lf in lfiles:
                         if self.dirstate.normalize(lf).startswith(d):
                             actualfiles.append(lf)
                             if not matcheddir:
                                 # There may still be normal files in the dir, so
                                 # add a directory to the list, which
                                 # forces status/dirstate to walk all files and
                                 # call the match function on the matcher, even
                                 # on case sensitive filesystems.
                                 actualfiles.append('.')
                                 matcheddir = True
                 # Nothing in dir, so readd it
                 # and let commit reject it
                 if not matcheddir:
                     actualfiles.append(f)
 
             # Always add normal files
             actualfiles += regulars
             return actualfiles
 
     repo.__class__ = lfilesrepo
 
     # stack of hooks being executed before committing.
     # only last element ("_lfcommithooks[-1]") is used for each committing.
     repo._lfcommithooks = [lfutil.updatestandinsbymatch]
 
     # Stack of status writer functions taking "*msg, **opts" arguments
     # like "ui.status()". Only last element ("_lfstatuswriters[-1]")
     # is used to write status out.
     repo._lfstatuswriters = [ui.status]
 
     def prepushoutgoinghook(pushop):
         """Push largefiles for pushop before pushing revisions."""
         lfrevs = pushop.lfrevs
         if lfrevs is None:
             lfrevs = pushop.outgoing.missing
         if lfrevs:
             toupload = set()
             addfunc = lambda fn, lfhash: toupload.add(lfhash)
             lfutil.getlfilestoupload(pushop.repo, lfrevs,
                                      addfunc)
             lfcommands.uploadlfiles(ui, pushop.repo, pushop.remote, toupload)
     repo.prepushoutgoinghooks.add("largefiles", prepushoutgoinghook)
 
     def checkrequireslfiles(ui, repo, **kwargs):
         if 'largefiles' not in repo.requirements and any(
                 lfutil.shortname+'/' in f[0] for f in repo.store.datafiles()):
             repo.requirements.add('largefiles')
             repo._writerequirements()
 
     ui.setconfig('hooks', 'changegroup.lfiles', checkrequireslfiles,
                  'largefiles')
     ui.setconfig('hooks', 'commit.lfiles', checkrequireslfiles, 'largefiles')

hgext/remotefilelog/remotefilelogserver.py

@@ -1,404 +1,404 b''
 # remotefilelogserver.py - server logic for a remotefilelog server
 #
 # Copyright 2013 Facebook, Inc.
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 from __future__ import absolute_import
 
 import errno
 import os
 import stat
 import time
 import zlib
 
 from mercurial.i18n import _
 from mercurial.node import bin, hex, nullid
 from mercurial import (
     changegroup,
     changelog,
     context,
     error,
     extensions,
     match,
     store,
     streamclone,
     util,
     wireprotoserver,
     wireprototypes,
     wireprotov1server,
 )
 from .  import (
     constants,
     shallowutil,
 )
 
 _sshv1server = wireprotoserver.sshv1protocolhandler
 
 def setupserver(ui, repo):
     """Sets up a normal Mercurial repo so it can serve files to shallow repos.
     """
     onetimesetup(ui)
 
     # don't send files to shallow clients during pulls
     def generatefiles(orig, self, changedfiles, linknodes, commonrevs, source,
                       *args, **kwargs):
         caps = self._bundlecaps or []
         if constants.BUNDLE2_CAPABLITY in caps:
             # only send files that don't match the specified patterns
             includepattern = None
             excludepattern = None
             for cap in (self._bundlecaps or []):
                 if cap.startswith("includepattern="):
                     includepattern = cap[len("includepattern="):].split('\0')
                 elif cap.startswith("excludepattern="):
                     excludepattern = cap[len("excludepattern="):].split('\0')
 
-            m = match.always(repo.root, '')
+            m = match.always()
             if includepattern or excludepattern:
                 m = match.match(repo.root, '', None,
                     includepattern, excludepattern)
 
             changedfiles = list([f for f in changedfiles if not m(f)])
         return orig(self, changedfiles, linknodes, commonrevs, source,
                     *args, **kwargs)
 
     extensions.wrapfunction(
         changegroup.cgpacker, 'generatefiles', generatefiles)
 
 onetime = False
 def onetimesetup(ui):
     """Configures the wireprotocol for both clients and servers.
     """
     global onetime
     if onetime:
         return
     onetime = True
 
     # support file content requests
     wireprotov1server.wireprotocommand(
         'x_rfl_getflogheads', 'path', permission='pull')(getflogheads)
     wireprotov1server.wireprotocommand(
         'x_rfl_getfiles', '', permission='pull')(getfiles)
     wireprotov1server.wireprotocommand(
         'x_rfl_getfile', 'file node', permission='pull')(getfile)
 
     class streamstate(object):
         match = None
         shallowremote = False
         noflatmf = False
     state = streamstate()
 
     def stream_out_shallow(repo, proto, other):
         includepattern = None
         excludepattern = None
         raw = other.get('includepattern')
         if raw:
             includepattern = raw.split('\0')
         raw = other.get('excludepattern')
         if raw:
             excludepattern = raw.split('\0')
 
         oldshallow = state.shallowremote
         oldmatch = state.match
         oldnoflatmf = state.noflatmf
         try:
             state.shallowremote = True
-            state.match = match.always(repo.root, '')
+            state.match = match.always()
             state.noflatmf = other.get('noflatmanifest') == 'True'
             if includepattern or excludepattern:
                 state.match = match.match(repo.root, '', None,
                     includepattern, excludepattern)
             streamres = wireprotov1server.stream(repo, proto)
 
             # Force the first value to execute, so the file list is computed
             # within the try/finally scope
             first = next(streamres.gen)
             second = next(streamres.gen)
             def gen():
                 yield first
                 yield second
                 for value in streamres.gen:
                     yield value
             return wireprototypes.streamres(gen())
         finally:
             state.shallowremote = oldshallow
             state.match = oldmatch
             state.noflatmf = oldnoflatmf
 
     wireprotov1server.commands['stream_out_shallow'] = (stream_out_shallow, '*')
 
     # don't clone filelogs to shallow clients
     def _walkstreamfiles(orig, repo, matcher=None):
         if state.shallowremote:
             # if we are shallow ourselves, stream our local commits
             if shallowutil.isenabled(repo):
                 striplen = len(repo.store.path) + 1
                 readdir = repo.store.rawvfs.readdir
                 visit = [os.path.join(repo.store.path, 'data')]
                 while visit:
                     p = visit.pop()
                     for f, kind, st in readdir(p, stat=True):
                         fp = p + '/' + f
                         if kind == stat.S_IFREG:
                             if not fp.endswith('.i') and not fp.endswith('.d'):
                                 n = util.pconvert(fp[striplen:])
                                 yield (store.decodedir(n), n, st.st_size)
                         if kind == stat.S_IFDIR:
                             visit.append(fp)
 
             if 'treemanifest' in repo.requirements:
                 for (u, e, s) in repo.store.datafiles():
                     if (u.startswith('meta/') and
                         (u.endswith('.i') or u.endswith('.d'))):
                         yield (u, e, s)
 
             # Return .d and .i files that do not match the shallow pattern
             match = state.match
             if match and not match.always():
                 for (u, e, s) in repo.store.datafiles():
                     f = u[5:-2]  # trim data/...  and .i/.d
                     if not state.match(f):
                         yield (u, e, s)
 
             for x in repo.store.topfiles():
                 if state.noflatmf and x[0][:11] == '00manifest.':
                     continue
                 yield x
 
         elif shallowutil.isenabled(repo):
             # don't allow cloning from a shallow repo to a full repo
             # since it would require fetching every version of every
             # file in order to create the revlogs.
             raise error.Abort(_("Cannot clone from a shallow repo "
                                 "to a full repo."))
         else:
             for x in orig(repo, matcher):
                 yield x
 
     extensions.wrapfunction(streamclone, '_walkstreamfiles', _walkstreamfiles)
 
     # expose remotefilelog capabilities
     def _capabilities(orig, repo, proto):
         caps = orig(repo, proto)
         if (shallowutil.isenabled(repo) or ui.configbool('remotefilelog',
                                                          'server')):
             if isinstance(proto, _sshv1server):
                 # legacy getfiles method which only works over ssh
                 caps.append(constants.NETWORK_CAP_LEGACY_SSH_GETFILES)
             caps.append('x_rfl_getflogheads')
             caps.append('x_rfl_getfile')
         return caps
     extensions.wrapfunction(wireprotov1server, '_capabilities', _capabilities)
 
     def _adjustlinkrev(orig, self, *args, **kwargs):
         # When generating file blobs, taking the real path is too slow on large
         # repos, so force it to just return the linkrev directly.
         repo = self._repo
         if util.safehasattr(repo, 'forcelinkrev') and repo.forcelinkrev:
             return self._filelog.linkrev(self._filelog.rev(self._filenode))
         return orig(self, *args, **kwargs)
 
     extensions.wrapfunction(
         context.basefilectx, '_adjustlinkrev', _adjustlinkrev)
 
     def _iscmd(orig, cmd):
         if cmd == 'x_rfl_getfiles':
             return False
         return orig(cmd)
 
     extensions.wrapfunction(wireprotoserver, 'iscmd', _iscmd)
 
 def _loadfileblob(repo, cachepath, path, node):
     filecachepath = os.path.join(cachepath, path, hex(node))
     if not os.path.exists(filecachepath) or os.path.getsize(filecachepath) == 0:
         filectx = repo.filectx(path, fileid=node)
         if filectx.node() == nullid:
             repo.changelog = changelog.changelog(repo.svfs)
             filectx = repo.filectx(path, fileid=node)
 
         text = createfileblob(filectx)
         # TODO configurable compression engines
         text = zlib.compress(text)
 
         # everything should be user & group read/writable
         oldumask = os.umask(0o002)
         try:
             dirname = os.path.dirname(filecachepath)
             if not os.path.exists(dirname):
                 try:
                     os.makedirs(dirname)
                 except OSError as ex:
                     if ex.errno != errno.EEXIST:
                         raise
 
             f = None
             try:
                 f = util.atomictempfile(filecachepath, "wb")
                 f.write(text)
             except (IOError, OSError):
                 # Don't abort if the user only has permission to read,
                 # and not write.
                 pass
             finally:
                 if f:
                     f.close()
         finally:
             os.umask(oldumask)
     else:
         with open(filecachepath, "rb") as f:
             text = f.read()
     return text
 
 def getflogheads(repo, proto, path):
     """A server api for requesting a filelog's heads
     """
     flog = repo.file(path)
     heads = flog.heads()
     return '\n'.join((hex(head) for head in heads if head != nullid))
 
 def getfile(repo, proto, file, node):
     """A server api for requesting a particular version of a file. Can be used
     in batches to request many files at once. The return protocol is:
     <errorcode>\0<data/errormsg> where <errorcode> is 0 for success or
     non-zero for an error.
 
     data is a compressed blob with revlog flag and ancestors information. See
     createfileblob for its content.
     """
     if shallowutil.isenabled(repo):
         return '1\0' + _('cannot fetch remote files from shallow repo')
     cachepath = repo.ui.config("remotefilelog", "servercachepath")
     if not cachepath:
         cachepath = os.path.join(repo.path, "remotefilelogcache")
     node = bin(node.strip())
     if node == nullid:
         return '0\0'
     return '0\0' + _loadfileblob(repo, cachepath, file, node)
 
 def getfiles(repo, proto):
     """A server api for requesting particular versions of particular files.
     """
     if shallowutil.isenabled(repo):
         raise error.Abort(_('cannot fetch remote files from shallow repo'))
     if not isinstance(proto, _sshv1server):
         raise error.Abort(_('cannot fetch remote files over non-ssh protocol'))
 
     def streamer():
         fin = proto._fin
 
         cachepath = repo.ui.config("remotefilelog", "servercachepath")
         if not cachepath:
             cachepath = os.path.join(repo.path, "remotefilelogcache")
 
         while True:
             request = fin.readline()[:-1]
             if not request:
                 break
 
             node = bin(request[:40])
             if node == nullid:
                 yield '0\n'
                 continue
 
             path = request[40:]
 
             text = _loadfileblob(repo, cachepath, path, node)
 
             yield '%d\n%s' % (len(text), text)
 
             # it would be better to only flush after processing a whole batch
             # but currently we don't know if there are more requests coming
             proto._fout.flush()
     return wireprototypes.streamres(streamer())
 
 def createfileblob(filectx):
     """
     format:
         v0:
             str(len(rawtext)) + '\0' + rawtext + ancestortext
         v1:
             'v1' + '\n' + metalist + '\0' + rawtext + ancestortext
             metalist := metalist + '\n' + meta | meta
             meta := sizemeta | flagmeta
             sizemeta := METAKEYSIZE + str(len(rawtext))
             flagmeta := METAKEYFLAG + str(flag)
 
             note: sizemeta must exist. METAKEYFLAG and METAKEYSIZE must have a
             length of 1.
     """
     flog = filectx.filelog()
     frev = filectx.filerev()
     revlogflags = flog._revlog.flags(frev)
     if revlogflags == 0:
         # normal files
         text = filectx.data()
     else:
         # lfs, read raw revision data
         text = flog.revision(frev, raw=True)
 
     repo = filectx._repo
 
     ancestors = [filectx]
 
     try:
         repo.forcelinkrev = True
         ancestors.extend([f for f in filectx.ancestors()])
 
         ancestortext = ""
         for ancestorctx in ancestors:
             parents = ancestorctx.parents()
             p1 = nullid
             p2 = nullid
             if len(parents) > 0:
                 p1 = parents[0].filenode()
             if len(parents) > 1:
                 p2 = parents[1].filenode()
 
             copyname = ""
             rename = ancestorctx.renamed()
             if rename:
                 copyname = rename[0]
             linknode = ancestorctx.node()
             ancestortext += "%s%s%s%s%s\0" % (
                 ancestorctx.filenode(), p1, p2, linknode,
                 copyname)
     finally:
         repo.forcelinkrev = False
 
     header = shallowutil.buildfileblobheader(len(text), revlogflags)
 
     return "%s\0%s%s" % (header, text, ancestortext)
 
 def gcserver(ui, repo):
     if not repo.ui.configbool("remotefilelog", "server"):
         return
 
     neededfiles = set()
     heads = repo.revs("heads(tip~25000:) - null")
 
     cachepath = repo.vfs.join("remotefilelogcache")
     for head in heads:
         mf = repo[head].manifest()
         for filename, filenode in mf.iteritems():
             filecachepath = os.path.join(cachepath, filename, hex(filenode))
             neededfiles.add(filecachepath)
 
     # delete unneeded older files
     days = repo.ui.configint("remotefilelog", "serverexpiration")
     expiration = time.time() - (days * 24 * 60 * 60)
 
     progress = ui.makeprogress(_("removing old server cache"), unit="files")
     progress.update(0)
     for root, dirs, files in os.walk(cachepath):
         for file in files:
             filepath = os.path.join(root, file)
             progress.increment()
             if filepath in neededfiles:
                 continue
 
             stat = os.stat(filepath)
             if stat.st_mtime < expiration:
                 os.remove(filepath)
 
     progress.complete()

hgext/remotefilelog/shallowbundle.py

@@ -1,293 +1,293 b''
 # shallowbundle.py - bundle10 implementation for use with shallow repositories
 #
 # Copyright 2013 Facebook, Inc.
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 from __future__ import absolute_import
 
 from mercurial.i18n import _
 from mercurial.node import bin, hex, nullid
 from mercurial import (
     bundlerepo,
     changegroup,
     error,
     match,
     mdiff,
     pycompat,
 )
 from . import (
     constants,
     remotefilelog,
     shallowutil,
 )
 
 NoFiles = 0
 LocalFiles = 1
 AllFiles = 2
 
 def shallowgroup(cls, self, nodelist, rlog, lookup, units=None, reorder=None):
     if not isinstance(rlog, remotefilelog.remotefilelog):
         for c in super(cls, self).group(nodelist, rlog, lookup,
                                         units=units):
             yield c
         return
 
     if len(nodelist) == 0:
         yield self.close()
         return
 
     nodelist = shallowutil.sortnodes(nodelist, rlog.parents)
 
     # add the parent of the first rev
     p = rlog.parents(nodelist[0])[0]
     nodelist.insert(0, p)
 
     # build deltas
     for i in pycompat.xrange(len(nodelist) - 1):
         prev, curr = nodelist[i], nodelist[i + 1]
         linknode = lookup(curr)
         for c in self.nodechunk(rlog, curr, prev, linknode):
             yield c
 
     yield self.close()
 
 class shallowcg1packer(changegroup.cgpacker):
     def generate(self, commonrevs, clnodes, fastpathlinkrev, source):
         if shallowutil.isenabled(self._repo):
             fastpathlinkrev = False
 
         return super(shallowcg1packer, self).generate(commonrevs, clnodes,
             fastpathlinkrev, source)
 
     def group(self, nodelist, rlog, lookup, units=None, reorder=None):
         return shallowgroup(shallowcg1packer, self, nodelist, rlog, lookup,
                             units=units)
 
     def generatefiles(self, changedfiles, *args):
         try:
             linknodes, commonrevs, source = args
         except ValueError:
             commonrevs, source, mfdicts, fastpathlinkrev, fnodes, clrevs = args
         if shallowutil.isenabled(self._repo):
             repo = self._repo
             if isinstance(repo, bundlerepo.bundlerepository):
                 # If the bundle contains filelogs, we can't pull from it, since
                 # bundlerepo is heavily tied to revlogs. Instead require that
                 # the user use unbundle instead.
                 # Force load the filelog data.
                 bundlerepo.bundlerepository.file(repo, 'foo')
                 if repo._cgfilespos:
                     raise error.Abort("cannot pull from full bundles",
                                       hint="use `hg unbundle` instead")
                 return []
             filestosend = self.shouldaddfilegroups(source)
             if filestosend == NoFiles:
                 changedfiles = list([f for f in changedfiles
                                      if not repo.shallowmatch(f)])
 
         return super(shallowcg1packer, self).generatefiles(
             changedfiles, *args)
 
     def shouldaddfilegroups(self, source):
         repo = self._repo
         if not shallowutil.isenabled(repo):
             return AllFiles
 
         if source == "push" or source == "bundle":
             return AllFiles
 
         caps = self._bundlecaps or []
         if source == "serve" or source == "pull":
             if constants.BUNDLE2_CAPABLITY in caps:
                 return LocalFiles
             else:
                 # Serving to a full repo requires us to serve everything
                 repo.ui.warn(_("pulling from a shallow repo\n"))
                 return AllFiles
 
         return NoFiles
 
     def prune(self, rlog, missing, commonrevs):
         if not isinstance(rlog, remotefilelog.remotefilelog):
             return super(shallowcg1packer, self).prune(rlog, missing,
                 commonrevs)
 
         repo = self._repo
         results = []
         for fnode in missing:
             fctx = repo.filectx(rlog.filename, fileid=fnode)
             if fctx.linkrev() not in commonrevs:
                 results.append(fnode)
         return results
 
     def nodechunk(self, revlog, node, prevnode, linknode):
         prefix = ''
         if prevnode == nullid:
             delta = revlog.revision(node, raw=True)
             prefix = mdiff.trivialdiffheader(len(delta))
         else:
             # Actually uses remotefilelog.revdiff which works on nodes, not revs
             delta = revlog.revdiff(prevnode, node)
         p1, p2 = revlog.parents(node)
         flags = revlog.flags(node)
         meta = self.builddeltaheader(node, p1, p2, prevnode, linknode, flags)
         meta += prefix
         l = len(meta) + len(delta)
         yield changegroup.chunkheader(l)
         yield meta
         yield delta
 
 def makechangegroup(orig, repo, outgoing, version, source, *args, **kwargs):
     if not shallowutil.isenabled(repo):
         return orig(repo, outgoing, version, source, *args, **kwargs)
 
     original = repo.shallowmatch
     try:
         # if serving, only send files the clients has patterns for
         if source == 'serve':
             bundlecaps = kwargs.get(r'bundlecaps')
             includepattern = None
             excludepattern = None
             for cap in (bundlecaps or []):
                 if cap.startswith("includepattern="):
                     raw = cap[len("includepattern="):]
                     if raw:
                         includepattern = raw.split('\0')
                 elif cap.startswith("excludepattern="):
                     raw = cap[len("excludepattern="):]
                     if raw:
                         excludepattern = raw.split('\0')
             if includepattern or excludepattern:
                 repo.shallowmatch = match.match(repo.root, '', None,
                     includepattern, excludepattern)
             else:
-                repo.shallowmatch = match.always(repo.root, '')
+                repo.shallowmatch = match.always()
         return orig(repo, outgoing, version, source, *args, **kwargs)
     finally:
         repo.shallowmatch = original
 
 def addchangegroupfiles(orig, repo, source, revmap, trp, expectedfiles, *args):
     if not shallowutil.isenabled(repo):
         return orig(repo, source, revmap, trp, expectedfiles, *args)
 
     newfiles = 0
     visited = set()
     revisiondatas = {}
     queue = []
 
     # Normal Mercurial processes each file one at a time, adding all
     # the new revisions for that file at once. In remotefilelog a file
     # revision may depend on a different file's revision (in the case
     # of a rename/copy), so we must lay all revisions down across all
     # files in topological order.
 
     # read all the file chunks but don't add them
     progress = repo.ui.makeprogress(_('files'), total=expectedfiles)
     while True:
         chunkdata = source.filelogheader()
         if not chunkdata:
             break
         f = chunkdata["filename"]
         repo.ui.debug("adding %s revisions\n" % f)
         progress.increment()
 
         if not repo.shallowmatch(f):
             fl = repo.file(f)
             deltas = source.deltaiter()
             fl.addgroup(deltas, revmap, trp)
             continue
 
         chain = None
         while True:
             # returns: (node, p1, p2, cs, deltabase, delta, flags) or None
             revisiondata = source.deltachunk(chain)
             if not revisiondata:
                 break
 
             chain = revisiondata[0]
 
             revisiondatas[(f, chain)] = revisiondata
             queue.append((f, chain))
 
             if f not in visited:
                 newfiles += 1
                 visited.add(f)
 
         if chain is None:
             raise error.Abort(_("received file revlog group is empty"))
 
     processed = set()
     def available(f, node, depf, depnode):
         if depnode != nullid and (depf, depnode) not in processed:
             if not (depf, depnode) in revisiondatas:
                 # It's not in the changegroup, assume it's already
                 # in the repo
                 return True
             # re-add self to queue
             queue.insert(0, (f, node))
             # add dependency in front
             queue.insert(0, (depf, depnode))
             return False
         return True
 
     skipcount = 0
 
     # Prefetch the non-bundled revisions that we will need
     prefetchfiles = []
     for f, node in queue:
         revisiondata = revisiondatas[(f, node)]
         # revisiondata: (node, p1, p2, cs, deltabase, delta, flags)
         dependents = [revisiondata[1], revisiondata[2], revisiondata[4]]
 
         for dependent in dependents:
             if dependent == nullid or (f, dependent) in revisiondatas:
                 continue
             prefetchfiles.append((f, hex(dependent)))
 
     repo.fileservice.prefetch(prefetchfiles)
 
     # Apply the revisions in topological order such that a revision
     # is only written once it's deltabase and parents have been written.
     while queue:
         f, node = queue.pop(0)
         if (f, node) in processed:
             continue
 
         skipcount += 1
         if skipcount > len(queue) + 1:
             raise error.Abort(_("circular node dependency"))
 
         fl = repo.file(f)
 
         revisiondata = revisiondatas[(f, node)]
         # revisiondata: (node, p1, p2, cs, deltabase, delta, flags)
         node, p1, p2, linknode, deltabase, delta, flags = revisiondata
 
         if not available(f, node, f, deltabase):
             continue
 
         base = fl.revision(deltabase, raw=True)
         text = mdiff.patch(base, delta)
         if not isinstance(text, bytes):
             text = bytes(text)
 
         meta, text = shallowutil.parsemeta(text)
         if 'copy' in meta:
             copyfrom = meta['copy']
             copynode = bin(meta['copyrev'])
             if not available(f, node, copyfrom, copynode):
                 continue
 
         for p in [p1, p2]:
             if p != nullid:
                 if not available(f, node, f, p):
                     continue
 
         fl.add(text, meta, trp, linknode, p1, p2)
         processed.add((f, node))
         skipcount = 0
 
     progress.complete()
 
     return len(revisiondatas), newfiles

hgext/remotefilelog/shallowrepo.py

@@ -1,305 +1,305 b''
 # shallowrepo.py - shallow repository that uses remote filelogs
 #
 # Copyright 2013 Facebook, Inc.
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 from __future__ import absolute_import
 
 import os
 
 from mercurial.i18n import _
 from mercurial.node import hex, nullid, nullrev
 from mercurial import (
     encoding,
     error,
     localrepo,
     match,
     scmutil,
     sparse,
     util,
 )
 from mercurial.utils import procutil
 from . import (
     connectionpool,
     constants,
     contentstore,
     datapack,
     fileserverclient,
     historypack,
     metadatastore,
     remotefilectx,
     remotefilelog,
     shallowutil,
 )
 
 if util.safehasattr(util, '_hgexecutable'):
     # Before 5be286db
     _hgexecutable = util.hgexecutable
 else:
     from mercurial.utils import procutil
     _hgexecutable = procutil.hgexecutable
 
 # These make*stores functions are global so that other extensions can replace
 # them.
 def makelocalstores(repo):
     """In-repo stores, like .hg/store/data; can not be discarded."""
     localpath = os.path.join(repo.svfs.vfs.base, 'data')
     if not os.path.exists(localpath):
         os.makedirs(localpath)
 
     # Instantiate local data stores
     localcontent = contentstore.remotefilelogcontentstore(
         repo, localpath, repo.name, shared=False)
     localmetadata = metadatastore.remotefilelogmetadatastore(
         repo, localpath, repo.name, shared=False)
     return localcontent, localmetadata
 
 def makecachestores(repo):
     """Typically machine-wide, cache of remote data; can be discarded."""
     # Instantiate shared cache stores
     cachepath = shallowutil.getcachepath(repo.ui)
     cachecontent = contentstore.remotefilelogcontentstore(
         repo, cachepath, repo.name, shared=True)
     cachemetadata = metadatastore.remotefilelogmetadatastore(
         repo, cachepath, repo.name, shared=True)
 
     repo.sharedstore = cachecontent
     repo.shareddatastores.append(cachecontent)
     repo.sharedhistorystores.append(cachemetadata)
 
     return cachecontent, cachemetadata
 
 def makeremotestores(repo, cachecontent, cachemetadata):
     """These stores fetch data from a remote server."""
     # Instantiate remote stores
     repo.fileservice = fileserverclient.fileserverclient(repo)
     remotecontent = contentstore.remotecontentstore(
         repo.ui, repo.fileservice, cachecontent)
     remotemetadata = metadatastore.remotemetadatastore(
         repo.ui, repo.fileservice, cachemetadata)
     return remotecontent, remotemetadata
 
 def makepackstores(repo):
     """Packs are more efficient (to read from) cache stores."""
     # Instantiate pack stores
     packpath = shallowutil.getcachepackpath(repo,
                                             constants.FILEPACK_CATEGORY)
     packcontentstore = datapack.datapackstore(repo.ui, packpath)
     packmetadatastore = historypack.historypackstore(repo.ui, packpath)
 
     repo.shareddatastores.append(packcontentstore)
     repo.sharedhistorystores.append(packmetadatastore)
     shallowutil.reportpackmetrics(repo.ui, 'filestore', packcontentstore,
         packmetadatastore)
     return packcontentstore, packmetadatastore
 
 def makeunionstores(repo):
     """Union stores iterate the other stores and return the first result."""
     repo.shareddatastores = []
     repo.sharedhistorystores = []
 
     packcontentstore, packmetadatastore = makepackstores(repo)
     cachecontent, cachemetadata = makecachestores(repo)
     localcontent, localmetadata = makelocalstores(repo)
     remotecontent, remotemetadata = makeremotestores(repo, cachecontent,
                                                      cachemetadata)
 
     # Instantiate union stores
     repo.contentstore = contentstore.unioncontentstore(
         packcontentstore, cachecontent,
         localcontent, remotecontent, writestore=localcontent)
     repo.metadatastore = metadatastore.unionmetadatastore(
         packmetadatastore, cachemetadata, localmetadata, remotemetadata,
         writestore=localmetadata)
 
     fileservicedatawrite = cachecontent
     fileservicehistorywrite = cachemetadata
     repo.fileservice.setstore(repo.contentstore, repo.metadatastore,
                               fileservicedatawrite, fileservicehistorywrite)
     shallowutil.reportpackmetrics(repo.ui, 'filestore',
         packcontentstore, packmetadatastore)
 
 def wraprepo(repo):
     class shallowrepository(repo.__class__):
         @util.propertycache
         def name(self):
             return self.ui.config('remotefilelog', 'reponame')
 
         @util.propertycache
         def fallbackpath(self):
             path = repo.ui.config("remotefilelog", "fallbackpath",
                                   repo.ui.config('paths', 'default'))
             if not path:
                 raise error.Abort("no remotefilelog server "
                     "configured - is your .hg/hgrc trusted?")
 
             return path
 
         def maybesparsematch(self, *revs, **kwargs):
             '''
             A wrapper that allows the remotefilelog to invoke sparsematch() if
             this is a sparse repository, or returns None if this is not a
             sparse repository.
             '''
             if revs:
                 ret = sparse.matcher(repo, revs=revs)
             else:
                 ret = sparse.matcher(repo)
 
             if ret.always():
                 return None
             return ret
 
         def file(self, f):
             if f[0] == '/':
                 f = f[1:]
 
             if self.shallowmatch(f):
                 return remotefilelog.remotefilelog(self.svfs, f, self)
             else:
                 return super(shallowrepository, self).file(f)
 
         def filectx(self, path, *args, **kwargs):
             if self.shallowmatch(path):
                 return remotefilectx.remotefilectx(self, path, *args, **kwargs)
             else:
                 return super(shallowrepository, self).filectx(path, *args,
                                                               **kwargs)
 
         @localrepo.unfilteredmethod
         def commitctx(self, ctx, error=False):
             """Add a new revision to current repository.
             Revision information is passed via the context argument.
             """
 
             # some contexts already have manifest nodes, they don't need any
             # prefetching (for example if we're just editing a commit message
             # we can reuse manifest
             if not ctx.manifestnode():
                 # prefetch files that will likely be compared
                 m1 = ctx.p1().manifest()
                 files = []
                 for f in ctx.modified() + ctx.added():
                     fparent1 = m1.get(f, nullid)
                     if fparent1 != nullid:
                         files.append((f, hex(fparent1)))
                 self.fileservice.prefetch(files)
             return super(shallowrepository, self).commitctx(ctx,
                                                             error=error)
 
         def backgroundprefetch(self, revs, base=None, repack=False, pats=None,
                                opts=None):
             """Runs prefetch in background with optional repack
             """
             cmd = [_hgexecutable(), '-R', repo.origroot, 'prefetch']
             if repack:
                 cmd.append('--repack')
             if revs:
                 cmd += ['-r', revs]
             procutil.runbgcommand(cmd, encoding.environ)
 
         def prefetch(self, revs, base=None, pats=None, opts=None):
             """Prefetches all the necessary file revisions for the given revs
             Optionally runs repack in background
             """
             with repo._lock(repo.svfs, 'prefetchlock', True, None, None,
                             _('prefetching in %s') % repo.origroot):
                 self._prefetch(revs, base, pats, opts)
 
         def _prefetch(self, revs, base=None, pats=None, opts=None):
             fallbackpath = self.fallbackpath
             if fallbackpath:
                 # If we know a rev is on the server, we should fetch the server
                 # version of those files, since our local file versions might
                 # become obsolete if the local commits are stripped.
                 localrevs = repo.revs('outgoing(%s)', fallbackpath)
                 if base is not None and base != nullrev:
                     serverbase = list(repo.revs('first(reverse(::%s) - %ld)',
                                                 base, localrevs))
                     if serverbase:
                         base = serverbase[0]
             else:
                 localrevs = repo
 
             mfl = repo.manifestlog
             mfrevlog = mfl.getstorage('')
             if base is not None:
                 mfdict = mfl[repo[base].manifestnode()].read()
                 skip = set(mfdict.iteritems())
             else:
                 skip = set()
 
             # Copy the skip set to start large and avoid constant resizing,
             # and since it's likely to be very similar to the prefetch set.
             files = skip.copy()
             serverfiles = skip.copy()
             visited = set()
             visited.add(nullrev)
             revcount = len(revs)
             progress = self.ui.makeprogress(_('prefetching'), total=revcount)
             progress.update(0)
             for rev in sorted(revs):
                 ctx = repo[rev]
                 if pats:
                     m = scmutil.match(ctx, pats, opts)
                 sparsematch = repo.maybesparsematch(rev)
 
                 mfnode = ctx.manifestnode()
                 mfrev = mfrevlog.rev(mfnode)
 
                 # Decompressing manifests is expensive.
                 # When possible, only read the deltas.
                 p1, p2 = mfrevlog.parentrevs(mfrev)
                 if p1 in visited and p2 in visited:
                     mfdict = mfl[mfnode].readfast()
                 else:
                     mfdict = mfl[mfnode].read()
 
                 diff = mfdict.iteritems()
                 if pats:
                     diff = (pf for pf in diff if m(pf[0]))
                 if sparsematch:
                     diff = (pf for pf in diff if sparsematch(pf[0]))
                 if rev not in localrevs:
                     serverfiles.update(diff)
                 else:
                     files.update(diff)
 
                 visited.add(mfrev)
                 progress.increment()
 
             files.difference_update(skip)
             serverfiles.difference_update(skip)
             progress.complete()
 
             # Fetch files known to be on the server
             if serverfiles:
                 results = [(path, hex(fnode)) for (path, fnode) in serverfiles]
                 repo.fileservice.prefetch(results, force=True)
 
             # Fetch files that may or may not be on the server
             if files:
                 results = [(path, hex(fnode)) for (path, fnode) in files]
                 repo.fileservice.prefetch(results)
 
         def close(self):
             super(shallowrepository, self).close()
             self.connectionpool.close()
 
     repo.__class__ = shallowrepository
 
-    repo.shallowmatch = match.always(repo.root, '')
+    repo.shallowmatch = match.always()
 
     makeunionstores(repo)
 
     repo.includepattern = repo.ui.configlist("remotefilelog", "includepattern",
                                              None)
     repo.excludepattern = repo.ui.configlist("remotefilelog", "excludepattern",
                                              None)
     if not util.safehasattr(repo, 'connectionpool'):
         repo.connectionpool = connectionpool.connectionpool(repo)
 
     if repo.includepattern or repo.excludepattern:
         repo.shallowmatch = match.match(repo.root, '', None,
             repo.includepattern, repo.excludepattern)

hgext/sparse.py

@@ -1,347 +1,347 b''
 # sparse.py - allow sparse checkouts of the working directory
 #
 # Copyright 2014 Facebook, Inc.
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 """allow sparse checkouts of the working directory (EXPERIMENTAL)
 
 (This extension is not yet protected by backwards compatibility
 guarantees. Any aspect may break in future releases until this
 notice is removed.)
 
 This extension allows the working directory to only consist of a
 subset of files for the revision. This allows specific files or
 directories to be explicitly included or excluded. Many repository
 operations have performance proportional to the number of files in
 the working directory. So only realizing a subset of files in the
 working directory can improve performance.
 
 Sparse Config Files
 -------------------
 
 The set of files that are part of a sparse checkout are defined by
 a sparse config file. The file defines 3 things: includes (files to
 include in the sparse checkout), excludes (files to exclude from the
 sparse checkout), and profiles (links to other config files).
 
 The file format is newline delimited. Empty lines and lines beginning
 with ``#`` are ignored.
 
 Lines beginning with ``%include `` denote another sparse config file
 to include. e.g. ``%include tests.sparse``. The filename is relative
 to the repository root.
 
 The special lines ``[include]`` and ``[exclude]`` denote the section
 for includes and excludes that follow, respectively. It is illegal to
 have ``[include]`` after ``[exclude]``.
 
 Non-special lines resemble file patterns to be added to either includes
 or excludes. The syntax of these lines is documented by :hg:`help patterns`.
 Patterns are interpreted as ``glob:`` by default and match against the
 root of the repository.
 
 Exclusion patterns take precedence over inclusion patterns. So even
 if a file is explicitly included, an ``[exclude]`` entry can remove it.
 
 For example, say you have a repository with 3 directories, ``frontend/``,
 ``backend/``, and ``tools/``. ``frontend/`` and ``backend/`` correspond
 to different projects and it is uncommon for someone working on one
 to need the files for the other. But ``tools/`` contains files shared
 between both projects. Your sparse config files may resemble::
 
   # frontend.sparse
   frontend/**
   tools/**
 
   # backend.sparse
   backend/**
   tools/**
 
 Say the backend grows in size. Or there's a directory with thousands
 of files you wish to exclude. You can modify the profile to exclude
 certain files::
 
   [include]
   backend/**
   tools/**
 
   [exclude]
   tools/tests/**
 """
 
 from __future__ import absolute_import
 
 from mercurial.i18n import _
 from mercurial import (
     commands,
     dirstate,
     error,
     extensions,
     hg,
     logcmdutil,
     match as matchmod,
     pycompat,
     registrar,
     sparse,
     util,
 )
 
 # Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
 # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
 # be specifying the version(s) of Mercurial they are tested with, or
 # leave the attribute unspecified.
 testedwith = 'ships-with-hg-core'
 
 cmdtable = {}
 command = registrar.command(cmdtable)
 
 def extsetup(ui):
     sparse.enabled = True
 
     _setupclone(ui)
     _setuplog(ui)
     _setupadd(ui)
     _setupdirstate(ui)
 
 def replacefilecache(cls, propname, replacement):
     """Replace a filecache property with a new class. This allows changing the
     cache invalidation condition."""
     origcls = cls
     assert callable(replacement)
     while cls is not object:
         if propname in cls.__dict__:
             orig = cls.__dict__[propname]
             setattr(cls, propname, replacement(orig))
             break
         cls = cls.__bases__[0]
 
     if cls is object:
         raise AttributeError(_("type '%s' has no property '%s'") % (origcls,
                              propname))
 
 def _setuplog(ui):
     entry = commands.table['log|history']
     entry[1].append(('', 'sparse', None,
         "limit to changesets affecting the sparse checkout"))
 
     def _initialrevs(orig, repo, opts):
         revs = orig(repo, opts)
         if opts.get('sparse'):
             sparsematch = sparse.matcher(repo)
             def ctxmatch(rev):
                 ctx = repo[rev]
                 return any(f for f in ctx.files() if sparsematch(f))
             revs = revs.filter(ctxmatch)
         return revs
     extensions.wrapfunction(logcmdutil, '_initialrevs', _initialrevs)
 
 def _clonesparsecmd(orig, ui, repo, *args, **opts):
     include_pat = opts.get(r'include')
     exclude_pat = opts.get(r'exclude')
     enableprofile_pat = opts.get(r'enable_profile')
     narrow_pat = opts.get(r'narrow')
     include = exclude = enableprofile = False
     if include_pat:
         pat = include_pat
         include = True
     if exclude_pat:
         pat = exclude_pat
         exclude = True
     if enableprofile_pat:
         pat = enableprofile_pat
         enableprofile = True
     if sum([include, exclude, enableprofile]) > 1:
         raise error.Abort(_("too many flags specified."))
     # if --narrow is passed, it means they are includes and excludes for narrow
     # clone
     if not narrow_pat and (include or exclude or enableprofile):
         def clonesparse(orig, self, node, overwrite, *args, **kwargs):
             sparse.updateconfig(self.unfiltered(), pat, {}, include=include,
                                 exclude=exclude, enableprofile=enableprofile,
                                 usereporootpaths=True)
             return orig(self, node, overwrite, *args, **kwargs)
         extensions.wrapfunction(hg, 'updaterepo', clonesparse)
     return orig(ui, repo, *args, **opts)
 
 def _setupclone(ui):
     entry = commands.table['clone']
     entry[1].append(('', 'enable-profile', [],
                     'enable a sparse profile'))
     entry[1].append(('', 'include', [],
                     'include sparse pattern'))
     entry[1].append(('', 'exclude', [],
                     'exclude sparse pattern'))
     extensions.wrapcommand(commands.table, 'clone', _clonesparsecmd)
 
 def _setupadd(ui):
     entry = commands.table['add']
     entry[1].append(('s', 'sparse', None,
                     'also include directories of added files in sparse config'))
 
     def _add(orig, ui, repo, *pats, **opts):
         if opts.get(r'sparse'):
             dirs = set()
             for pat in pats:
                 dirname, basename = util.split(pat)
                 dirs.add(dirname)
             sparse.updateconfig(repo, list(dirs), opts, include=True)
         return orig(ui, repo, *pats, **opts)
 
     extensions.wrapcommand(commands.table, 'add', _add)
 
 def _setupdirstate(ui):
     """Modify the dirstate to prevent stat'ing excluded files,
     and to prevent modifications to files outside the checkout.
     """
 
     def walk(orig, self, match, subrepos, unknown, ignored, full=True):
         # hack to not exclude explicitly-specified paths so that they can
         # be warned later on e.g. dirstate.add()
-        em = matchmod.exact(None, None, match.files())
+        em = matchmod.exact(match.files())
         sm = matchmod.unionmatcher([self._sparsematcher, em])
         match = matchmod.intersectmatchers(match, sm)
         return orig(self, match, subrepos, unknown, ignored, full)
 
     extensions.wrapfunction(dirstate.dirstate, 'walk', walk)
 
     # dirstate.rebuild should not add non-matching files
     def _rebuild(orig, self, parent, allfiles, changedfiles=None):
         matcher = self._sparsematcher
         if not matcher.always():
             allfiles = [f for f in allfiles if matcher(f)]
             if changedfiles:
                 changedfiles = [f for f in changedfiles if matcher(f)]
 
             if changedfiles is not None:
                 # In _rebuild, these files will be deleted from the dirstate
                 # when they are not found to be in allfiles
                 dirstatefilestoremove = set(f for f in self if not matcher(f))
                 changedfiles = dirstatefilestoremove.union(changedfiles)
 
         return orig(self, parent, allfiles, changedfiles)
     extensions.wrapfunction(dirstate.dirstate, 'rebuild', _rebuild)
 
     # Prevent adding files that are outside the sparse checkout
     editfuncs = ['normal', 'add', 'normallookup', 'copy', 'remove', 'merge']
     hint = _('include file with `hg debugsparse --include <pattern>` or use ' +
              '`hg add -s <file>` to include file directory while adding')
     for func in editfuncs:
         def _wrapper(orig, self, *args):
             sparsematch = self._sparsematcher
             if not sparsematch.always():
                 for f in args:
                     if (f is not None and not sparsematch(f) and
                         f not in self):
                         raise error.Abort(_("cannot add '%s' - it is outside "
                                             "the sparse checkout") % f,
                                           hint=hint)
             return orig(self, *args)
         extensions.wrapfunction(dirstate.dirstate, func, _wrapper)
 
 @command('debugsparse', [
     ('I', 'include', False, _('include files in the sparse checkout')),
     ('X', 'exclude', False, _('exclude files in the sparse checkout')),
     ('d', 'delete', False, _('delete an include/exclude rule')),
     ('f', 'force', False, _('allow changing rules even with pending changes')),
     ('', 'enable-profile', False, _('enables the specified profile')),
     ('', 'disable-profile', False, _('disables the specified profile')),
     ('', 'import-rules', False, _('imports rules from a file')),
     ('', 'clear-rules', False, _('clears local include/exclude rules')),
     ('', 'refresh', False, _('updates the working after sparseness changes')),
     ('', 'reset', False, _('makes the repo full again')),
     ] + commands.templateopts,
     _('[--OPTION] PATTERN...'),
     helpbasic=True)
 def debugsparse(ui, repo, *pats, **opts):
     """make the current checkout sparse, or edit the existing checkout
 
     The sparse command is used to make the current checkout sparse.
     This means files that don't meet the sparse condition will not be
     written to disk, or show up in any working copy operations. It does
     not affect files in history in any way.
 
     Passing no arguments prints the currently applied sparse rules.
 
     --include and --exclude are used to add and remove files from the sparse
     checkout. The effects of adding an include or exclude rule are applied
     immediately. If applying the new rule would cause a file with pending
     changes to be added or removed, the command will fail. Pass --force to
     force a rule change even with pending changes (the changes on disk will
     be preserved).
 
     --delete removes an existing include/exclude rule. The effects are
     immediate.
 
     --refresh refreshes the files on disk based on the sparse rules. This is
     only necessary if .hg/sparse was changed by hand.
 
     --enable-profile and --disable-profile accept a path to a .hgsparse file.
     This allows defining sparse checkouts and tracking them inside the
     repository. This is useful for defining commonly used sparse checkouts for
     many people to use. As the profile definition changes over time, the sparse
     checkout will automatically be updated appropriately, depending on which
     changeset is checked out. Changes to .hgsparse are not applied until they
     have been committed.
 
     --import-rules accepts a path to a file containing rules in the .hgsparse
     format, allowing you to add --include, --exclude and --enable-profile rules
     in bulk. Like the --include, --exclude and --enable-profile switches, the
     changes are applied immediately.
 
     --clear-rules removes all local include and exclude rules, while leaving
     any enabled profiles in place.
 
     Returns 0 if editing the sparse checkout succeeds.
     """
     opts = pycompat.byteskwargs(opts)
     include = opts.get('include')
     exclude = opts.get('exclude')
     force = opts.get('force')
     enableprofile = opts.get('enable_profile')
     disableprofile = opts.get('disable_profile')
     importrules = opts.get('import_rules')
     clearrules = opts.get('clear_rules')
     delete = opts.get('delete')
     refresh = opts.get('refresh')
     reset = opts.get('reset')
     count = sum([include, exclude, enableprofile, disableprofile, delete,
                  importrules, refresh, clearrules, reset])
     if count > 1:
         raise error.Abort(_("too many flags specified"))
 
     if count == 0:
         if repo.vfs.exists('sparse'):
             ui.status(repo.vfs.read("sparse") + "\n")
             temporaryincludes = sparse.readtemporaryincludes(repo)
             if temporaryincludes:
                 ui.status(_("Temporarily Included Files (for merge/rebase):\n"))
                 ui.status(("\n".join(temporaryincludes) + "\n"))
         else:
             ui.status(_('repo is not sparse\n'))
         return
 
     if include or exclude or delete or reset or enableprofile or disableprofile:
         sparse.updateconfig(repo, pats, opts, include=include, exclude=exclude,
                             reset=reset, delete=delete,
                             enableprofile=enableprofile,
                             disableprofile=disableprofile, force=force)
 
     if importrules:
         sparse.importfromfiles(repo, opts, pats, force=force)
 
     if clearrules:
         sparse.clearrules(repo, force=force)
 
     if refresh:
         try:
             wlock = repo.wlock()
             fcounts = map(
                 len,
                 sparse.refreshwdir(repo, repo.status(), sparse.matcher(repo),
                                    force=force))
             sparse.printchanges(ui, opts, added=fcounts[0], dropped=fcounts[1],
                                 conflicting=fcounts[2])
         finally:
             wlock.release()

hgext/transplant.py

@@ -1,765 +1,765 b''
 # Patch transplanting extension for Mercurial
 #
 # Copyright 2006, 2007 Brendan Cully <[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.
 
 '''command to transplant changesets from another branch
 
 This extension allows you to transplant changes to another parent revision,
 possibly in another repository. The transplant is done using 'diff' patches.
 
 Transplanted patches are recorded in .hg/transplant/transplants, as a
 map from a changeset hash to its hash in the source repository.
 '''
 from __future__ import absolute_import
 
 import os
 
 from mercurial.i18n import _
 from mercurial import (
     bundlerepo,
     cmdutil,
     error,
     exchange,
     hg,
     logcmdutil,
     match,
     merge,
     node as nodemod,
     patch,
     pycompat,
     registrar,
     revlog,
     revset,
     scmutil,
     smartset,
     util,
     vfs as vfsmod,
 )
 from mercurial.utils import (
     procutil,
     stringutil,
 )
 
 class TransplantError(error.Abort):
     pass
 
 cmdtable = {}
 command = registrar.command(cmdtable)
 # Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
 # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
 # be specifying the version(s) of Mercurial they are tested with, or
 # leave the attribute unspecified.
 testedwith = 'ships-with-hg-core'
 
 configtable = {}
 configitem = registrar.configitem(configtable)
 
 configitem('transplant', 'filter',
     default=None,
 )
 configitem('transplant', 'log',
     default=None,
 )
 
 class transplantentry(object):
     def __init__(self, lnode, rnode):
         self.lnode = lnode
         self.rnode = rnode
 
 class transplants(object):
     def __init__(self, path=None, transplantfile=None, opener=None):
         self.path = path
         self.transplantfile = transplantfile
         self.opener = opener
 
         if not opener:
             self.opener = vfsmod.vfs(self.path)
         self.transplants = {}
         self.dirty = False
         self.read()
 
     def read(self):
         abspath = os.path.join(self.path, self.transplantfile)
         if self.transplantfile and os.path.exists(abspath):
             for line in self.opener.read(self.transplantfile).splitlines():
                 lnode, rnode = map(revlog.bin, line.split(':'))
                 list = self.transplants.setdefault(rnode, [])
                 list.append(transplantentry(lnode, rnode))
 
     def write(self):
         if self.dirty and self.transplantfile:
             if not os.path.isdir(self.path):
                 os.mkdir(self.path)
             fp = self.opener(self.transplantfile, 'w')
             for list in self.transplants.itervalues():
                 for t in list:
                     l, r = map(nodemod.hex, (t.lnode, t.rnode))
                     fp.write(l + ':' + r + '\n')
             fp.close()
         self.dirty = False
 
     def get(self, rnode):
         return self.transplants.get(rnode) or []
 
     def set(self, lnode, rnode):
         list = self.transplants.setdefault(rnode, [])
         list.append(transplantentry(lnode, rnode))
         self.dirty = True
 
     def remove(self, transplant):
         list = self.transplants.get(transplant.rnode)
         if list:
             del list[list.index(transplant)]
             self.dirty = True
 
 class transplanter(object):
     def __init__(self, ui, repo, opts):
         self.ui = ui
         self.path = repo.vfs.join('transplant')
         self.opener = vfsmod.vfs(self.path)
         self.transplants = transplants(self.path, 'transplants',
                                        opener=self.opener)
         def getcommiteditor():
             editform = cmdutil.mergeeditform(repo[None], 'transplant')
             return cmdutil.getcommiteditor(editform=editform,
                                            **pycompat.strkwargs(opts))
         self.getcommiteditor = getcommiteditor
 
     def applied(self, repo, node, parent):
         '''returns True if a node is already an ancestor of parent
         or is parent or has already been transplanted'''
         if hasnode(repo, parent):
             parentrev = repo.changelog.rev(parent)
         if hasnode(repo, node):
             rev = repo.changelog.rev(node)
             reachable = repo.changelog.ancestors([parentrev], rev,
                                                  inclusive=True)
             if rev in reachable:
                 return True
         for t in self.transplants.get(node):
             # it might have been stripped
             if not hasnode(repo, t.lnode):
                 self.transplants.remove(t)
                 return False
             lnoderev = repo.changelog.rev(t.lnode)
             if lnoderev in repo.changelog.ancestors([parentrev], lnoderev,
                                                     inclusive=True):
                 return True
         return False
 
     def apply(self, repo, source, revmap, merges, opts=None):
         '''apply the revisions in revmap one by one in revision order'''
         if opts is None:
             opts = {}
         revs = sorted(revmap)
         p1 = repo.dirstate.p1()
         pulls = []
         diffopts = patch.difffeatureopts(self.ui, opts)
         diffopts.git = True
 
         lock = tr = None
         try:
             lock = repo.lock()
             tr = repo.transaction('transplant')
             for rev in revs:
                 node = revmap[rev]
                 revstr = '%d:%s' % (rev, nodemod.short(node))
 
                 if self.applied(repo, node, p1):
                     self.ui.warn(_('skipping already applied revision %s\n') %
                                  revstr)
                     continue
 
                 parents = source.changelog.parents(node)
                 if not (opts.get('filter') or opts.get('log')):
                     # If the changeset parent is the same as the
                     # wdir's parent, just pull it.
                     if parents[0] == p1:
                         pulls.append(node)
                         p1 = node
                         continue
                     if pulls:
                         if source != repo:
                             exchange.pull(repo, source.peer(), heads=pulls)
                         merge.update(repo, pulls[-1], branchmerge=False,
                                      force=False)
                         p1 = repo.dirstate.p1()
                         pulls = []
 
                 domerge = False
                 if node in merges:
                     # pulling all the merge revs at once would mean we
                     # couldn't transplant after the latest even if
                     # transplants before them fail.
                     domerge = True
                     if not hasnode(repo, node):
                         exchange.pull(repo, source.peer(), heads=[node])
 
                 skipmerge = False
                 if parents[1] != revlog.nullid:
                     if not opts.get('parent'):
                         self.ui.note(_('skipping merge changeset %d:%s\n')
                                      % (rev, nodemod.short(node)))
                         skipmerge = True
                     else:
                         parent = source.lookup(opts['parent'])
                         if parent not in parents:
                             raise error.Abort(_('%s is not a parent of %s') %
                                               (nodemod.short(parent),
                                                nodemod.short(node)))
                 else:
                     parent = parents[0]
 
                 if skipmerge:
                     patchfile = None
                 else:
                     fd, patchfile = pycompat.mkstemp(prefix='hg-transplant-')
                     fp = os.fdopen(fd, r'wb')
                     gen = patch.diff(source, parent, node, opts=diffopts)
                     for chunk in gen:
                         fp.write(chunk)
                     fp.close()
 
                 del revmap[rev]
                 if patchfile or domerge:
                     try:
                         try:
                             n = self.applyone(repo, node,
                                               source.changelog.read(node),
                                               patchfile, merge=domerge,
                                               log=opts.get('log'),
                                               filter=opts.get('filter'))
                         except TransplantError:
                             # Do not rollback, it is up to the user to
                             # fix the merge or cancel everything
                             tr.close()
                             raise
                         if n and domerge:
                             self.ui.status(_('%s merged at %s\n') % (revstr,
                                       nodemod.short(n)))
                         elif n:
                             self.ui.status(_('%s transplanted to %s\n')
                                            % (nodemod.short(node),
                                               nodemod.short(n)))
                     finally:
                         if patchfile:
                             os.unlink(patchfile)
             tr.close()
             if pulls:
                 exchange.pull(repo, source.peer(), heads=pulls)
                 merge.update(repo, pulls[-1], branchmerge=False, force=False)
         finally:
             self.saveseries(revmap, merges)
             self.transplants.write()
             if tr:
                 tr.release()
             if lock:
                 lock.release()
 
     def filter(self, filter, node, changelog, patchfile):
         '''arbitrarily rewrite changeset before applying it'''
 
         self.ui.status(_('filtering %s\n') % patchfile)
         user, date, msg = (changelog[1], changelog[2], changelog[4])
         fd, headerfile = pycompat.mkstemp(prefix='hg-transplant-')
         fp = os.fdopen(fd, r'wb')
         fp.write("# HG changeset patch\n")
         fp.write("# User %s\n" % user)
         fp.write("# Date %d %d\n" % date)
         fp.write(msg + '\n')
         fp.close()
 
         try:
             self.ui.system('%s %s %s' % (filter,
                                          procutil.shellquote(headerfile),
                                          procutil.shellquote(patchfile)),
                            environ={'HGUSER': changelog[1],
                                     'HGREVISION': nodemod.hex(node),
                                     },
                            onerr=error.Abort, errprefix=_('filter failed'),
                            blockedtag='transplant_filter')
             user, date, msg = self.parselog(open(headerfile, 'rb'))[1:4]
         finally:
             os.unlink(headerfile)
 
         return (user, date, msg)
 
     def applyone(self, repo, node, cl, patchfile, merge=False, log=False,
                  filter=None):
         '''apply the patch in patchfile to the repository as a transplant'''
         (manifest, user, (time, timezone), files, message) = cl[:5]
         date = "%d %d" % (time, timezone)
         extra = {'transplant_source': node}
         if filter:
             (user, date, message) = self.filter(filter, node, cl, patchfile)
 
         if log:
             # we don't translate messages inserted into commits
             message += '\n(transplanted from %s)' % nodemod.hex(node)
 
         self.ui.status(_('applying %s\n') % nodemod.short(node))
         self.ui.note('%s %s\n%s\n' % (user, date, message))
 
         if not patchfile and not merge:
             raise error.Abort(_('can only omit patchfile if merging'))
         if patchfile:
             try:
                 files = set()
                 patch.patch(self.ui, repo, patchfile, files=files, eolmode=None)
                 files = list(files)
             except Exception as inst:
                 seriespath = os.path.join(self.path, 'series')
                 if os.path.exists(seriespath):
                     os.unlink(seriespath)
                 p1 = repo.dirstate.p1()
                 p2 = node
                 self.log(user, date, message, p1, p2, merge=merge)
                 self.ui.write(stringutil.forcebytestr(inst) + '\n')
                 raise TransplantError(_('fix up the working directory and run '
                                         'hg transplant --continue'))
         else:
             files = None
         if merge:
             p1 = repo.dirstate.p1()
             repo.setparents(p1, node)
-            m = match.always(repo.root, '')
+            m = match.always()
         else:
-            m = match.exact(repo.root, '', files)
+            m = match.exact(files)
 
         n = repo.commit(message, user, date, extra=extra, match=m,
                         editor=self.getcommiteditor())
         if not n:
             self.ui.warn(_('skipping emptied changeset %s\n') %
                            nodemod.short(node))
             return None
         if not merge:
             self.transplants.set(n, node)
 
         return n
 
     def canresume(self):
         return os.path.exists(os.path.join(self.path, 'journal'))
 
     def resume(self, repo, source, opts):
         '''recover last transaction and apply remaining changesets'''
         if os.path.exists(os.path.join(self.path, 'journal')):
             n, node = self.recover(repo, source, opts)
             if n:
                 self.ui.status(_('%s transplanted as %s\n') %
                                  (nodemod.short(node),
                                   nodemod.short(n)))
             else:
                 self.ui.status(_('%s skipped due to empty diff\n')
                                % (nodemod.short(node),))
         seriespath = os.path.join(self.path, 'series')
         if not os.path.exists(seriespath):
             self.transplants.write()
             return
         nodes, merges = self.readseries()
         revmap = {}
         for n in nodes:
             revmap[source.changelog.rev(n)] = n
         os.unlink(seriespath)
 
         self.apply(repo, source, revmap, merges, opts)
 
     def recover(self, repo, source, opts):
         '''commit working directory using journal metadata'''
         node, user, date, message, parents = self.readlog()
         merge = False
 
         if not user or not date or not message or not parents[0]:
             raise error.Abort(_('transplant log file is corrupt'))
 
         parent = parents[0]
         if len(parents) > 1:
             if opts.get('parent'):
                 parent = source.lookup(opts['parent'])
                 if parent not in parents:
                     raise error.Abort(_('%s is not a parent of %s') %
                                       (nodemod.short(parent),
                                        nodemod.short(node)))
             else:
                 merge = True
 
         extra = {'transplant_source': node}
         try:
             p1 = repo.dirstate.p1()
             if p1 != parent:
                 raise error.Abort(_('working directory not at transplant '
                                    'parent %s') % nodemod.hex(parent))
             if merge:
                 repo.setparents(p1, parents[1])
             modified, added, removed, deleted = repo.status()[:4]
             if merge or modified or added or removed or deleted:
                 n = repo.commit(message, user, date, extra=extra,
                                 editor=self.getcommiteditor())
                 if not n:
                     raise error.Abort(_('commit failed'))
                 if not merge:
                     self.transplants.set(n, node)
             else:
                 n = None
             self.unlog()
 
             return n, node
         finally:
             # TODO: get rid of this meaningless try/finally enclosing.
             # this is kept only to reduce changes in a patch.
             pass
 
     def readseries(self):
         nodes = []
         merges = []
         cur = nodes
         for line in self.opener.read('series').splitlines():
             if line.startswith('# Merges'):
                 cur = merges
                 continue
             cur.append(revlog.bin(line))
 
         return (nodes, merges)
 
     def saveseries(self, revmap, merges):
         if not revmap:
             return
 
         if not os.path.isdir(self.path):
             os.mkdir(self.path)
         series = self.opener('series', 'w')
         for rev in sorted(revmap):
             series.write(nodemod.hex(revmap[rev]) + '\n')
         if merges:
             series.write('# Merges\n')
             for m in merges:
                 series.write(nodemod.hex(m) + '\n')
         series.close()
 
     def parselog(self, fp):
         parents = []
         message = []
         node = revlog.nullid
         inmsg = False
         user = None
         date = None
         for line in fp.read().splitlines():
             if inmsg:
                 message.append(line)
             elif line.startswith('# User '):
                 user = line[7:]
             elif line.startswith('# Date '):
                 date = line[7:]
             elif line.startswith('# Node ID '):
                 node = revlog.bin(line[10:])
             elif line.startswith('# Parent '):
                 parents.append(revlog.bin(line[9:]))
             elif not line.startswith('# '):
                 inmsg = True
                 message.append(line)
         if None in (user, date):
             raise error.Abort(_("filter corrupted changeset (no user or date)"))
         return (node, user, date, '\n'.join(message), parents)
 
     def log(self, user, date, message, p1, p2, merge=False):
         '''journal changelog metadata for later recover'''
 
         if not os.path.isdir(self.path):
             os.mkdir(self.path)
         fp = self.opener('journal', 'w')
         fp.write('# User %s\n' % user)
         fp.write('# Date %s\n' % date)
         fp.write('# Node ID %s\n' % nodemod.hex(p2))
         fp.write('# Parent ' + nodemod.hex(p1) + '\n')
         if merge:
             fp.write('# Parent ' + nodemod.hex(p2) + '\n')
         fp.write(message.rstrip() + '\n')
         fp.close()
 
     def readlog(self):
         return self.parselog(self.opener('journal'))
 
     def unlog(self):
         '''remove changelog journal'''
         absdst = os.path.join(self.path, 'journal')
         if os.path.exists(absdst):
             os.unlink(absdst)
 
     def transplantfilter(self, repo, source, root):
         def matchfn(node):
             if self.applied(repo, node, root):
                 return False
             if source.changelog.parents(node)[1] != revlog.nullid:
                 return False
             extra = source.changelog.read(node)[5]
             cnode = extra.get('transplant_source')
             if cnode and self.applied(repo, cnode, root):
                 return False
             return True
 
         return matchfn
 
 def hasnode(repo, node):
     try:
         return repo.changelog.rev(node) is not None
     except error.StorageError:
         return False
 
 def browserevs(ui, repo, nodes, opts):
     '''interactively transplant changesets'''
     displayer = logcmdutil.changesetdisplayer(ui, repo, opts)
     transplants = []
     merges = []
     prompt = _('apply changeset? [ynmpcq?]:'
                '$$ &yes, transplant this changeset'
                '$$ &no, skip this changeset'
                '$$ &merge at this changeset'
                '$$ show &patch'
                '$$ &commit selected changesets'
                '$$ &quit and cancel transplant'
                '$$ &? (show this help)')
     for node in nodes:
         displayer.show(repo[node])
         action = None
         while not action:
             choice = ui.promptchoice(prompt)
             action = 'ynmpcq?'[choice:choice + 1]
             if action == '?':
                 for c, t in ui.extractchoices(prompt)[1]:
                     ui.write('%s: %s\n' % (c, t))
                 action = None
             elif action == 'p':
                 parent = repo.changelog.parents(node)[0]
                 for chunk in patch.diff(repo, parent, node):
                     ui.write(chunk)
                 action = None
         if action == 'y':
             transplants.append(node)
         elif action == 'm':
             merges.append(node)
         elif action == 'c':
             break
         elif action == 'q':
             transplants = ()
             merges = ()
             break
     displayer.close()
     return (transplants, merges)
 
 @command('transplant',
     [('s', 'source', '', _('transplant changesets from REPO'), _('REPO')),
     ('b', 'branch', [], _('use this source changeset as head'), _('REV')),
     ('a', 'all', None, _('pull all changesets up to the --branch revisions')),
     ('p', 'prune', [], _('skip over REV'), _('REV')),
     ('m', 'merge', [], _('merge at REV'), _('REV')),
     ('', 'parent', '',
      _('parent to choose when transplanting merge'), _('REV')),
     ('e', 'edit', False, _('invoke editor on commit messages')),
     ('', 'log', None, _('append transplant info to log message')),
     ('c', 'continue', None, _('continue last transplant session '
                               'after fixing conflicts')),
     ('', 'filter', '',
      _('filter changesets through command'), _('CMD'))],
     _('hg transplant [-s REPO] [-b BRANCH [-a]] [-p REV] '
       '[-m REV] [REV]...'),
     helpcategory=command.CATEGORY_CHANGE_MANAGEMENT)
 def transplant(ui, repo, *revs, **opts):
     '''transplant changesets from another branch
 
     Selected changesets will be applied on top of the current working
     directory with the log of the original changeset. The changesets
     are copied and will thus appear twice in the history with different
     identities.
 
     Consider using the graft command if everything is inside the same
     repository - it will use merges and will usually give a better result.
     Use the rebase extension if the changesets are unpublished and you want
     to move them instead of copying them.
 
     If --log is specified, log messages will have a comment appended
     of the form::
 
       (transplanted from CHANGESETHASH)
 
     You can rewrite the changelog message with the --filter option.
     Its argument will be invoked with the current changelog message as
     $1 and the patch as $2.
 
     --source/-s specifies another repository to use for selecting changesets,
     just as if it temporarily had been pulled.
     If --branch/-b is specified, these revisions will be used as
     heads when deciding which changesets to transplant, just as if only
     these revisions had been pulled.
     If --all/-a is specified, all the revisions up to the heads specified
     with --branch will be transplanted.
 
     Example:
 
     - transplant all changes up to REV on top of your current revision::
 
         hg transplant --branch REV --all
 
     You can optionally mark selected transplanted changesets as merge
     changesets. You will not be prompted to transplant any ancestors
     of a merged transplant, and you can merge descendants of them
     normally instead of transplanting them.
 
     Merge changesets may be transplanted directly by specifying the
     proper parent changeset by calling :hg:`transplant --parent`.
 
     If no merges or revisions are provided, :hg:`transplant` will
     start an interactive changeset browser.
 
     If a changeset application fails, you can fix the merge by hand
     and then resume where you left off by calling :hg:`transplant
     --continue/-c`.
     '''
     with repo.wlock():
         return _dotransplant(ui, repo, *revs, **opts)
 
 def _dotransplant(ui, repo, *revs, **opts):
     def incwalk(repo, csets, match=util.always):
         for node in csets:
             if match(node):
                 yield node
 
     def transplantwalk(repo, dest, heads, match=util.always):
         '''Yield all nodes that are ancestors of a head but not ancestors
         of dest.
         If no heads are specified, the heads of repo will be used.'''
         if not heads:
             heads = repo.heads()
         ancestors = []
         ctx = repo[dest]
         for head in heads:
             ancestors.append(ctx.ancestor(repo[head]).node())
         for node in repo.changelog.nodesbetween(ancestors, heads)[0]:
             if match(node):
                 yield node
 
     def checkopts(opts, revs):
         if opts.get('continue'):
             if opts.get('branch') or opts.get('all') or opts.get('merge'):
                 raise error.Abort(_('--continue is incompatible with '
                                    '--branch, --all and --merge'))
             return
         if not (opts.get('source') or revs or
                 opts.get('merge') or opts.get('branch')):
             raise error.Abort(_('no source URL, branch revision, or revision '
                                'list provided'))
         if opts.get('all'):
             if not opts.get('branch'):
                 raise error.Abort(_('--all requires a branch revision'))
             if revs:
                 raise error.Abort(_('--all is incompatible with a '
                                    'revision list'))
 
     opts = pycompat.byteskwargs(opts)
     checkopts(opts, revs)
 
     if not opts.get('log'):
         # deprecated config: transplant.log
         opts['log'] = ui.config('transplant', 'log')
     if not opts.get('filter'):
         # deprecated config: transplant.filter
         opts['filter'] = ui.config('transplant', 'filter')
 
     tp = transplanter(ui, repo, opts)
 
     p1 = repo.dirstate.p1()
     if len(repo) > 0 and p1 == revlog.nullid:
         raise error.Abort(_('no revision checked out'))
     if opts.get('continue'):
         if not tp.canresume():
             raise error.Abort(_('no transplant to continue'))
     else:
         cmdutil.checkunfinished(repo)
         cmdutil.bailifchanged(repo)
 
     sourcerepo = opts.get('source')
     if sourcerepo:
         peer = hg.peer(repo, opts, ui.expandpath(sourcerepo))
         heads = pycompat.maplist(peer.lookup, opts.get('branch', ()))
         target = set(heads)
         for r in revs:
             try:
                 target.add(peer.lookup(r))
             except error.RepoError:
                 pass
         source, csets, cleanupfn = bundlerepo.getremotechanges(ui, repo, peer,
                                     onlyheads=sorted(target), force=True)
     else:
         source = repo
         heads = pycompat.maplist(source.lookup, opts.get('branch', ()))
         cleanupfn = None
 
     try:
         if opts.get('continue'):
             tp.resume(repo, source, opts)
             return
 
         tf = tp.transplantfilter(repo, source, p1)
         if opts.get('prune'):
             prune = set(source[r].node()
                         for r in scmutil.revrange(source, opts.get('prune')))
             matchfn = lambda x: tf(x) and x not in prune
         else:
             matchfn = tf
         merges = pycompat.maplist(source.lookup, opts.get('merge', ()))
         revmap = {}
         if revs:
             for r in scmutil.revrange(source, revs):
                 revmap[int(r)] = source[r].node()
         elif opts.get('all') or not merges:
             if source != repo:
                 alltransplants = incwalk(source, csets, match=matchfn)
             else:
                 alltransplants = transplantwalk(source, p1, heads,
                                                 match=matchfn)
             if opts.get('all'):
                 revs = alltransplants
             else:
                 revs, newmerges = browserevs(ui, source, alltransplants, opts)
                 merges.extend(newmerges)
             for r in revs:
                 revmap[source.changelog.rev(r)] = r
         for r in merges:
             revmap[source.changelog.rev(r)] = r
 
         tp.apply(repo, source, revmap, merges, opts)
     finally:
         if cleanupfn:
             cleanupfn()
 
 revsetpredicate = registrar.revsetpredicate()
 
 @revsetpredicate('transplanted([set])')
 def revsettransplanted(repo, subset, x):
     """Transplanted changesets in set, or all transplanted changesets.
     """
     if x:
         s = revset.getset(repo, subset, x)
     else:
         s = subset
     return smartset.baseset([r for r in s if
         repo[r].extra().get('transplant_source')])
 
 templatekeyword = registrar.templatekeyword()
 
 @templatekeyword('transplanted', requires={'ctx'})
 def kwtransplanted(context, mapping):
     """String. The node identifier of the transplanted
     changeset if any."""
     ctx = context.resource(mapping, 'ctx')
     n = ctx.extra().get('transplant_source')
     return n and nodemod.hex(n) or ''
 
 def extsetup(ui):
     cmdutil.unfinishedstates.append(
         ['transplant/journal', True, False, _('transplant in progress'),
          _("use 'hg transplant --continue' or 'hg update' to abort")])
 
 # tell hggettext to extract docstrings from these functions:
 i18nfunctions = [revsettransplanted, kwtransplanted]

mercurial/changegroup.py

@@ -1,1418 +1,1418 b''
 # changegroup.py - Mercurial changegroup manipulation functions
 #
 #  Copyright 2006 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 os
 import struct
 import weakref
 
 from .i18n import _
 from .node import (
     hex,
     nullid,
     nullrev,
     short,
 )
 
 from . import (
     error,
     match as matchmod,
     mdiff,
     phases,
     pycompat,
     repository,
     util,
 )
 
 _CHANGEGROUPV1_DELTA_HEADER = struct.Struct("20s20s20s20s")
 _CHANGEGROUPV2_DELTA_HEADER = struct.Struct("20s20s20s20s20s")
 _CHANGEGROUPV3_DELTA_HEADER = struct.Struct(">20s20s20s20s20sH")
 
 LFS_REQUIREMENT = 'lfs'
 
 readexactly = util.readexactly
 
 def getchunk(stream):
     """return the next chunk from stream as a string"""
     d = readexactly(stream, 4)
     l = struct.unpack(">l", d)[0]
     if l <= 4:
         if l:
             raise error.Abort(_("invalid chunk length %d") % l)
         return ""
     return readexactly(stream, l - 4)
 
 def chunkheader(length):
     """return a changegroup chunk header (string)"""
     return struct.pack(">l", length + 4)
 
 def closechunk():
     """return a changegroup chunk header (string) for a zero-length chunk"""
     return struct.pack(">l", 0)
 
 def _fileheader(path):
     """Obtain a changegroup chunk header for a named path."""
     return chunkheader(len(path)) + path
 
 def writechunks(ui, chunks, filename, vfs=None):
     """Write chunks to a file and return its filename.
 
     The stream is assumed to be a bundle file.
     Existing files will not be overwritten.
     If no filename is specified, a temporary file is created.
     """
     fh = None
     cleanup = None
     try:
         if filename:
             if vfs:
                 fh = vfs.open(filename, "wb")
             else:
                 # Increase default buffer size because default is usually
                 # small (4k is common on Linux).
                 fh = open(filename, "wb", 131072)
         else:
             fd, filename = pycompat.mkstemp(prefix="hg-bundle-", suffix=".hg")
             fh = os.fdopen(fd, r"wb")
         cleanup = filename
         for c in chunks:
             fh.write(c)
         cleanup = None
         return filename
     finally:
         if fh is not None:
             fh.close()
         if cleanup is not None:
             if filename and vfs:
                 vfs.unlink(cleanup)
             else:
                 os.unlink(cleanup)
 
 class cg1unpacker(object):
     """Unpacker for cg1 changegroup streams.
 
     A changegroup unpacker handles the framing of the revision data in
     the wire format. Most consumers will want to use the apply()
     method to add the changes from the changegroup to a repository.
 
     If you're forwarding a changegroup unmodified to another consumer,
     use getchunks(), which returns an iterator of changegroup
     chunks. This is mostly useful for cases where you need to know the
     data stream has ended by observing the end of the changegroup.
 
     deltachunk() is useful only if you're applying delta data. Most
     consumers should prefer apply() instead.
 
     A few other public methods exist. Those are used only for
     bundlerepo and some debug commands - their use is discouraged.
     """
     deltaheader = _CHANGEGROUPV1_DELTA_HEADER
     deltaheadersize = deltaheader.size
     version = '01'
     _grouplistcount = 1 # One list of files after the manifests
 
     def __init__(self, fh, alg, extras=None):
         if alg is None:
             alg = 'UN'
         if alg not in util.compengines.supportedbundletypes:
             raise error.Abort(_('unknown stream compression type: %s')
                              % alg)
         if alg == 'BZ':
             alg = '_truncatedBZ'
 
         compengine = util.compengines.forbundletype(alg)
         self._stream = compengine.decompressorreader(fh)
         self._type = alg
         self.extras = extras or {}
         self.callback = None
 
     # These methods (compressed, read, seek, tell) all appear to only
     # be used by bundlerepo, but it's a little hard to tell.
     def compressed(self):
         return self._type is not None and self._type != 'UN'
     def read(self, l):
         return self._stream.read(l)
     def seek(self, pos):
         return self._stream.seek(pos)
     def tell(self):
         return self._stream.tell()
     def close(self):
         return self._stream.close()
 
     def _chunklength(self):
         d = readexactly(self._stream, 4)
         l = struct.unpack(">l", d)[0]
         if l <= 4:
             if l:
                 raise error.Abort(_("invalid chunk length %d") % l)
             return 0
         if self.callback:
             self.callback()
         return l - 4
 
     def changelogheader(self):
         """v10 does not have a changelog header chunk"""
         return {}
 
     def manifestheader(self):
         """v10 does not have a manifest header chunk"""
         return {}
 
     def filelogheader(self):
         """return the header of the filelogs chunk, v10 only has the filename"""
         l = self._chunklength()
         if not l:
             return {}
         fname = readexactly(self._stream, l)
         return {'filename': fname}
 
     def _deltaheader(self, headertuple, prevnode):
         node, p1, p2, cs = headertuple
         if prevnode is None:
             deltabase = p1
         else:
             deltabase = prevnode
         flags = 0
         return node, p1, p2, deltabase, cs, flags
 
     def deltachunk(self, prevnode):
         l = self._chunklength()
         if not l:
             return {}
         headerdata = readexactly(self._stream, self.deltaheadersize)
         header = self.deltaheader.unpack(headerdata)
         delta = readexactly(self._stream, l - self.deltaheadersize)
         node, p1, p2, deltabase, cs, flags = self._deltaheader(header, prevnode)
         return (node, p1, p2, cs, deltabase, delta, flags)
 
     def getchunks(self):
         """returns all the chunks contains in the bundle
 
         Used when you need to forward the binary stream to a file or another
         network API. To do so, it parse the changegroup data, otherwise it will
         block in case of sshrepo because it don't know the end of the stream.
         """
         # For changegroup 1 and 2, we expect 3 parts: changelog, manifestlog,
         # and a list of filelogs. For changegroup 3, we expect 4 parts:
         # changelog, manifestlog, a list of tree manifestlogs, and a list of
         # filelogs.
         #
         # Changelog and manifestlog parts are terminated with empty chunks. The
         # tree and file parts are a list of entry sections. Each entry section
         # is a series of chunks terminating in an empty chunk. The list of these
         # entry sections is terminated in yet another empty chunk, so we know
         # we've reached the end of the tree/file list when we reach an empty
         # chunk that was proceeded by no non-empty chunks.
 
         parts = 0
         while parts < 2 + self._grouplistcount:
             noentries = True
             while True:
                 chunk = getchunk(self)
                 if not chunk:
                     # The first two empty chunks represent the end of the
                     # changelog and the manifestlog portions. The remaining
                     # empty chunks represent either A) the end of individual
                     # tree or file entries in the file list, or B) the end of
                     # the entire list. It's the end of the entire list if there
                     # were no entries (i.e. noentries is True).
                     if parts < 2:
                         parts += 1
                     elif noentries:
                         parts += 1
                     break
                 noentries = False
                 yield chunkheader(len(chunk))
                 pos = 0
                 while pos < len(chunk):
                     next = pos + 2**20
                     yield chunk[pos:next]
                     pos = next
             yield closechunk()
 
     def _unpackmanifests(self, repo, revmap, trp, prog):
         self.callback = prog.increment
         # no need to check for empty manifest group here:
         # if the result of the merge of 1 and 2 is the same in 3 and 4,
         # no new manifest will be created and the manifest group will
         # be empty during the pull
         self.manifestheader()
         deltas = self.deltaiter()
         repo.manifestlog.getstorage(b'').addgroup(deltas, revmap, trp)
         prog.complete()
         self.callback = None
 
     def apply(self, repo, tr, srctype, url, targetphase=phases.draft,
               expectedtotal=None):
         """Add the changegroup returned by source.read() to this repo.
         srctype is a string like 'push', 'pull', or 'unbundle'.  url is
         the URL of the repo where this changegroup is coming from.
 
         Return an integer summarizing the change to this repo:
         - nothing changed or no source: 0
         - more heads than before: 1+added heads (2..n)
         - fewer heads than before: -1-removed heads (-2..-n)
         - number of heads stays the same: 1
         """
         repo = repo.unfiltered()
         def csmap(x):
             repo.ui.debug("add changeset %s\n" % short(x))
             return len(cl)
 
         def revmap(x):
             return cl.rev(x)
 
         changesets = files = revisions = 0
 
         try:
             # The transaction may already carry source information. In this
             # case we use the top level data. We overwrite the argument
             # because we need to use the top level value (if they exist)
             # in this function.
             srctype = tr.hookargs.setdefault('source', srctype)
             tr.hookargs.setdefault('url', url)
             repo.hook('prechangegroup',
                       throw=True, **pycompat.strkwargs(tr.hookargs))
 
             # write changelog data to temp files so concurrent readers
             # will not see an inconsistent view
             cl = repo.changelog
             cl.delayupdate(tr)
             oldheads = set(cl.heads())
 
             trp = weakref.proxy(tr)
             # pull off the changeset group
             repo.ui.status(_("adding changesets\n"))
             clstart = len(cl)
             progress = repo.ui.makeprogress(_('changesets'), unit=_('chunks'),
                                             total=expectedtotal)
             self.callback = progress.increment
 
             efiles = set()
             def onchangelog(cl, node):
                 efiles.update(cl.readfiles(node))
 
             self.changelogheader()
             deltas = self.deltaiter()
             cgnodes = cl.addgroup(deltas, csmap, trp, addrevisioncb=onchangelog)
             efiles = len(efiles)
 
             if not cgnodes:
                 repo.ui.develwarn('applied empty changelog from changegroup',
                                   config='warn-empty-changegroup')
             clend = len(cl)
             changesets = clend - clstart
             progress.complete()
             self.callback = None
 
             # pull off the manifest group
             repo.ui.status(_("adding manifests\n"))
             # We know that we'll never have more manifests than we had
             # changesets.
             progress = repo.ui.makeprogress(_('manifests'), unit=_('chunks'),
                                             total=changesets)
             self._unpackmanifests(repo, revmap, trp, progress)
 
             needfiles = {}
             if repo.ui.configbool('server', 'validate'):
                 cl = repo.changelog
                 ml = repo.manifestlog
                 # validate incoming csets have their manifests
                 for cset in pycompat.xrange(clstart, clend):
                     mfnode = cl.changelogrevision(cset).manifest
                     mfest = ml[mfnode].readdelta()
                     # store file cgnodes we must see
                     for f, n in mfest.iteritems():
                         needfiles.setdefault(f, set()).add(n)
 
             # process the files
             repo.ui.status(_("adding file changes\n"))
             newrevs, newfiles = _addchangegroupfiles(
                 repo, self, revmap, trp, efiles, needfiles)
             revisions += newrevs
             files += newfiles
 
             deltaheads = 0
             if oldheads:
                 heads = cl.heads()
                 deltaheads = len(heads) - len(oldheads)
                 for h in heads:
                     if h not in oldheads and repo[h].closesbranch():
                         deltaheads -= 1
             htext = ""
             if deltaheads:
                 htext = _(" (%+d heads)") % deltaheads
 
             repo.ui.status(_("added %d changesets"
                              " with %d changes to %d files%s\n")
                              % (changesets, revisions, files, htext))
             repo.invalidatevolatilesets()
 
             if changesets > 0:
                 if 'node' not in tr.hookargs:
                     tr.hookargs['node'] = hex(cl.node(clstart))
                     tr.hookargs['node_last'] = hex(cl.node(clend - 1))
                     hookargs = dict(tr.hookargs)
                 else:
                     hookargs = dict(tr.hookargs)
                     hookargs['node'] = hex(cl.node(clstart))
                     hookargs['node_last'] = hex(cl.node(clend - 1))
                 repo.hook('pretxnchangegroup',
                           throw=True, **pycompat.strkwargs(hookargs))
 
             added = [cl.node(r) for r in pycompat.xrange(clstart, clend)]
             phaseall = None
             if srctype in ('push', 'serve'):
                 # Old servers can not push the boundary themselves.
                 # New servers won't push the boundary if changeset already
                 # exists locally as secret
                 #
                 # We should not use added here but the list of all change in
                 # the bundle
                 if repo.publishing():
                     targetphase = phaseall = phases.public
                 else:
                     # closer target phase computation
 
                     # Those changesets have been pushed from the
                     # outside, their phases are going to be pushed
                     # alongside. Therefor `targetphase` is
                     # ignored.
                     targetphase = phaseall = phases.draft
             if added:
                 phases.registernew(repo, tr, targetphase, added)
             if phaseall is not None:
                 phases.advanceboundary(repo, tr, phaseall, cgnodes)
 
             if changesets > 0:
 
                 def runhooks():
                     # These hooks run when the lock releases, not when the
                     # transaction closes. So it's possible for the changelog
                     # to have changed since we last saw it.
                     if clstart >= len(repo):
                         return
 
                     repo.hook("changegroup", **pycompat.strkwargs(hookargs))
 
                     for n in added:
                         args = hookargs.copy()
                         args['node'] = hex(n)
                         del args['node_last']
                         repo.hook("incoming", **pycompat.strkwargs(args))
 
                     newheads = [h for h in repo.heads()
                                 if h not in oldheads]
                     repo.ui.log("incoming",
                                 "%d incoming changes - new heads: %s\n",
                                 len(added),
                                 ', '.join([hex(c[:6]) for c in newheads]))
 
                 tr.addpostclose('changegroup-runhooks-%020i' % clstart,
                                 lambda tr: repo._afterlock(runhooks))
         finally:
             repo.ui.flush()
         # never return 0 here:
         if deltaheads < 0:
             ret = deltaheads - 1
         else:
             ret = deltaheads + 1
         return ret
 
     def deltaiter(self):
         """
         returns an iterator of the deltas in this changegroup
 
         Useful for passing to the underlying storage system to be stored.
         """
         chain = None
         for chunkdata in iter(lambda: self.deltachunk(chain), {}):
             # Chunkdata: (node, p1, p2, cs, deltabase, delta, flags)
             yield chunkdata
             chain = chunkdata[0]
 
 class cg2unpacker(cg1unpacker):
     """Unpacker for cg2 streams.
 
     cg2 streams add support for generaldelta, so the delta header
     format is slightly different. All other features about the data
     remain the same.
     """
     deltaheader = _CHANGEGROUPV2_DELTA_HEADER
     deltaheadersize = deltaheader.size
     version = '02'
 
     def _deltaheader(self, headertuple, prevnode):
         node, p1, p2, deltabase, cs = headertuple
         flags = 0
         return node, p1, p2, deltabase, cs, flags
 
 class cg3unpacker(cg2unpacker):
     """Unpacker for cg3 streams.
 
     cg3 streams add support for exchanging treemanifests and revlog
     flags. It adds the revlog flags to the delta header and an empty chunk
     separating manifests and files.
     """
     deltaheader = _CHANGEGROUPV3_DELTA_HEADER
     deltaheadersize = deltaheader.size
     version = '03'
     _grouplistcount = 2 # One list of manifests and one list of files
 
     def _deltaheader(self, headertuple, prevnode):
         node, p1, p2, deltabase, cs, flags = headertuple
         return node, p1, p2, deltabase, cs, flags
 
     def _unpackmanifests(self, repo, revmap, trp, prog):
         super(cg3unpacker, self)._unpackmanifests(repo, revmap, trp, prog)
         for chunkdata in iter(self.filelogheader, {}):
             # If we get here, there are directory manifests in the changegroup
             d = chunkdata["filename"]
             repo.ui.debug("adding %s revisions\n" % d)
             deltas = self.deltaiter()
             if not repo.manifestlog.getstorage(d).addgroup(deltas, revmap, trp):
                 raise error.Abort(_("received dir revlog group is empty"))
 
 class headerlessfixup(object):
     def __init__(self, fh, h):
         self._h = h
         self._fh = fh
     def read(self, n):
         if self._h:
             d, self._h = self._h[:n], self._h[n:]
             if len(d) < n:
                 d += readexactly(self._fh, n - len(d))
             return d
         return readexactly(self._fh, n)
 
 def _revisiondeltatochunks(delta, headerfn):
     """Serialize a revisiondelta to changegroup chunks."""
 
     # The captured revision delta may be encoded as a delta against
     # a base revision or as a full revision. The changegroup format
     # requires that everything on the wire be deltas. So for full
     # revisions, we need to invent a header that says to rewrite
     # data.
 
     if delta.delta is not None:
         prefix, data = b'', delta.delta
     elif delta.basenode == nullid:
         data = delta.revision
         prefix = mdiff.trivialdiffheader(len(data))
     else:
         data = delta.revision
         prefix = mdiff.replacediffheader(delta.baserevisionsize,
                                          len(data))
 
     meta = headerfn(delta)
 
     yield chunkheader(len(meta) + len(prefix) + len(data))
     yield meta
     if prefix:
         yield prefix
     yield data
 
 def _sortnodesellipsis(store, nodes, cl, lookup):
     """Sort nodes for changegroup generation."""
     # Ellipses serving mode.
     #
     # In a perfect world, we'd generate better ellipsis-ified graphs
     # for non-changelog revlogs. In practice, we haven't started doing
     # that yet, so the resulting DAGs for the manifestlog and filelogs
     # are actually full of bogus parentage on all the ellipsis
     # nodes. This has the side effect that, while the contents are
     # correct, the individual DAGs might be completely out of whack in
     # a case like 882681bc3166 and its ancestors (back about 10
     # revisions or so) in the main hg repo.
     #
     # The one invariant we *know* holds is that the new (potentially
     # bogus) DAG shape will be valid if we order the nodes in the
     # order that they're introduced in dramatis personae by the
     # changelog, so what we do is we sort the non-changelog histories
     # by the order in which they are used by the changelog.
     key = lambda n: cl.rev(lookup(n))
     return sorted(nodes, key=key)
 
 def _resolvenarrowrevisioninfo(cl, store, ischangelog, rev, linkrev,
                                linknode, clrevtolocalrev, fullclnodes,
                                precomputedellipsis):
     linkparents = precomputedellipsis[linkrev]
     def local(clrev):
         """Turn a changelog revnum into a local revnum.
 
         The ellipsis dag is stored as revnums on the changelog,
         but when we're producing ellipsis entries for
         non-changelog revlogs, we need to turn those numbers into
         something local. This does that for us, and during the
         changelog sending phase will also expand the stored
         mappings as needed.
         """
         if clrev == nullrev:
             return nullrev
 
         if ischangelog:
             return clrev
 
         # Walk the ellipsis-ized changelog breadth-first looking for a
         # change that has been linked from the current revlog.
         #
         # For a flat manifest revlog only a single step should be necessary
         # as all relevant changelog entries are relevant to the flat
         # manifest.
         #
         # For a filelog or tree manifest dirlog however not every changelog
         # entry will have been relevant, so we need to skip some changelog
         # nodes even after ellipsis-izing.
         walk = [clrev]
         while walk:
             p = walk[0]
             walk = walk[1:]
             if p in clrevtolocalrev:
                 return clrevtolocalrev[p]
             elif p in fullclnodes:
                 walk.extend([pp for pp in cl.parentrevs(p)
                                 if pp != nullrev])
             elif p in precomputedellipsis:
                 walk.extend([pp for pp in precomputedellipsis[p]
                                 if pp != nullrev])
             else:
                 # In this case, we've got an ellipsis with parents
                 # outside the current bundle (likely an
                 # incremental pull). We "know" that we can use the
                 # value of this same revlog at whatever revision
                 # is pointed to by linknode. "Know" is in scare
                 # quotes because I haven't done enough examination
                 # of edge cases to convince myself this is really
                 # a fact - it works for all the (admittedly
                 # thorough) cases in our testsuite, but I would be
                 # somewhat unsurprised to find a case in the wild
                 # where this breaks down a bit. That said, I don't
                 # know if it would hurt anything.
                 for i in pycompat.xrange(rev, 0, -1):
                     if store.linkrev(i) == clrev:
                         return i
                 # We failed to resolve a parent for this node, so
                 # we crash the changegroup construction.
                 raise error.Abort(
                     'unable to resolve parent while packing %r %r'
                     ' for changeset %r' % (store.indexfile, rev, clrev))
 
         return nullrev
 
     if not linkparents or (
         store.parentrevs(rev) == (nullrev, nullrev)):
         p1, p2 = nullrev, nullrev
     elif len(linkparents) == 1:
         p1, = sorted(local(p) for p in linkparents)
         p2 = nullrev
     else:
         p1, p2 = sorted(local(p) for p in linkparents)
 
     p1node, p2node = store.node(p1), store.node(p2)
 
     return p1node, p2node, linknode
 
 def deltagroup(repo, store, nodes, ischangelog, lookup, forcedeltaparentprev,
                topic=None,
                ellipses=False, clrevtolocalrev=None, fullclnodes=None,
                precomputedellipsis=None):
     """Calculate deltas for a set of revisions.
 
     Is a generator of ``revisiondelta`` instances.
 
     If topic is not None, progress detail will be generated using this
     topic name (e.g. changesets, manifests, etc).
     """
     if not nodes:
         return
 
     cl = repo.changelog
 
     if ischangelog:
         # `hg log` shows changesets in storage order. To preserve order
         # across clones, send out changesets in storage order.
         nodesorder = 'storage'
     elif ellipses:
         nodes = _sortnodesellipsis(store, nodes, cl, lookup)
         nodesorder = 'nodes'
     else:
         nodesorder = None
 
     # Perform ellipses filtering and revision massaging. We do this before
     # emitrevisions() because a) filtering out revisions creates less work
     # for emitrevisions() b) dropping revisions would break emitrevisions()'s
     # assumptions about delta choices and we would possibly send a delta
     # referencing a missing base revision.
     #
     # Also, calling lookup() has side-effects with regards to populating
     # data structures. If we don't call lookup() for each node or if we call
     # lookup() after the first pass through each node, things can break -
     # possibly intermittently depending on the python hash seed! For that
     # reason, we store a mapping of all linknodes during the initial node
     # pass rather than use lookup() on the output side.
     if ellipses:
         filtered = []
         adjustedparents = {}
         linknodes = {}
 
         for node in nodes:
             rev = store.rev(node)
             linknode = lookup(node)
             linkrev = cl.rev(linknode)
             clrevtolocalrev[linkrev] = rev
 
             # If linknode is in fullclnodes, it means the corresponding
             # changeset was a full changeset and is being sent unaltered.
             if linknode in fullclnodes:
                 linknodes[node] = linknode
 
             # If the corresponding changeset wasn't in the set computed
             # as relevant to us, it should be dropped outright.
             elif linkrev not in precomputedellipsis:
                 continue
 
             else:
                 # We could probably do this later and avoid the dict
                 # holding state. But it likely doesn't matter.
                 p1node, p2node, linknode = _resolvenarrowrevisioninfo(
                     cl, store, ischangelog, rev, linkrev, linknode,
                     clrevtolocalrev, fullclnodes, precomputedellipsis)
 
                 adjustedparents[node] = (p1node, p2node)
                 linknodes[node] = linknode
 
             filtered.append(node)
 
         nodes = filtered
 
     # We expect the first pass to be fast, so we only engage the progress
     # meter for constructing the revision deltas.
     progress = None
     if topic is not None:
         progress = repo.ui.makeprogress(topic, unit=_('chunks'),
                                         total=len(nodes))
 
     configtarget = repo.ui.config('devel', 'bundle.delta')
     if configtarget not in ('', 'p1', 'full'):
         msg = _("""config "devel.bundle.delta" as unknown value: %s""")
         repo.ui.warn(msg % configtarget)
 
     deltamode = repository.CG_DELTAMODE_STD
     if forcedeltaparentprev:
         deltamode = repository.CG_DELTAMODE_PREV
     elif configtarget == 'p1':
         deltamode = repository.CG_DELTAMODE_P1
     elif configtarget == 'full':
         deltamode = repository.CG_DELTAMODE_FULL
 
     revisions = store.emitrevisions(
         nodes,
         nodesorder=nodesorder,
         revisiondata=True,
         assumehaveparentrevisions=not ellipses,
         deltamode=deltamode)
 
     for i, revision in enumerate(revisions):
         if progress:
             progress.update(i + 1)
 
         if ellipses:
             linknode = linknodes[revision.node]
 
             if revision.node in adjustedparents:
                 p1node, p2node = adjustedparents[revision.node]
                 revision.p1node = p1node
                 revision.p2node = p2node
                 revision.flags |= repository.REVISION_FLAG_ELLIPSIS
 
         else:
             linknode = lookup(revision.node)
 
         revision.linknode = linknode
         yield revision
 
     if progress:
         progress.complete()
 
 class cgpacker(object):
     def __init__(self, repo, oldmatcher, matcher, version,
                  builddeltaheader, manifestsend,
                  forcedeltaparentprev=False,
                  bundlecaps=None, ellipses=False,
                  shallow=False, ellipsisroots=None, fullnodes=None):
         """Given a source repo, construct a bundler.
 
         oldmatcher is a matcher that matches on files the client already has.
         These will not be included in the changegroup.
 
         matcher is a matcher that matches on files to include in the
         changegroup. Used to facilitate sparse changegroups.
 
         forcedeltaparentprev indicates whether delta parents must be against
         the previous revision in a delta group. This should only be used for
         compatibility with changegroup version 1.
 
         builddeltaheader is a callable that constructs the header for a group
         delta.
 
         manifestsend is a chunk to send after manifests have been fully emitted.
 
         ellipses indicates whether ellipsis serving mode is enabled.
 
         bundlecaps is optional and can be used to specify the set of
         capabilities which can be used to build the bundle. While bundlecaps is
         unused in core Mercurial, extensions rely on this feature to communicate
         capabilities to customize the changegroup packer.
 
         shallow indicates whether shallow data might be sent. The packer may
         need to pack file contents not introduced by the changes being packed.
 
         fullnodes is the set of changelog nodes which should not be ellipsis
         nodes. We store this rather than the set of nodes that should be
         ellipsis because for very large histories we expect this to be
         significantly smaller.
         """
         assert oldmatcher
         assert matcher
         self._oldmatcher = oldmatcher
         self._matcher = matcher
 
         self.version = version
         self._forcedeltaparentprev = forcedeltaparentprev
         self._builddeltaheader = builddeltaheader
         self._manifestsend = manifestsend
         self._ellipses = ellipses
 
         # Set of capabilities we can use to build the bundle.
         if bundlecaps is None:
             bundlecaps = set()
         self._bundlecaps = bundlecaps
         self._isshallow = shallow
         self._fullclnodes = fullnodes
 
         # Maps ellipsis revs to their roots at the changelog level.
         self._precomputedellipsis = ellipsisroots
 
         self._repo = repo
 
         if self._repo.ui.verbose and not self._repo.ui.debugflag:
             self._verbosenote = self._repo.ui.note
         else:
             self._verbosenote = lambda s: None
 
     def generate(self, commonrevs, clnodes, fastpathlinkrev, source,
                  changelog=True):
         """Yield a sequence of changegroup byte chunks.
         If changelog is False, changelog data won't be added to changegroup
         """
 
         repo = self._repo
         cl = repo.changelog
 
         self._verbosenote(_('uncompressed size of bundle content:\n'))
         size = 0
 
         clstate, deltas = self._generatechangelog(cl, clnodes,
                                                   generate=changelog)
         for delta in deltas:
             for chunk in _revisiondeltatochunks(delta,
                                                 self._builddeltaheader):
                 size += len(chunk)
                 yield chunk
 
         close = closechunk()
         size += len(close)
         yield closechunk()
 
         self._verbosenote(_('%8.i (changelog)\n') % size)
 
         clrevorder = clstate['clrevorder']
         manifests = clstate['manifests']
         changedfiles = clstate['changedfiles']
 
         # We need to make sure that the linkrev in the changegroup refers to
         # the first changeset that introduced the manifest or file revision.
         # The fastpath is usually safer than the slowpath, because the filelogs
         # are walked in revlog order.
         #
         # When taking the slowpath when the manifest revlog uses generaldelta,
         # the manifest may be walked in the "wrong" order. Without 'clrevorder',
         # we would get an incorrect linkrev (see fix in cc0ff93d0c0c).
         #
         # When taking the fastpath, we are only vulnerable to reordering
         # of the changelog itself. The changelog never uses generaldelta and is
         # never reordered. To handle this case, we simply take the slowpath,
         # which already has the 'clrevorder' logic. This was also fixed in
         # cc0ff93d0c0c.
 
         # Treemanifests don't work correctly with fastpathlinkrev
         # either, because we don't discover which directory nodes to
         # send along with files. This could probably be fixed.
         fastpathlinkrev = fastpathlinkrev and (
             'treemanifest' not in repo.requirements)
 
         fnodes = {}  # needed file nodes
 
         size = 0
         it = self.generatemanifests(
             commonrevs, clrevorder, fastpathlinkrev, manifests, fnodes, source,
             clstate['clrevtomanifestrev'])
 
         for tree, deltas in it:
             if tree:
                 assert self.version == b'03'
                 chunk = _fileheader(tree)
                 size += len(chunk)
                 yield chunk
 
             for delta in deltas:
                 chunks = _revisiondeltatochunks(delta, self._builddeltaheader)
                 for chunk in chunks:
                     size += len(chunk)
                     yield chunk
 
             close = closechunk()
             size += len(close)
             yield close
 
         self._verbosenote(_('%8.i (manifests)\n') % size)
         yield self._manifestsend
 
         mfdicts = None
         if self._ellipses and self._isshallow:
             mfdicts = [(self._repo.manifestlog[n].read(), lr)
                        for (n, lr) in manifests.iteritems()]
 
         manifests.clear()
         clrevs = set(cl.rev(x) for x in clnodes)
 
         it = self.generatefiles(changedfiles, commonrevs,
                                 source, mfdicts, fastpathlinkrev,
                                 fnodes, clrevs)
 
         for path, deltas in it:
             h = _fileheader(path)
             size = len(h)
             yield h
 
             for delta in deltas:
                 chunks = _revisiondeltatochunks(delta, self._builddeltaheader)
                 for chunk in chunks:
                     size += len(chunk)
                     yield chunk
 
             close = closechunk()
             size += len(close)
             yield close
 
             self._verbosenote(_('%8.i  %s\n') % (size, path))
 
         yield closechunk()
 
         if clnodes:
             repo.hook('outgoing', node=hex(clnodes[0]), source=source)
 
     def _generatechangelog(self, cl, nodes, generate=True):
         """Generate data for changelog chunks.
 
         Returns a 2-tuple of a dict containing state and an iterable of
         byte chunks. The state will not be fully populated until the
         chunk stream has been fully consumed.
 
         if generate is False, the state will be fully populated and no chunk
         stream will be yielded
         """
         clrevorder = {}
         manifests = {}
         mfl = self._repo.manifestlog
         changedfiles = set()
         clrevtomanifestrev = {}
 
         state = {
             'clrevorder': clrevorder,
             'manifests': manifests,
             'changedfiles': changedfiles,
             'clrevtomanifestrev': clrevtomanifestrev,
         }
 
         if not (generate or self._ellipses):
             # sort the nodes in storage order
             nodes = sorted(nodes, key=cl.rev)
             for node in nodes:
                 c = cl.changelogrevision(node)
                 clrevorder[node] = len(clrevorder)
                 # record the first changeset introducing this manifest version
                 manifests.setdefault(c.manifest, node)
                 # Record a complete list of potentially-changed files in
                 # this manifest.
                 changedfiles.update(c.files)
 
             return state, ()
 
         # Callback for the changelog, used to collect changed files and
         # manifest nodes.
         # Returns the linkrev node (identity in the changelog case).
         def lookupcl(x):
             c = cl.changelogrevision(x)
             clrevorder[x] = len(clrevorder)
 
             if self._ellipses:
                 # Only update manifests if x is going to be sent. Otherwise we
                 # end up with bogus linkrevs specified for manifests and
                 # we skip some manifest nodes that we should otherwise
                 # have sent.
                 if (x in self._fullclnodes
                     or cl.rev(x) in self._precomputedellipsis):
 
                     manifestnode = c.manifest
                     # Record the first changeset introducing this manifest
                     # version.
                     manifests.setdefault(manifestnode, x)
                     # Set this narrow-specific dict so we have the lowest
                     # manifest revnum to look up for this cl revnum. (Part of
                     # mapping changelog ellipsis parents to manifest ellipsis
                     # parents)
                     clrevtomanifestrev.setdefault(
                         cl.rev(x), mfl.rev(manifestnode))
                 # We can't trust the changed files list in the changeset if the
                 # client requested a shallow clone.
                 if self._isshallow:
                     changedfiles.update(mfl[c.manifest].read().keys())
                 else:
                     changedfiles.update(c.files)
             else:
                 # record the first changeset introducing this manifest version
                 manifests.setdefault(c.manifest, x)
                 # Record a complete list of potentially-changed files in
                 # this manifest.
                 changedfiles.update(c.files)
 
             return x
 
         gen = deltagroup(
             self._repo, cl, nodes, True, lookupcl,
             self._forcedeltaparentprev,
             ellipses=self._ellipses,
             topic=_('changesets'),
             clrevtolocalrev={},
             fullclnodes=self._fullclnodes,
             precomputedellipsis=self._precomputedellipsis)
 
         return state, gen
 
     def generatemanifests(self, commonrevs, clrevorder, fastpathlinkrev,
                           manifests, fnodes, source, clrevtolocalrev):
         """Returns an iterator of changegroup chunks containing manifests.
 
         `source` is unused here, but is used by extensions like remotefilelog to
         change what is sent based in pulls vs pushes, etc.
         """
         repo = self._repo
         mfl = repo.manifestlog
         tmfnodes = {'': manifests}
 
         # Callback for the manifest, used to collect linkrevs for filelog
         # revisions.
         # Returns the linkrev node (collected in lookupcl).
         def makelookupmflinknode(tree, nodes):
             if fastpathlinkrev:
                 assert not tree
                 return manifests.__getitem__
 
             def lookupmflinknode(x):
                 """Callback for looking up the linknode for manifests.
 
                 Returns the linkrev node for the specified manifest.
 
                 SIDE EFFECT:
 
                 1) fclnodes gets populated with the list of relevant
                    file nodes if we're not using fastpathlinkrev
                 2) When treemanifests are in use, collects treemanifest nodes
                    to send
 
                 Note that this means manifests must be completely sent to
                 the client before you can trust the list of files and
                 treemanifests to send.
                 """
                 clnode = nodes[x]
                 mdata = mfl.get(tree, x).readfast(shallow=True)
                 for p, n, fl in mdata.iterentries():
                     if fl == 't': # subdirectory manifest
                         subtree = tree + p + '/'
                         tmfclnodes = tmfnodes.setdefault(subtree, {})
                         tmfclnode = tmfclnodes.setdefault(n, clnode)
                         if clrevorder[clnode] < clrevorder[tmfclnode]:
                             tmfclnodes[n] = clnode
                     else:
                         f = tree + p
                         fclnodes = fnodes.setdefault(f, {})
                         fclnode = fclnodes.setdefault(n, clnode)
                         if clrevorder[clnode] < clrevorder[fclnode]:
                             fclnodes[n] = clnode
                 return clnode
             return lookupmflinknode
 
         while tmfnodes:
             tree, nodes = tmfnodes.popitem()
 
             should_visit = self._matcher.visitdir(tree[:-1] or '.')
             if tree and not should_visit:
                 continue
 
             store = mfl.getstorage(tree)
 
             if not should_visit:
                 # No nodes to send because this directory is out of
                 # the client's view of the repository (probably
                 # because of narrow clones). Do this even for the root
                 # directory (tree=='')
                 prunednodes = []
             else:
                 # Avoid sending any manifest nodes we can prove the
                 # client already has by checking linkrevs. See the
                 # related comment in generatefiles().
                 prunednodes = self._prunemanifests(store, nodes, commonrevs)
 
             if tree and not prunednodes:
                 continue
 
             lookupfn = makelookupmflinknode(tree, nodes)
 
             deltas = deltagroup(
                 self._repo, store, prunednodes, False, lookupfn,
                 self._forcedeltaparentprev,
                 ellipses=self._ellipses,
                 topic=_('manifests'),
                 clrevtolocalrev=clrevtolocalrev,
                 fullclnodes=self._fullclnodes,
                 precomputedellipsis=self._precomputedellipsis)
 
             if not self._oldmatcher.visitdir(store.tree[:-1] or '.'):
                 yield tree, deltas
             else:
                 # 'deltas' is a generator and we need to consume it even if
                 # we are not going to send it because a side-effect is that
                 # it updates tmdnodes (via lookupfn)
                 for d in deltas:
                     pass
                 if not tree:
                     yield tree, []
 
     def _prunemanifests(self, store, nodes, commonrevs):
         # This is split out as a separate method to allow filtering
         # commonrevs in extension code.
         #
         # TODO(augie): this shouldn't be required, instead we should
         # make filtering of revisions to send delegated to the store
         # layer.
         frev, flr = store.rev, store.linkrev
         return [n for n in nodes if flr(frev(n)) not in commonrevs]
 
     # The 'source' parameter is useful for extensions
     def generatefiles(self, changedfiles, commonrevs, source,
                       mfdicts, fastpathlinkrev, fnodes, clrevs):
         changedfiles = [f for f in changedfiles
                         if self._matcher(f) and not self._oldmatcher(f)]
 
         if not fastpathlinkrev:
             def normallinknodes(unused, fname):
                 return fnodes.get(fname, {})
         else:
             cln = self._repo.changelog.node
 
             def normallinknodes(store, fname):
                 flinkrev = store.linkrev
                 fnode = store.node
                 revs = ((r, flinkrev(r)) for r in store)
                 return dict((fnode(r), cln(lr))
                             for r, lr in revs if lr in clrevs)
 
         clrevtolocalrev = {}
 
         if self._isshallow:
             # In a shallow clone, the linknodes callback needs to also include
             # those file nodes that are in the manifests we sent but weren't
             # introduced by those manifests.
             commonctxs = [self._repo[c] for c in commonrevs]
             clrev = self._repo.changelog.rev
 
             def linknodes(flog, fname):
                 for c in commonctxs:
                     try:
                         fnode = c.filenode(fname)
                         clrevtolocalrev[c.rev()] = flog.rev(fnode)
                     except error.ManifestLookupError:
                         pass
                 links = normallinknodes(flog, fname)
                 if len(links) != len(mfdicts):
                     for mf, lr in mfdicts:
                         fnode = mf.get(fname, None)
                         if fnode in links:
                             links[fnode] = min(links[fnode], lr, key=clrev)
                         elif fnode:
                             links[fnode] = lr
                 return links
         else:
             linknodes = normallinknodes
 
         repo = self._repo
         progress = repo.ui.makeprogress(_('files'), unit=_('files'),
                                         total=len(changedfiles))
         for i, fname in enumerate(sorted(changedfiles)):
             filerevlog = repo.file(fname)
             if not filerevlog:
                 raise error.Abort(_("empty or missing file data for %s") %
                                   fname)
 
             clrevtolocalrev.clear()
 
             linkrevnodes = linknodes(filerevlog, fname)
             # Lookup for filenodes, we collected the linkrev nodes above in the
             # fastpath case and with lookupmf in the slowpath case.
             def lookupfilelog(x):
                 return linkrevnodes[x]
 
             frev, flr = filerevlog.rev, filerevlog.linkrev
             # Skip sending any filenode we know the client already
             # has. This avoids over-sending files relatively
             # inexpensively, so it's not a problem if we under-filter
             # here.
             filenodes = [n for n in linkrevnodes
                          if flr(frev(n)) not in commonrevs]
 
             if not filenodes:
                 continue
 
             progress.update(i + 1, item=fname)
 
             deltas = deltagroup(
                 self._repo, filerevlog, filenodes, False, lookupfilelog,
                 self._forcedeltaparentprev,
                 ellipses=self._ellipses,
                 clrevtolocalrev=clrevtolocalrev,
                 fullclnodes=self._fullclnodes,
                 precomputedellipsis=self._precomputedellipsis)
 
             yield fname, deltas
 
         progress.complete()
 
 def _makecg1packer(repo, oldmatcher, matcher, bundlecaps,
                    ellipses=False, shallow=False, ellipsisroots=None,
                    fullnodes=None):
     builddeltaheader = lambda d: _CHANGEGROUPV1_DELTA_HEADER.pack(
         d.node, d.p1node, d.p2node, d.linknode)
 
     return cgpacker(repo, oldmatcher, matcher, b'01',
                     builddeltaheader=builddeltaheader,
                     manifestsend=b'',
                     forcedeltaparentprev=True,
                     bundlecaps=bundlecaps,
                     ellipses=ellipses,
                     shallow=shallow,
                     ellipsisroots=ellipsisroots,
                     fullnodes=fullnodes)
 
 def _makecg2packer(repo, oldmatcher, matcher, bundlecaps,
                    ellipses=False, shallow=False, ellipsisroots=None,
                    fullnodes=None):
     builddeltaheader = lambda d: _CHANGEGROUPV2_DELTA_HEADER.pack(
         d.node, d.p1node, d.p2node, d.basenode, d.linknode)
 
     return cgpacker(repo, oldmatcher, matcher, b'02',
                     builddeltaheader=builddeltaheader,
                     manifestsend=b'',
                     bundlecaps=bundlecaps,
                     ellipses=ellipses,
                     shallow=shallow,
                     ellipsisroots=ellipsisroots,
                     fullnodes=fullnodes)
 
 def _makecg3packer(repo, oldmatcher, matcher, bundlecaps,
                    ellipses=False, shallow=False, ellipsisroots=None,
                    fullnodes=None):
     builddeltaheader = lambda d: _CHANGEGROUPV3_DELTA_HEADER.pack(
         d.node, d.p1node, d.p2node, d.basenode, d.linknode, d.flags)
 
     return cgpacker(repo, oldmatcher, matcher, b'03',
                     builddeltaheader=builddeltaheader,
                     manifestsend=closechunk(),
                     bundlecaps=bundlecaps,
                     ellipses=ellipses,
                     shallow=shallow,
                     ellipsisroots=ellipsisroots,
                     fullnodes=fullnodes)
 
 _packermap = {'01': (_makecg1packer, cg1unpacker),
              # cg2 adds support for exchanging generaldelta
              '02': (_makecg2packer, cg2unpacker),
              # cg3 adds support for exchanging revlog flags and treemanifests
              '03': (_makecg3packer, cg3unpacker),
 }
 
 def allsupportedversions(repo):
     versions = set(_packermap.keys())
     if not (repo.ui.configbool('experimental', 'changegroup3') or
             repo.ui.configbool('experimental', 'treemanifest') or
             'treemanifest' in repo.requirements):
         versions.discard('03')
     return versions
 
 # Changegroup versions that can be applied to the repo
 def supportedincomingversions(repo):
     return allsupportedversions(repo)
 
 # Changegroup versions that can be created from the repo
 def supportedoutgoingversions(repo):
     versions = allsupportedversions(repo)
     if 'treemanifest' in repo.requirements:
         # Versions 01 and 02 support only flat manifests and it's just too
         # expensive to convert between the flat manifest and tree manifest on
         # the fly. Since tree manifests are hashed differently, all of history
         # would have to be converted. Instead, we simply don't even pretend to
         # support versions 01 and 02.
         versions.discard('01')
         versions.discard('02')
     if repository.NARROW_REQUIREMENT in repo.requirements:
         # Versions 01 and 02 don't support revlog flags, and we need to
         # support that for stripping and unbundling to work.
         versions.discard('01')
         versions.discard('02')
     if LFS_REQUIREMENT in repo.requirements:
         # Versions 01 and 02 don't support revlog flags, and we need to
         # mark LFS entries with REVIDX_EXTSTORED.
         versions.discard('01')
         versions.discard('02')
 
     return versions
 
 def localversion(repo):
     # Finds the best version to use for bundles that are meant to be used
     # locally, such as those from strip and shelve, and temporary bundles.
     return max(supportedoutgoingversions(repo))
 
 def safeversion(repo):
     # Finds the smallest version that it's safe to assume clients of the repo
     # will support. For example, all hg versions that support generaldelta also
     # support changegroup 02.
     versions = supportedoutgoingversions(repo)
     if 'generaldelta' in repo.requirements:
         versions.discard('01')
     assert versions
     return min(versions)
 
 def getbundler(version, repo, bundlecaps=None, oldmatcher=None,
                matcher=None, ellipses=False, shallow=False,
                ellipsisroots=None, fullnodes=None):
     assert version in supportedoutgoingversions(repo)
 
     if matcher is None:
-        matcher = matchmod.always(repo.root, '')
+        matcher = matchmod.always()
     if oldmatcher is None:
-        oldmatcher = matchmod.never(repo.root, '')
+        oldmatcher = matchmod.never()
 
     if version == '01' and not matcher.always():
         raise error.ProgrammingError('version 01 changegroups do not support '
                                      'sparse file matchers')
 
     if ellipses and version in (b'01', b'02'):
         raise error.Abort(
             _('ellipsis nodes require at least cg3 on client and server, '
               'but negotiated version %s') % version)
 
     # Requested files could include files not in the local store. So
     # filter those out.
     matcher = repo.narrowmatch(matcher)
 
     fn = _packermap[version][0]
     return fn(repo, oldmatcher, matcher, bundlecaps, ellipses=ellipses,
               shallow=shallow, ellipsisroots=ellipsisroots,
               fullnodes=fullnodes)
 
 def getunbundler(version, fh, alg, extras=None):
     return _packermap[version][1](fh, alg, extras=extras)
 
 def _changegroupinfo(repo, nodes, source):
     if repo.ui.verbose or source == 'bundle':
         repo.ui.status(_("%d changesets found\n") % len(nodes))
     if repo.ui.debugflag:
         repo.ui.debug("list of changesets:\n")
         for node in nodes:
             repo.ui.debug("%s\n" % hex(node))
 
 def makechangegroup(repo, outgoing, version, source, fastpath=False,
                     bundlecaps=None):
     cgstream = makestream(repo, outgoing, version, source,
                           fastpath=fastpath, bundlecaps=bundlecaps)
     return getunbundler(version, util.chunkbuffer(cgstream), None,
                         {'clcount': len(outgoing.missing) })
 
 def makestream(repo, outgoing, version, source, fastpath=False,
                bundlecaps=None, matcher=None):
     bundler = getbundler(version, repo, bundlecaps=bundlecaps,
                          matcher=matcher)
 
     repo = repo.unfiltered()
     commonrevs = outgoing.common
     csets = outgoing.missing
     heads = outgoing.missingheads
     # We go through the fast path if we get told to, or if all (unfiltered
     # heads have been requested (since we then know there all linkrevs will
     # be pulled by the client).
     heads.sort()
     fastpathlinkrev = fastpath or (
             repo.filtername is None and heads == sorted(repo.heads()))
 
     repo.hook('preoutgoing', throw=True, source=source)
     _changegroupinfo(repo, csets, source)
     return bundler.generate(commonrevs, csets, fastpathlinkrev, source)
 
 def _addchangegroupfiles(repo, source, revmap, trp, expectedfiles, needfiles):
     revisions = 0
     files = 0
     progress = repo.ui.makeprogress(_('files'), unit=_('files'),
                                     total=expectedfiles)
     for chunkdata in iter(source.filelogheader, {}):
         files += 1
         f = chunkdata["filename"]
         repo.ui.debug("adding %s revisions\n" % f)
         progress.increment()
         fl = repo.file(f)
         o = len(fl)
         try:
             deltas = source.deltaiter()
             if not fl.addgroup(deltas, revmap, trp):
                 raise error.Abort(_("received file revlog group is empty"))
         except error.CensoredBaseError as e:
             raise error.Abort(_("received delta base is censored: %s") % e)
         revisions += len(fl) - o
         if f in needfiles:
             needs = needfiles[f]
             for new in pycompat.xrange(o, len(fl)):
                 n = fl.node(new)
                 if n in needs:
                     needs.remove(n)
                 else:
                     raise error.Abort(
                         _("received spurious file revlog entry"))
             if not needs:
                 del needfiles[f]
     progress.complete()
 
     for f, needs in needfiles.iteritems():
         fl = repo.file(f)
         for n in needs:
             try:
                 fl.rev(n)
             except error.LookupError:
                 raise error.Abort(
                     _('missing file data for %s:%s - run hg verify') %
                     (f, hex(n)))
 
     return revisions, files

mercurial/dirstate.py

@@ -1,1508 +1,1508 b''
 # dirstate.py - working directory tracking for mercurial
 #
 # Copyright 2005-2007 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 collections
 import contextlib
 import errno
 import os
 import stat
 
 from .i18n import _
 from .node import nullid
 from . import (
     encoding,
     error,
     match as matchmod,
     pathutil,
     policy,
     pycompat,
     scmutil,
     txnutil,
     util,
 )
 
 parsers = policy.importmod(r'parsers')
 
 propertycache = util.propertycache
 filecache = scmutil.filecache
 _rangemask = 0x7fffffff
 
 dirstatetuple = parsers.dirstatetuple
 
 class repocache(filecache):
     """filecache for files in .hg/"""
     def join(self, obj, fname):
         return obj._opener.join(fname)
 
 class rootcache(filecache):
     """filecache for files in the repository root"""
     def join(self, obj, fname):
         return obj._join(fname)
 
 def _getfsnow(vfs):
     '''Get "now" timestamp on filesystem'''
     tmpfd, tmpname = vfs.mkstemp()
     try:
         return os.fstat(tmpfd)[stat.ST_MTIME]
     finally:
         os.close(tmpfd)
         vfs.unlink(tmpname)
 
 class dirstate(object):
 
     def __init__(self, opener, ui, root, validate, sparsematchfn):
         '''Create a new dirstate object.
 
         opener is an open()-like callable that can be used to open the
         dirstate file; root is the root of the directory tracked by
         the dirstate.
         '''
         self._opener = opener
         self._validate = validate
         self._root = root
         self._sparsematchfn = sparsematchfn
         # ntpath.join(root, '') of Python 2.7.9 does not add sep if root is
         # UNC path pointing to root share (issue4557)
         self._rootdir = pathutil.normasprefix(root)
         self._dirty = False
         self._lastnormaltime = 0
         self._ui = ui
         self._filecache = {}
         self._parentwriters = 0
         self._filename = 'dirstate'
         self._pendingfilename = '%s.pending' % self._filename
         self._plchangecallbacks = {}
         self._origpl = None
         self._updatedfiles = set()
         self._mapcls = dirstatemap
         # Access and cache cwd early, so we don't access it for the first time
         # after a working-copy update caused it to not exist (accessing it then
         # raises an exception).
         self._cwd
 
     @contextlib.contextmanager
     def parentchange(self):
         '''Context manager for handling dirstate parents.
 
         If an exception occurs in the scope of the context manager,
         the incoherent dirstate won't be written when wlock is
         released.
         '''
         self._parentwriters += 1
         yield
         # Typically we want the "undo" step of a context manager in a
         # finally block so it happens even when an exception
         # occurs. In this case, however, we only want to decrement
         # parentwriters if the code in the with statement exits
         # normally, so we don't have a try/finally here on purpose.
         self._parentwriters -= 1
 
     def pendingparentchange(self):
         '''Returns true if the dirstate is in the middle of a set of changes
         that modify the dirstate parent.
         '''
         return self._parentwriters > 0
 
     @propertycache
     def _map(self):
         """Return the dirstate contents (see documentation for dirstatemap)."""
         self._map = self._mapcls(self._ui, self._opener, self._root)
         return self._map
 
     @property
     def _sparsematcher(self):
         """The matcher for the sparse checkout.
 
         The working directory may not include every file from a manifest. The
         matcher obtained by this property will match a path if it is to be
         included in the working directory.
         """
         # TODO there is potential to cache this property. For now, the matcher
         # is resolved on every access. (But the called function does use a
         # cache to keep the lookup fast.)
         return self._sparsematchfn()
 
     @repocache('branch')
     def _branch(self):
         try:
             return self._opener.read("branch").strip() or "default"
         except IOError as inst:
             if inst.errno != errno.ENOENT:
                 raise
             return "default"
 
     @property
     def _pl(self):
         return self._map.parents()
 
     def hasdir(self, d):
         return self._map.hastrackeddir(d)
 
     @rootcache('.hgignore')
     def _ignore(self):
         files = self._ignorefiles()
         if not files:
-            return matchmod.never(self._root, '')
+            return matchmod.never()
 
         pats = ['include:%s' % f for f in files]
         return matchmod.match(self._root, '', [], pats, warn=self._ui.warn)
 
     @propertycache
     def _slash(self):
         return self._ui.configbool('ui', 'slash') and pycompat.ossep != '/'
 
     @propertycache
     def _checklink(self):
         return util.checklink(self._root)
 
     @propertycache
     def _checkexec(self):
         return util.checkexec(self._root)
 
     @propertycache
     def _checkcase(self):
         return not util.fscasesensitive(self._join('.hg'))
 
     def _join(self, f):
         # much faster than os.path.join()
         # it's safe because f is always a relative path
         return self._rootdir + f
 
     def flagfunc(self, buildfallback):
         if self._checklink and self._checkexec:
             def f(x):
                 try:
                     st = os.lstat(self._join(x))
                     if util.statislink(st):
                         return 'l'
                     if util.statisexec(st):
                         return 'x'
                 except OSError:
                     pass
                 return ''
             return f
 
         fallback = buildfallback()
         if self._checklink:
             def f(x):
                 if os.path.islink(self._join(x)):
                     return 'l'
                 if 'x' in fallback(x):
                     return 'x'
                 return ''
             return f
         if self._checkexec:
             def f(x):
                 if 'l' in fallback(x):
                     return 'l'
                 if util.isexec(self._join(x)):
                     return 'x'
                 return ''
             return f
         else:
             return fallback
 
     @propertycache
     def _cwd(self):
         # internal config: ui.forcecwd
         forcecwd = self._ui.config('ui', 'forcecwd')
         if forcecwd:
             return forcecwd
         return encoding.getcwd()
 
     def getcwd(self):
         '''Return the path from which a canonical path is calculated.
 
         This path should be used to resolve file patterns or to convert
         canonical paths back to file paths for display. It shouldn't be
         used to get real file paths. Use vfs functions instead.
         '''
         cwd = self._cwd
         if cwd == self._root:
             return ''
         # self._root ends with a path separator if self._root is '/' or 'C:\'
         rootsep = self._root
         if not util.endswithsep(rootsep):
             rootsep += pycompat.ossep
         if cwd.startswith(rootsep):
             return cwd[len(rootsep):]
         else:
             # we're outside the repo. return an absolute path.
             return cwd
 
     def pathto(self, f, cwd=None):
         if cwd is None:
             cwd = self.getcwd()
         path = util.pathto(self._root, cwd, f)
         if self._slash:
             return util.pconvert(path)
         return path
 
     def __getitem__(self, key):
         '''Return the current state of key (a filename) in the dirstate.
 
         States are:
           n  normal
           m  needs merging
           r  marked for removal
           a  marked for addition
           ?  not tracked
         '''
         return self._map.get(key, ("?",))[0]
 
     def __contains__(self, key):
         return key in self._map
 
     def __iter__(self):
         return iter(sorted(self._map))
 
     def items(self):
         return self._map.iteritems()
 
     iteritems = items
 
     def parents(self):
         return [self._validate(p) for p in self._pl]
 
     def p1(self):
         return self._validate(self._pl[0])
 
     def p2(self):
         return self._validate(self._pl[1])
 
     def branch(self):
         return encoding.tolocal(self._branch)
 
     def setparents(self, p1, p2=nullid):
         """Set dirstate parents to p1 and p2.
 
         When moving from two parents to one, 'm' merged entries a
         adjusted to normal and previous copy records discarded and
         returned by the call.
 
         See localrepo.setparents()
         """
         if self._parentwriters == 0:
             raise ValueError("cannot set dirstate parent without "
                              "calling dirstate.beginparentchange")
 
         self._dirty = True
         oldp2 = self._pl[1]
         if self._origpl is None:
             self._origpl = self._pl
         self._map.setparents(p1, p2)
         copies = {}
         if oldp2 != nullid and p2 == nullid:
             candidatefiles = self._map.nonnormalset.union(
                                 self._map.otherparentset)
             for f in candidatefiles:
                 s = self._map.get(f)
                 if s is None:
                     continue
 
                 # Discard 'm' markers when moving away from a merge state
                 if s[0] == 'm':
                     source = self._map.copymap.get(f)
                     if source:
                         copies[f] = source
                     self.normallookup(f)
                 # Also fix up otherparent markers
                 elif s[0] == 'n' and s[2] == -2:
                     source = self._map.copymap.get(f)
                     if source:
                         copies[f] = source
                     self.add(f)
         return copies
 
     def setbranch(self, branch):
         self.__class__._branch.set(self, encoding.fromlocal(branch))
         f = self._opener('branch', 'w', atomictemp=True, checkambig=True)
         try:
             f.write(self._branch + '\n')
             f.close()
 
             # make sure filecache has the correct stat info for _branch after
             # replacing the underlying file
             ce = self._filecache['_branch']
             if ce:
                 ce.refresh()
         except: # re-raises
             f.discard()
             raise
 
     def invalidate(self):
         '''Causes the next access to reread the dirstate.
 
         This is different from localrepo.invalidatedirstate() because it always
         rereads the dirstate. Use localrepo.invalidatedirstate() if you want to
         check whether the dirstate has changed before rereading it.'''
 
         for a in (r"_map", r"_branch", r"_ignore"):
             if a in self.__dict__:
                 delattr(self, a)
         self._lastnormaltime = 0
         self._dirty = False
         self._updatedfiles.clear()
         self._parentwriters = 0
         self._origpl = None
 
     def copy(self, source, dest):
         """Mark dest as a copy of source. Unmark dest if source is None."""
         if source == dest:
             return
         self._dirty = True
         if source is not None:
             self._map.copymap[dest] = source
             self._updatedfiles.add(source)
             self._updatedfiles.add(dest)
         elif self._map.copymap.pop(dest, None):
             self._updatedfiles.add(dest)
 
     def copied(self, file):
         return self._map.copymap.get(file, None)
 
     def copies(self):
         return self._map.copymap
 
     def _addpath(self, f, state, mode, size, mtime):
         oldstate = self[f]
         if state == 'a' or oldstate == 'r':
             scmutil.checkfilename(f)
             if self._map.hastrackeddir(f):
                 raise error.Abort(_('directory %r already in dirstate') %
                                   pycompat.bytestr(f))
             # shadows
             for d in util.finddirs(f):
                 if self._map.hastrackeddir(d):
                     break
                 entry = self._map.get(d)
                 if entry is not None and entry[0] != 'r':
                     raise error.Abort(
                         _('file %r in dirstate clashes with %r') %
                         (pycompat.bytestr(d), pycompat.bytestr(f)))
         self._dirty = True
         self._updatedfiles.add(f)
         self._map.addfile(f, oldstate, state, mode, size, mtime)
 
     def normal(self, f):
         '''Mark a file normal and clean.'''
         s = os.lstat(self._join(f))
         mtime = s[stat.ST_MTIME]
         self._addpath(f, 'n', s.st_mode,
                       s.st_size & _rangemask, mtime & _rangemask)
         self._map.copymap.pop(f, None)
         if f in self._map.nonnormalset:
             self._map.nonnormalset.remove(f)
         if mtime > self._lastnormaltime:
             # Remember the most recent modification timeslot for status(),
             # to make sure we won't miss future size-preserving file content
             # modifications that happen within the same timeslot.
             self._lastnormaltime = mtime
 
     def normallookup(self, f):
         '''Mark a file normal, but possibly dirty.'''
         if self._pl[1] != nullid:
             # if there is a merge going on and the file was either
             # in state 'm' (-1) or coming from other parent (-2) before
             # being removed, restore that state.
             entry = self._map.get(f)
             if entry is not None:
                 if entry[0] == 'r' and entry[2] in (-1, -2):
                     source = self._map.copymap.get(f)
                     if entry[2] == -1:
                         self.merge(f)
                     elif entry[2] == -2:
                         self.otherparent(f)
                     if source:
                         self.copy(source, f)
                     return
                 if entry[0] == 'm' or entry[0] == 'n' and entry[2] == -2:
                     return
         self._addpath(f, 'n', 0, -1, -1)
         self._map.copymap.pop(f, None)
 
     def otherparent(self, f):
         '''Mark as coming from the other parent, always dirty.'''
         if self._pl[1] == nullid:
             raise error.Abort(_("setting %r to other parent "
                                "only allowed in merges") % f)
         if f in self and self[f] == 'n':
             # merge-like
             self._addpath(f, 'm', 0, -2, -1)
         else:
             # add-like
             self._addpath(f, 'n', 0, -2, -1)
         self._map.copymap.pop(f, None)
 
     def add(self, f):
         '''Mark a file added.'''
         self._addpath(f, 'a', 0, -1, -1)
         self._map.copymap.pop(f, None)
 
     def remove(self, f):
         '''Mark a file removed.'''
         self._dirty = True
         oldstate = self[f]
         size = 0
         if self._pl[1] != nullid:
             entry = self._map.get(f)
             if entry is not None:
                 # backup the previous state
                 if entry[0] == 'm': # merge
                     size = -1
                 elif entry[0] == 'n' and entry[2] == -2: # other parent
                     size = -2
                     self._map.otherparentset.add(f)
         self._updatedfiles.add(f)
         self._map.removefile(f, oldstate, size)
         if size == 0:
             self._map.copymap.pop(f, None)
 
     def merge(self, f):
         '''Mark a file merged.'''
         if self._pl[1] == nullid:
             return self.normallookup(f)
         return self.otherparent(f)
 
     def drop(self, f):
         '''Drop a file from the dirstate'''
         oldstate = self[f]
         if self._map.dropfile(f, oldstate):
             self._dirty = True
             self._updatedfiles.add(f)
             self._map.copymap.pop(f, None)
 
     def _discoverpath(self, path, normed, ignoremissing, exists, storemap):
         if exists is None:
             exists = os.path.lexists(os.path.join(self._root, path))
         if not exists:
             # Maybe a path component exists
             if not ignoremissing and '/' in path:
                 d, f = path.rsplit('/', 1)
                 d = self._normalize(d, False, ignoremissing, None)
                 folded = d + "/" + f
             else:
                 # No path components, preserve original case
                 folded = path
         else:
             # recursively normalize leading directory components
             # against dirstate
             if '/' in normed:
                 d, f = normed.rsplit('/', 1)
                 d = self._normalize(d, False, ignoremissing, True)
                 r = self._root + "/" + d
                 folded = d + "/" + util.fspath(f, r)
             else:
                 folded = util.fspath(normed, self._root)
             storemap[normed] = folded
 
         return folded
 
     def _normalizefile(self, path, isknown, ignoremissing=False, exists=None):
         normed = util.normcase(path)
         folded = self._map.filefoldmap.get(normed, None)
         if folded is None:
             if isknown:
                 folded = path
             else:
                 folded = self._discoverpath(path, normed, ignoremissing, exists,
                                             self._map.filefoldmap)
         return folded
 
     def _normalize(self, path, isknown, ignoremissing=False, exists=None):
         normed = util.normcase(path)
         folded = self._map.filefoldmap.get(normed, None)
         if folded is None:
             folded = self._map.dirfoldmap.get(normed, None)
         if folded is None:
             if isknown:
                 folded = path
             else:
                 # store discovered result in dirfoldmap so that future
                 # normalizefile calls don't start matching directories
                 folded = self._discoverpath(path, normed, ignoremissing, exists,
                                             self._map.dirfoldmap)
         return folded
 
     def normalize(self, path, isknown=False, ignoremissing=False):
         '''
         normalize the case of a pathname when on a casefolding filesystem
 
         isknown specifies whether the filename came from walking the
         disk, to avoid extra filesystem access.
 
         If ignoremissing is True, missing path are returned
         unchanged. Otherwise, we try harder to normalize possibly
         existing path components.
 
         The normalized case is determined based on the following precedence:
 
         - version of name already stored in the dirstate
         - version of name stored on disk
         - version provided via command arguments
         '''
 
         if self._checkcase:
             return self._normalize(path, isknown, ignoremissing)
         return path
 
     def clear(self):
         self._map.clear()
         self._lastnormaltime = 0
         self._updatedfiles.clear()
         self._dirty = True
 
     def rebuild(self, parent, allfiles, changedfiles=None):
         if changedfiles is None:
             # Rebuild entire dirstate
             changedfiles = allfiles
             lastnormaltime = self._lastnormaltime
             self.clear()
             self._lastnormaltime = lastnormaltime
 
         if self._origpl is None:
             self._origpl = self._pl
         self._map.setparents(parent, nullid)
         for f in changedfiles:
             if f in allfiles:
                 self.normallookup(f)
             else:
                 self.drop(f)
 
         self._dirty = True
 
     def identity(self):
         '''Return identity of dirstate itself to detect changing in storage
 
         If identity of previous dirstate is equal to this, writing
         changes based on the former dirstate out can keep consistency.
         '''
         return self._map.identity
 
     def write(self, tr):
         if not self._dirty:
             return
 
         filename = self._filename
         if tr:
             # 'dirstate.write()' is not only for writing in-memory
             # changes out, but also for dropping ambiguous timestamp.
             # delayed writing re-raise "ambiguous timestamp issue".
             # See also the wiki page below for detail:
             # https://www.mercurial-scm.org/wiki/DirstateTransactionPlan
 
             # emulate dropping timestamp in 'parsers.pack_dirstate'
             now = _getfsnow(self._opener)
             self._map.clearambiguoustimes(self._updatedfiles, now)
 
             # emulate that all 'dirstate.normal' results are written out
             self._lastnormaltime = 0
             self._updatedfiles.clear()
 
             # delay writing in-memory changes out
             tr.addfilegenerator('dirstate', (self._filename,),
                                 self._writedirstate, location='plain')
             return
 
         st = self._opener(filename, "w", atomictemp=True, checkambig=True)
         self._writedirstate(st)
 
     def addparentchangecallback(self, category, callback):
         """add a callback to be called when the wd parents are changed
 
         Callback will be called with the following arguments:
             dirstate, (oldp1, oldp2), (newp1, newp2)
 
         Category is a unique identifier to allow overwriting an old callback
         with a newer callback.
         """
         self._plchangecallbacks[category] = callback
 
     def _writedirstate(self, st):
         # notify callbacks about parents change
         if self._origpl is not None and self._origpl != self._pl:
             for c, callback in sorted(self._plchangecallbacks.iteritems()):
                 callback(self, self._origpl, self._pl)
             self._origpl = None
         # use the modification time of the newly created temporary file as the
         # filesystem's notion of 'now'
         now = util.fstat(st)[stat.ST_MTIME] & _rangemask
 
         # enough 'delaywrite' prevents 'pack_dirstate' from dropping
         # timestamp of each entries in dirstate, because of 'now > mtime'
         delaywrite = self._ui.configint('debug', 'dirstate.delaywrite')
         if delaywrite > 0:
             # do we have any files to delay for?
             for f, e in self._map.iteritems():
                 if e[0] == 'n' and e[3] == now:
                     import time # to avoid useless import
                     # rather than sleep n seconds, sleep until the next
                     # multiple of n seconds
                     clock = time.time()
                     start = int(clock) - (int(clock) % delaywrite)
                     end = start + delaywrite
                     time.sleep(end - clock)
                     now = end # trust our estimate that the end is near now
                     break
 
         self._map.write(st, now)
         self._lastnormaltime = 0
         self._dirty = False
 
     def _dirignore(self, f):
         if f == '.':
             return False
         if self._ignore(f):
             return True
         for p in util.finddirs(f):
             if self._ignore(p):
                 return True
         return False
 
     def _ignorefiles(self):
         files = []
         if os.path.exists(self._join('.hgignore')):
             files.append(self._join('.hgignore'))
         for name, path in self._ui.configitems("ui"):
             if name == 'ignore' or name.startswith('ignore.'):
                 # we need to use os.path.join here rather than self._join
                 # because path is arbitrary and user-specified
                 files.append(os.path.join(self._rootdir, util.expandpath(path)))
         return files
 
     def _ignorefileandline(self, f):
         files = collections.deque(self._ignorefiles())
         visited = set()
         while files:
             i = files.popleft()
             patterns = matchmod.readpatternfile(i, self._ui.warn,
                                                 sourceinfo=True)
             for pattern, lineno, line in patterns:
                 kind, p = matchmod._patsplit(pattern, 'glob')
                 if kind == "subinclude":
                     if p not in visited:
                         files.append(p)
                     continue
                 m = matchmod.match(self._root, '', [], [pattern],
                                    warn=self._ui.warn)
                 if m(f):
                     return (i, lineno, line)
             visited.add(i)
         return (None, -1, "")
 
     def _walkexplicit(self, match, subrepos):
         '''Get stat data about the files explicitly specified by match.
 
         Return a triple (results, dirsfound, dirsnotfound).
         - results is a mapping from filename to stat result. It also contains
           listings mapping subrepos and .hg to None.
         - dirsfound is a list of files found to be directories.
         - dirsnotfound is a list of files that the dirstate thinks are
           directories and that were not found.'''
 
         def badtype(mode):
             kind = _('unknown')
             if stat.S_ISCHR(mode):
                 kind = _('character device')
             elif stat.S_ISBLK(mode):
                 kind = _('block device')
             elif stat.S_ISFIFO(mode):
                 kind = _('fifo')
             elif stat.S_ISSOCK(mode):
                 kind = _('socket')
             elif stat.S_ISDIR(mode):
                 kind = _('directory')
             return _('unsupported file type (type is %s)') % kind
 
         matchedir = match.explicitdir
         badfn = match.bad
         dmap = self._map
         lstat = os.lstat
         getkind = stat.S_IFMT
         dirkind = stat.S_IFDIR
         regkind = stat.S_IFREG
         lnkkind = stat.S_IFLNK
         join = self._join
         dirsfound = []
         foundadd = dirsfound.append
         dirsnotfound = []
         notfoundadd = dirsnotfound.append
 
         if not match.isexact() and self._checkcase:
             normalize = self._normalize
         else:
             normalize = None
 
         files = sorted(match.files())
         subrepos.sort()
         i, j = 0, 0
         while i < len(files) and j < len(subrepos):
             subpath = subrepos[j] + "/"
             if files[i] < subpath:
                 i += 1
                 continue
             while i < len(files) and files[i].startswith(subpath):
                 del files[i]
             j += 1
 
         if not files or '.' in files:
             files = ['.']
         results = dict.fromkeys(subrepos)
         results['.hg'] = None
 
         for ff in files:
             # constructing the foldmap is expensive, so don't do it for the
             # common case where files is ['.']
             if normalize and ff != '.':
                 nf = normalize(ff, False, True)
             else:
                 nf = ff
             if nf in results:
                 continue
 
             try:
                 st = lstat(join(nf))
                 kind = getkind(st.st_mode)
                 if kind == dirkind:
                     if nf in dmap:
                         # file replaced by dir on disk but still in dirstate
                         results[nf] = None
                     if matchedir:
                         matchedir(nf)
                     foundadd((nf, ff))
                 elif kind == regkind or kind == lnkkind:
                     results[nf] = st
                 else:
                     badfn(ff, badtype(kind))
                     if nf in dmap:
                         results[nf] = None
             except OSError as inst: # nf not found on disk - it is dirstate only
                 if nf in dmap: # does it exactly match a missing file?
                     results[nf] = None
                 else: # does it match a missing directory?
                     if self._map.hasdir(nf):
                         if matchedir:
                             matchedir(nf)
                         notfoundadd(nf)
                     else:
                         badfn(ff, encoding.strtolocal(inst.strerror))
 
         # match.files() may contain explicitly-specified paths that shouldn't
         # be taken; drop them from the list of files found. dirsfound/notfound
         # aren't filtered here because they will be tested later.
         if match.anypats():
             for f in list(results):
                 if f == '.hg' or f in subrepos:
                     # keep sentinel to disable further out-of-repo walks
                     continue
                 if not match(f):
                     del results[f]
 
         # Case insensitive filesystems cannot rely on lstat() failing to detect
         # a case-only rename.  Prune the stat object for any file that does not
         # match the case in the filesystem, if there are multiple files that
         # normalize to the same path.
         if match.isexact() and self._checkcase:
             normed = {}
 
             for f, st in results.iteritems():
                 if st is None:
                     continue
 
                 nc = util.normcase(f)
                 paths = normed.get(nc)
 
                 if paths is None:
                     paths = set()
                     normed[nc] = paths
 
                 paths.add(f)
 
             for norm, paths in normed.iteritems():
                 if len(paths) > 1:
                     for path in paths:
                         folded = self._discoverpath(path, norm, True, None,
                                                     self._map.dirfoldmap)
                         if path != folded:
                             results[path] = None
 
         return results, dirsfound, dirsnotfound
 
     def walk(self, match, subrepos, unknown, ignored, full=True):
         '''
         Walk recursively through the directory tree, finding all files
         matched by match.
 
         If full is False, maybe skip some known-clean files.
 
         Return a dict mapping filename to stat-like object (either
         mercurial.osutil.stat instance or return value of os.stat()).
 
         '''
         # full is a flag that extensions that hook into walk can use -- this
         # implementation doesn't use it at all. This satisfies the contract
         # because we only guarantee a "maybe".
 
         if ignored:
             ignore = util.never
             dirignore = util.never
         elif unknown:
             ignore = self._ignore
             dirignore = self._dirignore
         else:
             # if not unknown and not ignored, drop dir recursion and step 2
             ignore = util.always
             dirignore = util.always
 
         matchfn = match.matchfn
         matchalways = match.always()
         matchtdir = match.traversedir
         dmap = self._map
         listdir = util.listdir
         lstat = os.lstat
         dirkind = stat.S_IFDIR
         regkind = stat.S_IFREG
         lnkkind = stat.S_IFLNK
         join = self._join
 
         exact = skipstep3 = False
         if match.isexact(): # match.exact
             exact = True
             dirignore = util.always # skip step 2
         elif match.prefix(): # match.match, no patterns
             skipstep3 = True
 
         if not exact and self._checkcase:
             normalize = self._normalize
             normalizefile = self._normalizefile
             skipstep3 = False
         else:
             normalize = self._normalize
             normalizefile = None
 
         # step 1: find all explicit files
         results, work, dirsnotfound = self._walkexplicit(match, subrepos)
 
         skipstep3 = skipstep3 and not (work or dirsnotfound)
         work = [d for d in work if not dirignore(d[0])]
 
         # step 2: visit subdirectories
         def traverse(work, alreadynormed):
             wadd = work.append
             while work:
                 nd = work.pop()
                 visitentries = match.visitchildrenset(nd)
                 if not visitentries:
                     continue
                 if visitentries == 'this' or visitentries == 'all':
                     visitentries = None
                 skip = None
                 if nd == '.':
                     nd = ''
                 else:
                     skip = '.hg'
                 try:
                     entries = listdir(join(nd), stat=True, skip=skip)
                 except OSError as inst:
                     if inst.errno in (errno.EACCES, errno.ENOENT):
                         match.bad(self.pathto(nd),
                                   encoding.strtolocal(inst.strerror))
                         continue
                     raise
                 for f, kind, st in entries:
                     # Some matchers may return files in the visitentries set,
                     # instead of 'this', if the matcher explicitly mentions them
                     # and is not an exactmatcher. This is acceptable; we do not
                     # make any hard assumptions about file-or-directory below
                     # based on the presence of `f` in visitentries. If
                     # visitchildrenset returned a set, we can always skip the
                     # entries *not* in the set it provided regardless of whether
                     # they're actually a file or a directory.
                     if visitentries and f not in visitentries:
                         continue
                     if normalizefile:
                         # even though f might be a directory, we're only
                         # interested in comparing it to files currently in the
                         # dmap -- therefore normalizefile is enough
                         nf = normalizefile(nd and (nd + "/" + f) or f, True,
                                            True)
                     else:
                         nf = nd and (nd + "/" + f) or f
                     if nf not in results:
                         if kind == dirkind:
                             if not ignore(nf):
                                 if matchtdir:
                                     matchtdir(nf)
                                 wadd(nf)
                             if nf in dmap and (matchalways or matchfn(nf)):
                                 results[nf] = None
                         elif kind == regkind or kind == lnkkind:
                             if nf in dmap:
                                 if matchalways or matchfn(nf):
                                     results[nf] = st
                             elif ((matchalways or matchfn(nf))
                                   and not ignore(nf)):
                                 # unknown file -- normalize if necessary
                                 if not alreadynormed:
                                     nf = normalize(nf, False, True)
                                 results[nf] = st
                         elif nf in dmap and (matchalways or matchfn(nf)):
                             results[nf] = None
 
         for nd, d in work:
             # alreadynormed means that processwork doesn't have to do any
             # expensive directory normalization
             alreadynormed = not normalize or nd == d
             traverse([d], alreadynormed)
 
         for s in subrepos:
             del results[s]
         del results['.hg']
 
         # step 3: visit remaining files from dmap
         if not skipstep3 and not exact:
             # If a dmap file is not in results yet, it was either
             # a) not matching matchfn b) ignored, c) missing, or d) under a
             # symlink directory.
             if not results and matchalways:
                 visit = [f for f in dmap]
             else:
                 visit = [f for f in dmap if f not in results and matchfn(f)]
             visit.sort()
 
             if unknown:
                 # unknown == True means we walked all dirs under the roots
                 # that wasn't ignored, and everything that matched was stat'ed
                 # and is already in results.
                 # The rest must thus be ignored or under a symlink.
                 audit_path = pathutil.pathauditor(self._root, cached=True)
 
                 for nf in iter(visit):
                     # If a stat for the same file was already added with a
                     # different case, don't add one for this, since that would
                     # make it appear as if the file exists under both names
                     # on disk.
                     if (normalizefile and
                         normalizefile(nf, True, True) in results):
                         results[nf] = None
                     # Report ignored items in the dmap as long as they are not
                     # under a symlink directory.
                     elif audit_path.check(nf):
                         try:
                             results[nf] = lstat(join(nf))
                             # file was just ignored, no links, and exists
                         except OSError:
                             # file doesn't exist
                             results[nf] = None
                     else:
                         # It's either missing or under a symlink directory
                         # which we in this case report as missing
                         results[nf] = None
             else:
                 # We may not have walked the full directory tree above,
                 # so stat and check everything we missed.
                 iv = iter(visit)
                 for st in util.statfiles([join(i) for i in visit]):
                     results[next(iv)] = st
         return results
 
     def status(self, match, subrepos, ignored, clean, unknown):
         '''Determine the status of the working copy relative to the
         dirstate and return a pair of (unsure, status), where status is of type
         scmutil.status and:
 
           unsure:
             files that might have been modified since the dirstate was
             written, but need to be read to be sure (size is the same
             but mtime differs)
           status.modified:
             files that have definitely been modified since the dirstate
             was written (different size or mode)
           status.clean:
             files that have definitely not been modified since the
             dirstate was written
         '''
         listignored, listclean, listunknown = ignored, clean, unknown
         lookup, modified, added, unknown, ignored = [], [], [], [], []
         removed, deleted, clean = [], [], []
 
         dmap = self._map
         dmap.preload()
         dcontains = dmap.__contains__
         dget = dmap.__getitem__
         ladd = lookup.append            # aka "unsure"
         madd = modified.append
         aadd = added.append
         uadd = unknown.append
         iadd = ignored.append
         radd = removed.append
         dadd = deleted.append
         cadd = clean.append
         mexact = match.exact
         dirignore = self._dirignore
         checkexec = self._checkexec
         copymap = self._map.copymap
         lastnormaltime = self._lastnormaltime
 
         # We need to do full walks when either
         # - we're listing all clean files, or
         # - match.traversedir does something, because match.traversedir should
         #   be called for every dir in the working dir
         full = listclean or match.traversedir is not None
         for fn, st in self.walk(match, subrepos, listunknown, listignored,
                                 full=full).iteritems():
             if not dcontains(fn):
                 if (listignored or mexact(fn)) and dirignore(fn):
                     if listignored:
                         iadd(fn)
                 else:
                     uadd(fn)
                 continue
 
             # This is equivalent to 'state, mode, size, time = dmap[fn]' but not
             # written like that for performance reasons. dmap[fn] is not a
             # Python tuple in compiled builds. The CPython UNPACK_SEQUENCE
             # opcode has fast paths when the value to be unpacked is a tuple or
             # a list, but falls back to creating a full-fledged iterator in
             # general. That is much slower than simply accessing and storing the
             # tuple members one by one.
             t = dget(fn)
             state = t[0]
             mode = t[1]
             size = t[2]
             time = t[3]
 
             if not st and state in "nma":
                 dadd(fn)
             elif state == 'n':
                 if (size >= 0 and
                     ((size != st.st_size and size != st.st_size & _rangemask)
                      or ((mode ^ st.st_mode) & 0o100 and checkexec))
                     or size == -2 # other parent
                     or fn in copymap):
                     madd(fn)
                 elif (time != st[stat.ST_MTIME]
                       and time != st[stat.ST_MTIME] & _rangemask):
                     ladd(fn)
                 elif st[stat.ST_MTIME] == lastnormaltime:
                     # fn may have just been marked as normal and it may have
                     # changed in the same second without changing its size.
                     # This can happen if we quickly do multiple commits.
                     # Force lookup, so we don't miss such a racy file change.
                     ladd(fn)
                 elif listclean:
                     cadd(fn)
             elif state == 'm':
                 madd(fn)
             elif state == 'a':
                 aadd(fn)
             elif state == 'r':
                 radd(fn)
 
         return (lookup, scmutil.status(modified, added, removed, deleted,
                                        unknown, ignored, clean))
 
     def matches(self, match):
         '''
         return files in the dirstate (in whatever state) filtered by match
         '''
         dmap = self._map
         if match.always():
             return dmap.keys()
         files = match.files()
         if match.isexact():
             # fast path -- filter the other way around, since typically files is
             # much smaller than dmap
             return [f for f in files if f in dmap]
         if match.prefix() and all(fn in dmap for fn in files):
             # fast path -- all the values are known to be files, so just return
             # that
             return list(files)
         return [f for f in dmap if match(f)]
 
     def _actualfilename(self, tr):
         if tr:
             return self._pendingfilename
         else:
             return self._filename
 
     def savebackup(self, tr, backupname):
         '''Save current dirstate into backup file'''
         filename = self._actualfilename(tr)
         assert backupname != filename
 
         # use '_writedirstate' instead of 'write' to write changes certainly,
         # because the latter omits writing out if transaction is running.
         # output file will be used to create backup of dirstate at this point.
         if self._dirty or not self._opener.exists(filename):
             self._writedirstate(self._opener(filename, "w", atomictemp=True,
                                              checkambig=True))
 
         if tr:
             # ensure that subsequent tr.writepending returns True for
             # changes written out above, even if dirstate is never
             # changed after this
             tr.addfilegenerator('dirstate', (self._filename,),
                                 self._writedirstate, location='plain')
 
             # ensure that pending file written above is unlinked at
             # failure, even if tr.writepending isn't invoked until the
             # end of this transaction
             tr.registertmp(filename, location='plain')
 
         self._opener.tryunlink(backupname)
         # hardlink backup is okay because _writedirstate is always called
         # with an "atomictemp=True" file.
         util.copyfile(self._opener.join(filename),
                       self._opener.join(backupname), hardlink=True)
 
     def restorebackup(self, tr, backupname):
         '''Restore dirstate by backup file'''
         # this "invalidate()" prevents "wlock.release()" from writing
         # changes of dirstate out after restoring from backup file
         self.invalidate()
         filename = self._actualfilename(tr)
         o = self._opener
         if util.samefile(o.join(backupname), o.join(filename)):
             o.unlink(backupname)
         else:
             o.rename(backupname, filename, checkambig=True)
 
     def clearbackup(self, tr, backupname):
         '''Clear backup file'''
         self._opener.unlink(backupname)
 
 class dirstatemap(object):
     """Map encapsulating the dirstate's contents.
 
     The dirstate contains the following state:
 
     - `identity` is the identity of the dirstate file, which can be used to
       detect when changes have occurred to the dirstate file.
 
     - `parents` is a pair containing the parents of the working copy. The
       parents are updated by calling `setparents`.
 
     - the state map maps filenames to tuples of (state, mode, size, mtime),
       where state is a single character representing 'normal', 'added',
       'removed', or 'merged'. It is read by treating the dirstate as a
       dict.  File state is updated by calling the `addfile`, `removefile` and
       `dropfile` methods.
 
     - `copymap` maps destination filenames to their source filename.
 
     The dirstate also provides the following views onto the state:
 
     - `nonnormalset` is a set of the filenames that have state other
       than 'normal', or are normal but have an mtime of -1 ('normallookup').
 
     - `otherparentset` is a set of the filenames that are marked as coming
       from the second parent when the dirstate is currently being merged.
 
     - `filefoldmap` is a dict mapping normalized filenames to the denormalized
       form that they appear as in the dirstate.
 
     - `dirfoldmap` is a dict mapping normalized directory names to the
       denormalized form that they appear as in the dirstate.
     """
 
     def __init__(self, ui, opener, root):
         self._ui = ui
         self._opener = opener
         self._root = root
         self._filename = 'dirstate'
 
         self._parents = None
         self._dirtyparents = False
 
         # for consistent view between _pl() and _read() invocations
         self._pendingmode = None
 
     @propertycache
     def _map(self):
         self._map = {}
         self.read()
         return self._map
 
     @propertycache
     def copymap(self):
         self.copymap = {}
         self._map
         return self.copymap
 
     def clear(self):
         self._map.clear()
         self.copymap.clear()
         self.setparents(nullid, nullid)
         util.clearcachedproperty(self, "_dirs")
         util.clearcachedproperty(self, "_alldirs")
         util.clearcachedproperty(self, "filefoldmap")
         util.clearcachedproperty(self, "dirfoldmap")
         util.clearcachedproperty(self, "nonnormalset")
         util.clearcachedproperty(self, "otherparentset")
 
     def items(self):
         return self._map.iteritems()
 
     # forward for python2,3 compat
     iteritems = items
 
     def __len__(self):
         return len(self._map)
 
     def __iter__(self):
         return iter(self._map)
 
     def get(self, key, default=None):
         return self._map.get(key, default)
 
     def __contains__(self, key):
         return key in self._map
 
     def __getitem__(self, key):
         return self._map[key]
 
     def keys(self):
         return self._map.keys()
 
     def preload(self):
         """Loads the underlying data, if it's not already loaded"""
         self._map
 
     def addfile(self, f, oldstate, state, mode, size, mtime):
         """Add a tracked file to the dirstate."""
         if oldstate in "?r" and r"_dirs" in self.__dict__:
             self._dirs.addpath(f)
         if oldstate == "?" and r"_alldirs" in self.__dict__:
             self._alldirs.addpath(f)
         self._map[f] = dirstatetuple(state, mode, size, mtime)
         if state != 'n' or mtime == -1:
             self.nonnormalset.add(f)
         if size == -2:
             self.otherparentset.add(f)
 
     def removefile(self, f, oldstate, size):
         """
         Mark a file as removed in the dirstate.
 
         The `size` parameter is used to store sentinel values that indicate
         the file's previous state.  In the future, we should refactor this
         to be more explicit about what that state is.
         """
         if oldstate not in "?r" and r"_dirs" in self.__dict__:
             self._dirs.delpath(f)
         if oldstate == "?" and r"_alldirs" in self.__dict__:
             self._alldirs.addpath(f)
         if r"filefoldmap" in self.__dict__:
             normed = util.normcase(f)
             self.filefoldmap.pop(normed, None)
         self._map[f] = dirstatetuple('r', 0, size, 0)
         self.nonnormalset.add(f)
 
     def dropfile(self, f, oldstate):
         """
         Remove a file from the dirstate.  Returns True if the file was
         previously recorded.
         """
         exists = self._map.pop(f, None) is not None
         if exists:
             if oldstate != "r" and r"_dirs" in self.__dict__:
                 self._dirs.delpath(f)
             if r"_alldirs" in self.__dict__:
                 self._alldirs.delpath(f)
         if r"filefoldmap" in self.__dict__:
             normed = util.normcase(f)
             self.filefoldmap.pop(normed, None)
         self.nonnormalset.discard(f)
         return exists
 
     def clearambiguoustimes(self, files, now):
         for f in files:
             e = self.get(f)
             if e is not None and e[0] == 'n' and e[3] == now:
                 self._map[f] = dirstatetuple(e[0], e[1], e[2], -1)
                 self.nonnormalset.add(f)
 
     def nonnormalentries(self):
         '''Compute the nonnormal dirstate entries from the dmap'''
         try:
             return parsers.nonnormalotherparententries(self._map)
         except AttributeError:
             nonnorm = set()
             otherparent = set()
             for fname, e in self._map.iteritems():
                 if e[0] != 'n' or e[3] == -1:
                     nonnorm.add(fname)
                 if e[0] == 'n' and e[2] == -2:
                     otherparent.add(fname)
             return nonnorm, otherparent
 
     @propertycache
     def filefoldmap(self):
         """Returns a dictionary mapping normalized case paths to their
         non-normalized versions.
         """
         try:
             makefilefoldmap = parsers.make_file_foldmap
         except AttributeError:
             pass
         else:
             return makefilefoldmap(self._map, util.normcasespec,
                                    util.normcasefallback)
 
         f = {}
         normcase = util.normcase
         for name, s in self._map.iteritems():
             if s[0] != 'r':
                 f[normcase(name)] = name
         f['.'] = '.' # prevents useless util.fspath() invocation
         return f
 
     def hastrackeddir(self, d):
         """
         Returns True if the dirstate contains a tracked (not removed) file
         in this directory.
         """
         return d in self._dirs
 
     def hasdir(self, d):
         """
         Returns True if the dirstate contains a file (tracked or removed)
         in this directory.
         """
         return d in self._alldirs
 
     @propertycache
     def _dirs(self):
         return util.dirs(self._map, 'r')
 
     @propertycache
     def _alldirs(self):
         return util.dirs(self._map)
 
     def _opendirstatefile(self):
         fp, mode = txnutil.trypending(self._root, self._opener, self._filename)
         if self._pendingmode is not None and self._pendingmode != mode:
             fp.close()
             raise error.Abort(_('working directory state may be '
                                 'changed parallelly'))
         self._pendingmode = mode
         return fp
 
     def parents(self):
         if not self._parents:
             try:
                 fp = self._opendirstatefile()
                 st = fp.read(40)
                 fp.close()
             except IOError as err:
                 if err.errno != errno.ENOENT:
                     raise
                 # File doesn't exist, so the current state is empty
                 st = ''
 
             l = len(st)
             if l == 40:
                 self._parents = (st[:20], st[20:40])
             elif l == 0:
                 self._parents = (nullid, nullid)
             else:
                 raise error.Abort(_('working directory state appears '
                                     'damaged!'))
 
         return self._parents
 
     def setparents(self, p1, p2):
         self._parents = (p1, p2)
         self._dirtyparents = True
 
     def read(self):
         # ignore HG_PENDING because identity is used only for writing
         self.identity = util.filestat.frompath(
             self._opener.join(self._filename))
 
         try:
             fp = self._opendirstatefile()
             try:
                 st = fp.read()
             finally:
                 fp.close()
         except IOError as err:
             if err.errno != errno.ENOENT:
                 raise
             return
         if not st:
             return
 
         if util.safehasattr(parsers, 'dict_new_presized'):
             # Make an estimate of the number of files in the dirstate based on
             # its size. From a linear regression on a set of real-world repos,
             # all over 10,000 files, the size of a dirstate entry is 85
             # bytes. The cost of resizing is significantly higher than the cost
             # of filling in a larger presized dict, so subtract 20% from the
             # size.
             #
             # This heuristic is imperfect in many ways, so in a future dirstate
             # format update it makes sense to just record the number of entries
             # on write.
             self._map = parsers.dict_new_presized(len(st) // 71)
 
         # Python's garbage collector triggers a GC each time a certain number
         # of container objects (the number being defined by
         # gc.get_threshold()) are allocated. parse_dirstate creates a tuple
         # for each file in the dirstate. The C version then immediately marks
         # them as not to be tracked by the collector. However, this has no
         # effect on when GCs are triggered, only on what objects the GC looks
         # into. This means that O(number of files) GCs are unavoidable.
         # Depending on when in the process's lifetime the dirstate is parsed,
         # this can get very expensive. As a workaround, disable GC while
         # parsing the dirstate.
         #
         # (we cannot decorate the function directly since it is in a C module)
         parse_dirstate = util.nogc(parsers.parse_dirstate)
         p = parse_dirstate(self._map, self.copymap, st)
         if not self._dirtyparents:
             self.setparents(*p)
 
         # Avoid excess attribute lookups by fast pathing certain checks
         self.__contains__ = self._map.__contains__
         self.__getitem__ = self._map.__getitem__
         self.get = self._map.get
 
     def write(self, st, now):
         st.write(parsers.pack_dirstate(self._map, self.copymap,
                                        self.parents(), now))
         st.close()
         self._dirtyparents = False
         self.nonnormalset, self.otherparentset = self.nonnormalentries()
 
     @propertycache
     def nonnormalset(self):
         nonnorm, otherparents = self.nonnormalentries()
         self.otherparentset = otherparents
         return nonnorm
 
     @propertycache
     def otherparentset(self):
         nonnorm, otherparents = self.nonnormalentries()
         self.nonnormalset = nonnorm
         return otherparents
 
     @propertycache
     def identity(self):
         self._map
         return self.identity
 
     @propertycache
     def dirfoldmap(self):
         f = {}
         normcase = util.normcase
         for name in self._dirs:
             f[normcase(name)] = name
         return f

mercurial/fileset.py

@@ -1,560 +1,559 b''
 # fileset.py - file set queries for mercurial
 #
 # Copyright 2010 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 re
 
 from .i18n import _
 from . import (
     error,
     filesetlang,
     match as matchmod,
     merge,
     pycompat,
     registrar,
     scmutil,
     util,
 )
 from .utils import (
     stringutil,
 )
 
 # common weight constants
 _WEIGHT_CHECK_FILENAME = filesetlang.WEIGHT_CHECK_FILENAME
 _WEIGHT_READ_CONTENTS = filesetlang.WEIGHT_READ_CONTENTS
 _WEIGHT_STATUS = filesetlang.WEIGHT_STATUS
 _WEIGHT_STATUS_THOROUGH = filesetlang.WEIGHT_STATUS_THOROUGH
 
 # helpers for processing parsed tree
 getsymbol = filesetlang.getsymbol
 getstring = filesetlang.getstring
 _getkindpat = filesetlang.getkindpat
 getpattern = filesetlang.getpattern
 getargs = filesetlang.getargs
 
 def getmatch(mctx, x):
     if not x:
         raise error.ParseError(_("missing argument"))
     return methods[x[0]](mctx, *x[1:])
 
 def getmatchwithstatus(mctx, x, hint):
     keys = set(getstring(hint, 'status hint must be a string').split())
     return getmatch(mctx.withstatus(keys), x)
 
 def stringmatch(mctx, x):
     return mctx.matcher([x])
 
 def kindpatmatch(mctx, x, y):
     return stringmatch(mctx, _getkindpat(x, y, matchmod.allpatternkinds,
                                          _("pattern must be a string")))
 
 def patternsmatch(mctx, *xs):
     allkinds = matchmod.allpatternkinds
     patterns = [getpattern(x, allkinds, _("pattern must be a string"))
                 for x in xs]
     return mctx.matcher(patterns)
 
 def andmatch(mctx, x, y):
     xm = getmatch(mctx, x)
     ym = getmatch(mctx.narrowed(xm), y)
     return matchmod.intersectmatchers(xm, ym)
 
 def ormatch(mctx, *xs):
     ms = [getmatch(mctx, x) for x in xs]
     return matchmod.unionmatcher(ms)
 
 def notmatch(mctx, x):
     m = getmatch(mctx, x)
     return mctx.predicate(lambda f: not m(f), predrepr=('<not %r>', m))
 
 def minusmatch(mctx, x, y):
     xm = getmatch(mctx, x)
     ym = getmatch(mctx.narrowed(xm), y)
     return matchmod.differencematcher(xm, ym)
 
 def listmatch(mctx, *xs):
     raise error.ParseError(_("can't use a list in this context"),
                            hint=_('see \'hg help "filesets.x or y"\''))
 
 def func(mctx, a, b):
     funcname = getsymbol(a)
     if funcname in symbols:
         return symbols[funcname](mctx, b)
 
     keep = lambda fn: getattr(fn, '__doc__', None) is not None
 
     syms = [s for (s, fn) in symbols.items() if keep(fn)]
     raise error.UnknownIdentifier(funcname, syms)
 
 # symbols are callable like:
 #  fun(mctx, x)
 # with:
 #  mctx - current matchctx instance
 #  x - argument in tree form
 symbols = filesetlang.symbols
 
 predicate = registrar.filesetpredicate(symbols)
 
 @predicate('modified()', callstatus=True, weight=_WEIGHT_STATUS)
 def modified(mctx, x):
     """File that is modified according to :hg:`status`.
     """
     # i18n: "modified" is a keyword
     getargs(x, 0, 0, _("modified takes no arguments"))
     s = set(mctx.status().modified)
     return mctx.predicate(s.__contains__, predrepr='modified')
 
 @predicate('added()', callstatus=True, weight=_WEIGHT_STATUS)
 def added(mctx, x):
     """File that is added according to :hg:`status`.
     """
     # i18n: "added" is a keyword
     getargs(x, 0, 0, _("added takes no arguments"))
     s = set(mctx.status().added)
     return mctx.predicate(s.__contains__, predrepr='added')
 
 @predicate('removed()', callstatus=True, weight=_WEIGHT_STATUS)
 def removed(mctx, x):
     """File that is removed according to :hg:`status`.
     """
     # i18n: "removed" is a keyword
     getargs(x, 0, 0, _("removed takes no arguments"))
     s = set(mctx.status().removed)
     return mctx.predicate(s.__contains__, predrepr='removed')
 
 @predicate('deleted()', callstatus=True, weight=_WEIGHT_STATUS)
 def deleted(mctx, x):
     """Alias for ``missing()``.
     """
     # i18n: "deleted" is a keyword
     getargs(x, 0, 0, _("deleted takes no arguments"))
     s = set(mctx.status().deleted)
     return mctx.predicate(s.__contains__, predrepr='deleted')
 
 @predicate('missing()', callstatus=True, weight=_WEIGHT_STATUS)
 def missing(mctx, x):
     """File that is missing according to :hg:`status`.
     """
     # i18n: "missing" is a keyword
     getargs(x, 0, 0, _("missing takes no arguments"))
     s = set(mctx.status().deleted)
     return mctx.predicate(s.__contains__, predrepr='deleted')
 
 @predicate('unknown()', callstatus=True, weight=_WEIGHT_STATUS_THOROUGH)
 def unknown(mctx, x):
     """File that is unknown according to :hg:`status`."""
     # i18n: "unknown" is a keyword
     getargs(x, 0, 0, _("unknown takes no arguments"))
     s = set(mctx.status().unknown)
     return mctx.predicate(s.__contains__, predrepr='unknown')
 
 @predicate('ignored()', callstatus=True, weight=_WEIGHT_STATUS_THOROUGH)
 def ignored(mctx, x):
     """File that is ignored according to :hg:`status`."""
     # i18n: "ignored" is a keyword
     getargs(x, 0, 0, _("ignored takes no arguments"))
     s = set(mctx.status().ignored)
     return mctx.predicate(s.__contains__, predrepr='ignored')
 
 @predicate('clean()', callstatus=True, weight=_WEIGHT_STATUS)
 def clean(mctx, x):
     """File that is clean according to :hg:`status`.
     """
     # i18n: "clean" is a keyword
     getargs(x, 0, 0, _("clean takes no arguments"))
     s = set(mctx.status().clean)
     return mctx.predicate(s.__contains__, predrepr='clean')
 
 @predicate('tracked()')
 def tracked(mctx, x):
     """File that is under Mercurial control."""
     # i18n: "tracked" is a keyword
     getargs(x, 0, 0, _("tracked takes no arguments"))
     return mctx.predicate(mctx.ctx.__contains__, predrepr='tracked')
 
 @predicate('binary()', weight=_WEIGHT_READ_CONTENTS)
 def binary(mctx, x):
     """File that appears to be binary (contains NUL bytes).
     """
     # i18n: "binary" is a keyword
     getargs(x, 0, 0, _("binary takes no arguments"))
     return mctx.fpredicate(lambda fctx: fctx.isbinary(),
                            predrepr='binary', cache=True)
 
 @predicate('exec()')
 def exec_(mctx, x):
     """File that is marked as executable.
     """
     # i18n: "exec" is a keyword
     getargs(x, 0, 0, _("exec takes no arguments"))
     ctx = mctx.ctx
     return mctx.predicate(lambda f: ctx.flags(f) == 'x', predrepr='exec')
 
 @predicate('symlink()')
 def symlink(mctx, x):
     """File that is marked as a symlink.
     """
     # i18n: "symlink" is a keyword
     getargs(x, 0, 0, _("symlink takes no arguments"))
     ctx = mctx.ctx
     return mctx.predicate(lambda f: ctx.flags(f) == 'l', predrepr='symlink')
 
 @predicate('resolved()', weight=_WEIGHT_STATUS)
 def resolved(mctx, x):
     """File that is marked resolved according to :hg:`resolve -l`.
     """
     # i18n: "resolved" is a keyword
     getargs(x, 0, 0, _("resolved takes no arguments"))
     if mctx.ctx.rev() is not None:
         return mctx.never()
     ms = merge.mergestate.read(mctx.ctx.repo())
     return mctx.predicate(lambda f: f in ms and ms[f] == 'r',
                           predrepr='resolved')
 
 @predicate('unresolved()', weight=_WEIGHT_STATUS)
 def unresolved(mctx, x):
     """File that is marked unresolved according to :hg:`resolve -l`.
     """
     # i18n: "unresolved" is a keyword
     getargs(x, 0, 0, _("unresolved takes no arguments"))
     if mctx.ctx.rev() is not None:
         return mctx.never()
     ms = merge.mergestate.read(mctx.ctx.repo())
     return mctx.predicate(lambda f: f in ms and ms[f] == 'u',
                           predrepr='unresolved')
 
 @predicate('hgignore()', weight=_WEIGHT_STATUS)
 def hgignore(mctx, x):
     """File that matches the active .hgignore pattern.
     """
     # i18n: "hgignore" is a keyword
     getargs(x, 0, 0, _("hgignore takes no arguments"))
     return mctx.ctx.repo().dirstate._ignore
 
 @predicate('portable()', weight=_WEIGHT_CHECK_FILENAME)
 def portable(mctx, x):
     """File that has a portable name. (This doesn't include filenames with case
     collisions.)
     """
     # i18n: "portable" is a keyword
     getargs(x, 0, 0, _("portable takes no arguments"))
     return mctx.predicate(lambda f: util.checkwinfilename(f) is None,
                           predrepr='portable')
 
 @predicate('grep(regex)', weight=_WEIGHT_READ_CONTENTS)
 def grep(mctx, x):
     """File contains the given regular expression.
     """
     try:
         # i18n: "grep" is a keyword
         r = re.compile(getstring(x, _("grep requires a pattern")))
     except re.error as e:
         raise error.ParseError(_('invalid match pattern: %s') %
                                stringutil.forcebytestr(e))
     return mctx.fpredicate(lambda fctx: r.search(fctx.data()),
                            predrepr=('grep(%r)', r.pattern), cache=True)
 
 def _sizetomax(s):
     try:
         s = s.strip().lower()
         for k, v in util._sizeunits:
             if s.endswith(k):
                 # max(4k) = 5k - 1, max(4.5k) = 4.6k - 1
                 n = s[:-len(k)]
                 inc = 1.0
                 if "." in n:
                     inc /= 10 ** len(n.split(".")[1])
                 return int((float(n) + inc) * v) - 1
         # no extension, this is a precise value
         return int(s)
     except ValueError:
         raise error.ParseError(_("couldn't parse size: %s") % s)
 
 def sizematcher(expr):
     """Return a function(size) -> bool from the ``size()`` expression"""
     expr = expr.strip()
     if '-' in expr: # do we have a range?
         a, b = expr.split('-', 1)
         a = util.sizetoint(a)
         b = util.sizetoint(b)
         return lambda x: x >= a and x <= b
     elif expr.startswith("<="):
         a = util.sizetoint(expr[2:])
         return lambda x: x <= a
     elif expr.startswith("<"):
         a = util.sizetoint(expr[1:])
         return lambda x: x < a
     elif expr.startswith(">="):
         a = util.sizetoint(expr[2:])
         return lambda x: x >= a
     elif expr.startswith(">"):
         a = util.sizetoint(expr[1:])
         return lambda x: x > a
     else:
         a = util.sizetoint(expr)
         b = _sizetomax(expr)
         return lambda x: x >= a and x <= b
 
 @predicate('size(expression)', weight=_WEIGHT_STATUS)
 def size(mctx, x):
     """File size matches the given expression. Examples:
 
     - size('1k') - files from 1024 to 2047 bytes
     - size('< 20k') - files less than 20480 bytes
     - size('>= .5MB') - files at least 524288 bytes
     - size('4k - 1MB') - files from 4096 bytes to 1048576 bytes
     """
     # i18n: "size" is a keyword
     expr = getstring(x, _("size requires an expression"))
     m = sizematcher(expr)
     return mctx.fpredicate(lambda fctx: m(fctx.size()),
                            predrepr=('size(%r)', expr), cache=True)
 
 @predicate('encoding(name)', weight=_WEIGHT_READ_CONTENTS)
 def encoding(mctx, x):
     """File can be successfully decoded with the given character
     encoding. May not be useful for encodings other than ASCII and
     UTF-8.
     """
 
     # i18n: "encoding" is a keyword
     enc = getstring(x, _("encoding requires an encoding name"))
 
     def encp(fctx):
         d = fctx.data()
         try:
             d.decode(pycompat.sysstr(enc))
             return True
         except LookupError:
             raise error.Abort(_("unknown encoding '%s'") % enc)
         except UnicodeDecodeError:
             return False
 
     return mctx.fpredicate(encp, predrepr=('encoding(%r)', enc), cache=True)
 
 @predicate('eol(style)', weight=_WEIGHT_READ_CONTENTS)
 def eol(mctx, x):
     """File contains newlines of the given style (dos, unix, mac). Binary
     files are excluded, files with mixed line endings match multiple
     styles.
     """
 
     # i18n: "eol" is a keyword
     enc = getstring(x, _("eol requires a style name"))
 
     def eolp(fctx):
         if fctx.isbinary():
             return False
         d = fctx.data()
         if (enc == 'dos' or enc == 'win') and '\r\n' in d:
             return True
         elif enc == 'unix' and re.search('(?<!\r)\n', d):
             return True
         elif enc == 'mac' and re.search('\r(?!\n)', d):
             return True
         return False
     return mctx.fpredicate(eolp, predrepr=('eol(%r)', enc), cache=True)
 
 @predicate('copied()')
 def copied(mctx, x):
     """File that is recorded as being copied.
     """
     # i18n: "copied" is a keyword
     getargs(x, 0, 0, _("copied takes no arguments"))
     def copiedp(fctx):
         p = fctx.parents()
         return p and p[0].path() != fctx.path()
     return mctx.fpredicate(copiedp, predrepr='copied', cache=True)
 
 @predicate('revs(revs, pattern)', weight=_WEIGHT_STATUS)
 def revs(mctx, x):
     """Evaluate set in the specified revisions. If the revset match multiple
     revs, this will return file matching pattern in any of the revision.
     """
     # i18n: "revs" is a keyword
     r, x = getargs(x, 2, 2, _("revs takes two arguments"))
     # i18n: "revs" is a keyword
     revspec = getstring(r, _("first argument to revs must be a revision"))
     repo = mctx.ctx.repo()
     revs = scmutil.revrange(repo, [revspec])
 
     matchers = []
     for r in revs:
         ctx = repo[r]
         mc = mctx.switch(ctx.p1(), ctx)
         matchers.append(getmatch(mc, x))
     if not matchers:
         return mctx.never()
     if len(matchers) == 1:
         return matchers[0]
     return matchmod.unionmatcher(matchers)
 
 @predicate('status(base, rev, pattern)', weight=_WEIGHT_STATUS)
 def status(mctx, x):
     """Evaluate predicate using status change between ``base`` and
     ``rev``. Examples:
 
     - ``status(3, 7, added())`` - matches files added from "3" to "7"
     """
     repo = mctx.ctx.repo()
     # i18n: "status" is a keyword
     b, r, x = getargs(x, 3, 3, _("status takes three arguments"))
     # i18n: "status" is a keyword
     baseerr = _("first argument to status must be a revision")
     baserevspec = getstring(b, baseerr)
     if not baserevspec:
         raise error.ParseError(baseerr)
     reverr = _("second argument to status must be a revision")
     revspec = getstring(r, reverr)
     if not revspec:
         raise error.ParseError(reverr)
     basectx, ctx = scmutil.revpair(repo, [baserevspec, revspec])
     mc = mctx.switch(basectx, ctx)
     return getmatch(mc, x)
 
 @predicate('subrepo([pattern])')
 def subrepo(mctx, x):
     """Subrepositories whose paths match the given pattern.
     """
     # i18n: "subrepo" is a keyword
     getargs(x, 0, 1, _("subrepo takes at most one argument"))
     ctx = mctx.ctx
     sstate = ctx.substate
     if x:
         pat = getpattern(x, matchmod.allpatternkinds,
                          # i18n: "subrepo" is a keyword
                          _("subrepo requires a pattern or no arguments"))
         fast = not matchmod.patkind(pat)
         if fast:
             def m(s):
                 return (s == pat)
         else:
             m = matchmod.match(ctx.repo().root, '', [pat], ctx=ctx)
         return mctx.predicate(lambda f: f in sstate and m(f),
                               predrepr=('subrepo(%r)', pat))
     else:
         return mctx.predicate(sstate.__contains__, predrepr='subrepo')
 
 methods = {
     'withstatus': getmatchwithstatus,
     'string': stringmatch,
     'symbol': stringmatch,
     'kindpat': kindpatmatch,
     'patterns': patternsmatch,
     'and': andmatch,
     'or': ormatch,
     'minus': minusmatch,
     'list': listmatch,
     'not': notmatch,
     'func': func,
 }
 
 class matchctx(object):
     def __init__(self, basectx, ctx, badfn=None):
         self._basectx = basectx
         self.ctx = ctx
         self._badfn = badfn
         self._match = None
         self._status = None
 
     def narrowed(self, match):
         """Create matchctx for a sub-tree narrowed by the given matcher"""
         mctx = matchctx(self._basectx, self.ctx, self._badfn)
         mctx._match = match
         # leave wider status which we don't have to care
         mctx._status = self._status
         return mctx
 
     def switch(self, basectx, ctx):
         mctx = matchctx(basectx, ctx, self._badfn)
         mctx._match = self._match
         return mctx
 
     def withstatus(self, keys):
         """Create matchctx which has precomputed status specified by the keys"""
         mctx = matchctx(self._basectx, self.ctx, self._badfn)
         mctx._match = self._match
         mctx._buildstatus(keys)
         return mctx
 
     def _buildstatus(self, keys):
         self._status = self._basectx.status(self.ctx, self._match,
                                             listignored='ignored' in keys,
                                             listclean='clean' in keys,
                                             listunknown='unknown' in keys)
 
     def status(self):
         return self._status
 
     def matcher(self, patterns):
         return self.ctx.match(patterns, badfn=self._badfn)
 
     def predicate(self, predfn, predrepr=None, cache=False):
         """Create a matcher to select files by predfn(filename)"""
         if cache:
             predfn = util.cachefunc(predfn)
         return matchmod.predicatematcher(predfn, predrepr=predrepr,
                                          badfn=self._badfn)
 
     def fpredicate(self, predfn, predrepr=None, cache=False):
         """Create a matcher to select files by predfn(fctx) at the current
         revision
 
         Missing files are ignored.
         """
         ctx = self.ctx
         if ctx.rev() is None:
             def fctxpredfn(f):
                 try:
                     fctx = ctx[f]
                 except error.LookupError:
                     return False
                 try:
                     fctx.audit()
                 except error.Abort:
                     return False
                 try:
                     return predfn(fctx)
                 except (IOError, OSError) as e:
                     # open()-ing a directory fails with EACCES on Windows
                     if e.errno in (errno.ENOENT, errno.EACCES, errno.ENOTDIR,
                                    errno.EISDIR):
                         return False
                     raise
         else:
             def fctxpredfn(f):
                 try:
                     fctx = ctx[f]
                 except error.LookupError:
                     return False
                 return predfn(fctx)
         return self.predicate(fctxpredfn, predrepr=predrepr, cache=cache)
 
     def never(self):
         """Create a matcher to select nothing"""
-        repo = self.ctx.repo()
-        return matchmod.never(repo.root, repo.getcwd(), badfn=self._badfn)
+        return matchmod.never(badfn=self._badfn)
 
 def match(ctx, expr, badfn=None):
     """Create a matcher for a single fileset expression"""
     tree = filesetlang.parse(expr)
     tree = filesetlang.analyze(tree)
     tree = filesetlang.optimize(tree)
     mctx = matchctx(ctx.p1(), ctx, badfn=badfn)
     return getmatch(mctx, tree)
 
 
 def loadpredicate(ui, extname, registrarobj):
     """Load fileset predicates from specified registrarobj
     """
     for name, func in registrarobj._table.iteritems():
         symbols[name] = func
 
 # tell hggettext to extract docstrings from these functions:
 i18nfunctions = symbols.values()

mercurial/hgweb/webutil.py

@@ -1,813 +1,813 b''
 # hgweb/webutil.py - utility library for the web interface.
 #
 # Copyright 21 May 2005 - (c) 2005 Jake Edge <[e-mail]>
 # Copyright 2005-2007 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 copy
 import difflib
 import os
 import re
 
 from ..i18n import _
 from ..node import hex, nullid, short
 
 from .common import (
     ErrorResponse,
     HTTP_BAD_REQUEST,
     HTTP_NOT_FOUND,
     paritygen,
 )
 
 from .. import (
     context,
     diffutil,
     error,
     match,
     mdiff,
     obsutil,
     patch,
     pathutil,
     pycompat,
     scmutil,
     templatefilters,
     templatekw,
     templateutil,
     ui as uimod,
     util,
 )
 
 from ..utils import (
     stringutil,
 )
 
 archivespecs = util.sortdict((
     ('zip', ('application/zip', 'zip', '.zip', None)),
     ('gz', ('application/x-gzip', 'tgz', '.tar.gz', None)),
     ('bz2', ('application/x-bzip2', 'tbz2', '.tar.bz2', None)),
 ))
 
 def archivelist(ui, nodeid, url=None):
     allowed = ui.configlist('web', 'allow-archive', untrusted=True)
     archives = []
 
     for typ, spec in archivespecs.iteritems():
         if typ in allowed or ui.configbool('web', 'allow' + typ,
                                            untrusted=True):
             archives.append({
                 'type': typ,
                 'extension': spec[2],
                 'node': nodeid,
                 'url': url,
             })
 
     return templateutil.mappinglist(archives)
 
 def up(p):
     if p[0:1] != "/":
         p = "/" + p
     if p[-1:] == "/":
         p = p[:-1]
     up = os.path.dirname(p)
     if up == "/":
         return "/"
     return up + "/"
 
 def _navseq(step, firststep=None):
     if firststep:
         yield firststep
         if firststep >= 20 and firststep <= 40:
             firststep = 50
             yield firststep
         assert step > 0
         assert firststep > 0
         while step <= firststep:
             step *= 10
     while True:
         yield 1 * step
         yield 3 * step
         step *= 10
 
 class revnav(object):
 
     def __init__(self, repo):
         """Navigation generation object
 
         :repo: repo object we generate nav for
         """
         # used for hex generation
         self._revlog = repo.changelog
 
     def __nonzero__(self):
         """return True if any revision to navigate over"""
         return self._first() is not None
 
     __bool__ = __nonzero__
 
     def _first(self):
         """return the minimum non-filtered changeset or None"""
         try:
             return next(iter(self._revlog))
         except StopIteration:
             return None
 
     def hex(self, rev):
         return hex(self._revlog.node(rev))
 
     def gen(self, pos, pagelen, limit):
         """computes label and revision id for navigation link
 
         :pos: is the revision relative to which we generate navigation.
         :pagelen: the size of each navigation page
         :limit: how far shall we link
 
         The return is:
             - a single element mappinglist
             - containing a dictionary with a `before` and `after` key
             - values are dictionaries with `label` and `node` keys
         """
         if not self:
             # empty repo
             return templateutil.mappinglist([
                 {'before': templateutil.mappinglist([]),
                  'after': templateutil.mappinglist([])},
             ])
 
         targets = []
         for f in _navseq(1, pagelen):
             if f > limit:
                 break
             targets.append(pos + f)
             targets.append(pos - f)
         targets.sort()
 
         first = self._first()
         navbefore = [{'label': '(%i)' % first, 'node': self.hex(first)}]
         navafter = []
         for rev in targets:
             if rev not in self._revlog:
                 continue
             if pos < rev < limit:
                 navafter.append({'label': '+%d' % abs(rev - pos),
                                  'node': self.hex(rev)})
             if 0 < rev < pos:
                 navbefore.append({'label': '-%d' % abs(rev - pos),
                                   'node': self.hex(rev)})
 
         navafter.append({'label': 'tip', 'node': 'tip'})
 
         # TODO: maybe this can be a scalar object supporting tomap()
         return templateutil.mappinglist([
             {'before': templateutil.mappinglist(navbefore),
              'after': templateutil.mappinglist(navafter)},
         ])
 
 class filerevnav(revnav):
 
     def __init__(self, repo, path):
         """Navigation generation object
 
         :repo: repo object we generate nav for
         :path: path of the file we generate nav for
         """
         # used for iteration
         self._changelog = repo.unfiltered().changelog
         # used for hex generation
         self._revlog = repo.file(path)
 
     def hex(self, rev):
         return hex(self._changelog.node(self._revlog.linkrev(rev)))
 
 # TODO: maybe this can be a wrapper class for changectx/filectx list, which
 # yields {'ctx': ctx}
 def _ctxsgen(context, ctxs):
     for s in ctxs:
         d = {
             'node': s.hex(),
             'rev': s.rev(),
             'user': s.user(),
             'date': s.date(),
             'description': s.description(),
             'branch': s.branch(),
         }
         if util.safehasattr(s, 'path'):
             d['file'] = s.path()
         yield d
 
 def _siblings(siblings=None, hiderev=None):
     if siblings is None:
         siblings = []
     siblings = [s for s in siblings if s.node() != nullid]
     if len(siblings) == 1 and siblings[0].rev() == hiderev:
         siblings = []
     return templateutil.mappinggenerator(_ctxsgen, args=(siblings,))
 
 def difffeatureopts(req, ui, section):
     diffopts = diffutil.difffeatureopts(ui, untrusted=True,
                                         section=section, whitespace=True)
 
     for k in ('ignorews', 'ignorewsamount', 'ignorewseol', 'ignoreblanklines'):
         v = req.qsparams.get(k)
         if v is not None:
             v = stringutil.parsebool(v)
             setattr(diffopts, k, v if v is not None else True)
 
     return diffopts
 
 def annotate(req, fctx, ui):
     diffopts = difffeatureopts(req, ui, 'annotate')
     return fctx.annotate(follow=True, diffopts=diffopts)
 
 def parents(ctx, hide=None):
     if isinstance(ctx, context.basefilectx):
         introrev = ctx.introrev()
         if ctx.changectx().rev() != introrev:
             return _siblings([ctx.repo()[introrev]], hide)
     return _siblings(ctx.parents(), hide)
 
 def children(ctx, hide=None):
     return _siblings(ctx.children(), hide)
 
 def renamelink(fctx):
     r = fctx.renamed()
     if r:
         return templateutil.mappinglist([{'file': r[0], 'node': hex(r[1])}])
     return templateutil.mappinglist([])
 
 def nodetagsdict(repo, node):
     return templateutil.hybridlist(repo.nodetags(node), name='name')
 
 def nodebookmarksdict(repo, node):
     return templateutil.hybridlist(repo.nodebookmarks(node), name='name')
 
 def nodebranchdict(repo, ctx):
     branches = []
     branch = ctx.branch()
     # If this is an empty repo, ctx.node() == nullid,
     # ctx.branch() == 'default'.
     try:
         branchnode = repo.branchtip(branch)
     except error.RepoLookupError:
         branchnode = None
     if branchnode == ctx.node():
         branches.append(branch)
     return templateutil.hybridlist(branches, name='name')
 
 def nodeinbranch(repo, ctx):
     branches = []
     branch = ctx.branch()
     try:
         branchnode = repo.branchtip(branch)
     except error.RepoLookupError:
         branchnode = None
     if branch != 'default' and branchnode != ctx.node():
         branches.append(branch)
     return templateutil.hybridlist(branches, name='name')
 
 def nodebranchnodefault(ctx):
     branches = []
     branch = ctx.branch()
     if branch != 'default':
         branches.append(branch)
     return templateutil.hybridlist(branches, name='name')
 
 def _nodenamesgen(context, f, node, name):
     for t in f(node):
         yield {name: t}
 
 def showtag(repo, t1, node=nullid):
     args = (repo.nodetags, node, 'tag')
     return templateutil.mappinggenerator(_nodenamesgen, args=args, name=t1)
 
 def showbookmark(repo, t1, node=nullid):
     args = (repo.nodebookmarks, node, 'bookmark')
     return templateutil.mappinggenerator(_nodenamesgen, args=args, name=t1)
 
 def branchentries(repo, stripecount, limit=0):
     tips = []
     heads = repo.heads()
     parity = paritygen(stripecount)
     sortkey = lambda item: (not item[1], item[0].rev())
 
     def entries(context):
         count = 0
         if not tips:
             for tag, hs, tip, closed in repo.branchmap().iterbranches():
                 tips.append((repo[tip], closed))
         for ctx, closed in sorted(tips, key=sortkey, reverse=True):
             if limit > 0 and count >= limit:
                 return
             count += 1
             if closed:
                 status = 'closed'
             elif ctx.node() not in heads:
                 status = 'inactive'
             else:
                 status = 'open'
             yield {
                 'parity': next(parity),
                 'branch': ctx.branch(),
                 'status': status,
                 'node': ctx.hex(),
                 'date': ctx.date()
             }
 
     return templateutil.mappinggenerator(entries)
 
 def cleanpath(repo, path):
     path = path.lstrip('/')
     auditor = pathutil.pathauditor(repo.root, realfs=False)
     return pathutil.canonpath(repo.root, '', path, auditor=auditor)
 
 def changectx(repo, req):
     changeid = "tip"
     if 'node' in req.qsparams:
         changeid = req.qsparams['node']
         ipos = changeid.find(':')
         if ipos != -1:
             changeid = changeid[(ipos + 1):]
 
     return scmutil.revsymbol(repo, changeid)
 
 def basechangectx(repo, req):
     if 'node' in req.qsparams:
         changeid = req.qsparams['node']
         ipos = changeid.find(':')
         if ipos != -1:
             changeid = changeid[:ipos]
             return scmutil.revsymbol(repo, changeid)
 
     return None
 
 def filectx(repo, req):
     if 'file' not in req.qsparams:
         raise ErrorResponse(HTTP_NOT_FOUND, 'file not given')
     path = cleanpath(repo, req.qsparams['file'])
     if 'node' in req.qsparams:
         changeid = req.qsparams['node']
     elif 'filenode' in req.qsparams:
         changeid = req.qsparams['filenode']
     else:
         raise ErrorResponse(HTTP_NOT_FOUND, 'node or filenode not given')
     try:
         fctx = scmutil.revsymbol(repo, changeid)[path]
     except error.RepoError:
         fctx = repo.filectx(path, fileid=changeid)
 
     return fctx
 
 def linerange(req):
     linerange = req.qsparams.getall('linerange')
     if not linerange:
         return None
     if len(linerange) > 1:
         raise ErrorResponse(HTTP_BAD_REQUEST,
                             'redundant linerange parameter')
     try:
         fromline, toline = map(int, linerange[0].split(':', 1))
     except ValueError:
         raise ErrorResponse(HTTP_BAD_REQUEST,
                             'invalid linerange parameter')
     try:
         return util.processlinerange(fromline, toline)
     except error.ParseError as exc:
         raise ErrorResponse(HTTP_BAD_REQUEST, pycompat.bytestr(exc))
 
 def formatlinerange(fromline, toline):
     return '%d:%d' % (fromline + 1, toline)
 
 def _succsandmarkersgen(context, mapping):
     repo = context.resource(mapping, 'repo')
     itemmappings = templatekw.showsuccsandmarkers(context, mapping)
     for item in itemmappings.tovalue(context, mapping):
         item['successors'] = _siblings(repo[successor]
                                        for successor in item['successors'])
         yield item
 
 def succsandmarkers(context, mapping):
     return templateutil.mappinggenerator(_succsandmarkersgen, args=(mapping,))
 
 # teach templater succsandmarkers is switched to (context, mapping) API
 succsandmarkers._requires = {'repo', 'ctx'}
 
 def _whyunstablegen(context, mapping):
     repo = context.resource(mapping, 'repo')
     ctx = context.resource(mapping, 'ctx')
 
     entries = obsutil.whyunstable(repo, ctx)
     for entry in entries:
         if entry.get('divergentnodes'):
             entry['divergentnodes'] = _siblings(entry['divergentnodes'])
         yield entry
 
 def whyunstable(context, mapping):
     return templateutil.mappinggenerator(_whyunstablegen, args=(mapping,))
 
 whyunstable._requires = {'repo', 'ctx'}
 
 # helper to mark a function as a new-style template keyword; can be removed
 # once old-style function gets unsupported and new-style becomes the default
 def _kwfunc(f):
     f._requires = ()
     return f
 
 def commonentry(repo, ctx):
     node = scmutil.binnode(ctx)
     return {
         # TODO: perhaps ctx.changectx() should be assigned if ctx is a
         # filectx, but I'm not pretty sure if that would always work because
         # fctx.parents() != fctx.changectx.parents() for example.
         'ctx': ctx,
         'rev': ctx.rev(),
         'node': hex(node),
         'author': ctx.user(),
         'desc': ctx.description(),
         'date': ctx.date(),
         'extra': ctx.extra(),
         'phase': ctx.phasestr(),
         'obsolete': ctx.obsolete(),
         'succsandmarkers': succsandmarkers,
         'instabilities': templateutil.hybridlist(ctx.instabilities(),
                                                  name='instability'),
         'whyunstable': whyunstable,
         'branch': nodebranchnodefault(ctx),
         'inbranch': nodeinbranch(repo, ctx),
         'branches': nodebranchdict(repo, ctx),
         'tags': nodetagsdict(repo, node),
         'bookmarks': nodebookmarksdict(repo, node),
         'parent': _kwfunc(lambda context, mapping: parents(ctx)),
         'child': _kwfunc(lambda context, mapping: children(ctx)),
     }
 
 def changelistentry(web, ctx):
     '''Obtain a dictionary to be used for entries in a changelist.
 
     This function is called when producing items for the "entries" list passed
     to the "shortlog" and "changelog" templates.
     '''
     repo = web.repo
     rev = ctx.rev()
     n = scmutil.binnode(ctx)
     showtags = showtag(repo, 'changelogtag', n)
     files = listfilediffs(ctx.files(), n, web.maxfiles)
 
     entry = commonentry(repo, ctx)
     entry.update({
         'allparents': _kwfunc(lambda context, mapping: parents(ctx)),
         'parent': _kwfunc(lambda context, mapping: parents(ctx, rev - 1)),
         'child': _kwfunc(lambda context, mapping: children(ctx, rev + 1)),
         'changelogtag': showtags,
         'files': files,
     })
     return entry
 
 def changelistentries(web, revs, maxcount, parityfn):
     """Emit up to N records for an iterable of revisions."""
     repo = web.repo
 
     count = 0
     for rev in revs:
         if count >= maxcount:
             break
 
         count += 1
 
         entry = changelistentry(web, repo[rev])
         entry['parity'] = next(parityfn)
 
         yield entry
 
 def symrevorshortnode(req, ctx):
     if 'node' in req.qsparams:
         return templatefilters.revescape(req.qsparams['node'])
     else:
         return short(scmutil.binnode(ctx))
 
 def _listfilesgen(context, ctx, stripecount):
     parity = paritygen(stripecount)
     for blockno, f in enumerate(ctx.files()):
         template = 'filenodelink' if f in ctx else 'filenolink'
         yield context.process(template, {
             'node': ctx.hex(),
             'file': f,
             'blockno': blockno + 1,
             'parity': next(parity),
         })
 
 def changesetentry(web, ctx):
     '''Obtain a dictionary to be used to render the "changeset" template.'''
 
     showtags = showtag(web.repo, 'changesettag', scmutil.binnode(ctx))
     showbookmarks = showbookmark(web.repo, 'changesetbookmark',
                                  scmutil.binnode(ctx))
     showbranch = nodebranchnodefault(ctx)
 
     basectx = basechangectx(web.repo, web.req)
     if basectx is None:
         basectx = ctx.p1()
 
     style = web.config('web', 'style')
     if 'style' in web.req.qsparams:
         style = web.req.qsparams['style']
 
     diff = diffs(web, ctx, basectx, None, style)
 
     parity = paritygen(web.stripecount)
     diffstatsgen = diffstatgen(web.repo.ui, ctx, basectx)
     diffstats = diffstat(ctx, diffstatsgen, parity)
 
     return dict(
         diff=diff,
         symrev=symrevorshortnode(web.req, ctx),
         basenode=basectx.hex(),
         changesettag=showtags,
         changesetbookmark=showbookmarks,
         changesetbranch=showbranch,
         files=templateutil.mappedgenerator(_listfilesgen,
                                            args=(ctx, web.stripecount)),
         diffsummary=_kwfunc(lambda context, mapping: diffsummary(diffstatsgen)),
         diffstat=diffstats,
         archives=web.archivelist(ctx.hex()),
         **pycompat.strkwargs(commonentry(web.repo, ctx)))
 
 def _listfilediffsgen(context, files, node, max):
     for f in files[:max]:
         yield context.process('filedifflink', {'node': hex(node), 'file': f})
     if len(files) > max:
         yield context.process('fileellipses', {})
 
 def listfilediffs(files, node, max):
     return templateutil.mappedgenerator(_listfilediffsgen,
                                         args=(files, node, max))
 
 def _prettyprintdifflines(context, lines, blockno, lineidprefix):
     for lineno, l in enumerate(lines, 1):
         difflineno = "%d.%d" % (blockno, lineno)
         if l.startswith('+'):
             ltype = "difflineplus"
         elif l.startswith('-'):
             ltype = "difflineminus"
         elif l.startswith('@'):
             ltype = "difflineat"
         else:
             ltype = "diffline"
         yield context.process(ltype, {
             'line': l,
             'lineno': lineno,
             'lineid': lineidprefix + "l%s" % difflineno,
             'linenumber': "% 8s" % difflineno,
         })
 
 def _diffsgen(context, repo, ctx, basectx, files, style, stripecount,
               linerange, lineidprefix):
     if files:
-        m = match.exact(repo.root, repo.getcwd(), files)
+        m = match.exact(files)
     else:
-        m = match.always(repo.root, repo.getcwd())
+        m = match.always()
 
     diffopts = patch.diffopts(repo.ui, untrusted=True)
     parity = paritygen(stripecount)
 
     diffhunks = patch.diffhunks(repo, basectx, ctx, m, opts=diffopts)
     for blockno, (fctx1, fctx2, header, hunks) in enumerate(diffhunks, 1):
         if style != 'raw':
             header = header[1:]
         lines = [h + '\n' for h in header]
         for hunkrange, hunklines in hunks:
             if linerange is not None and hunkrange is not None:
                 s1, l1, s2, l2 = hunkrange
                 if not mdiff.hunkinrange((s2, l2), linerange):
                     continue
             lines.extend(hunklines)
         if lines:
             l = templateutil.mappedgenerator(_prettyprintdifflines,
                                              args=(lines, blockno,
                                                    lineidprefix))
             yield {
                 'parity': next(parity),
                 'blockno': blockno,
                 'lines': l,
             }
 
 def diffs(web, ctx, basectx, files, style, linerange=None, lineidprefix=''):
     args = (web.repo, ctx, basectx, files, style, web.stripecount,
             linerange, lineidprefix)
     return templateutil.mappinggenerator(_diffsgen, args=args, name='diffblock')
 
 def _compline(type, leftlineno, leftline, rightlineno, rightline):
     lineid = leftlineno and ("l%d" % leftlineno) or ''
     lineid += rightlineno and ("r%d" % rightlineno) or ''
     llno = '%d' % leftlineno if leftlineno else ''
     rlno = '%d' % rightlineno if rightlineno else ''
     return {
         'type': type,
         'lineid': lineid,
         'leftlineno': leftlineno,
         'leftlinenumber': "% 6s" % llno,
         'leftline': leftline or '',
         'rightlineno': rightlineno,
         'rightlinenumber': "% 6s" % rlno,
         'rightline': rightline or '',
     }
 
 def _getcompblockgen(context, leftlines, rightlines, opcodes):
     for type, llo, lhi, rlo, rhi in opcodes:
         type = pycompat.sysbytes(type)
         len1 = lhi - llo
         len2 = rhi - rlo
         count = min(len1, len2)
         for i in pycompat.xrange(count):
             yield _compline(type=type,
                             leftlineno=llo + i + 1,
                             leftline=leftlines[llo + i],
                             rightlineno=rlo + i + 1,
                             rightline=rightlines[rlo + i])
         if len1 > len2:
             for i in pycompat.xrange(llo + count, lhi):
                 yield _compline(type=type,
                                 leftlineno=i + 1,
                                 leftline=leftlines[i],
                                 rightlineno=None,
                                 rightline=None)
         elif len2 > len1:
             for i in pycompat.xrange(rlo + count, rhi):
                 yield _compline(type=type,
                                 leftlineno=None,
                                 leftline=None,
                                 rightlineno=i + 1,
                                 rightline=rightlines[i])
 
 def _getcompblock(leftlines, rightlines, opcodes):
     args = (leftlines, rightlines, opcodes)
     return templateutil.mappinggenerator(_getcompblockgen, args=args,
                                          name='comparisonline')
 
 def _comparegen(context, contextnum, leftlines, rightlines):
     '''Generator function that provides side-by-side comparison data.'''
     s = difflib.SequenceMatcher(None, leftlines, rightlines)
     if contextnum < 0:
         l = _getcompblock(leftlines, rightlines, s.get_opcodes())
         yield {'lines': l}
     else:
         for oc in s.get_grouped_opcodes(n=contextnum):
             l = _getcompblock(leftlines, rightlines, oc)
             yield {'lines': l}
 
 def compare(contextnum, leftlines, rightlines):
     args = (contextnum, leftlines, rightlines)
     return templateutil.mappinggenerator(_comparegen, args=args,
                                          name='comparisonblock')
 
 def diffstatgen(ui, ctx, basectx):
     '''Generator function that provides the diffstat data.'''
 
     diffopts = patch.diffopts(ui, {'noprefix': False})
     stats = patch.diffstatdata(
         util.iterlines(ctx.diff(basectx, opts=diffopts)))
     maxname, maxtotal, addtotal, removetotal, binary = patch.diffstatsum(stats)
     while True:
         yield stats, maxname, maxtotal, addtotal, removetotal, binary
 
 def diffsummary(statgen):
     '''Return a short summary of the diff.'''
 
     stats, maxname, maxtotal, addtotal, removetotal, binary = next(statgen)
     return _(' %d files changed, %d insertions(+), %d deletions(-)\n') % (
              len(stats), addtotal, removetotal)
 
 def _diffstattmplgen(context, ctx, statgen, parity):
     stats, maxname, maxtotal, addtotal, removetotal, binary = next(statgen)
     files = ctx.files()
 
     def pct(i):
         if maxtotal == 0:
             return 0
         return (float(i) / maxtotal) * 100
 
     fileno = 0
     for filename, adds, removes, isbinary in stats:
         template = 'diffstatlink' if filename in files else 'diffstatnolink'
         total = adds + removes
         fileno += 1
         yield context.process(template, {
             'node': ctx.hex(),
             'file': filename,
             'fileno': fileno,
             'total': total,
             'addpct': pct(adds),
             'removepct': pct(removes),
             'parity': next(parity),
         })
 
 def diffstat(ctx, statgen, parity):
     '''Return a diffstat template for each file in the diff.'''
     args = (ctx, statgen, parity)
     return templateutil.mappedgenerator(_diffstattmplgen, args=args)
 
 class sessionvars(templateutil.wrapped):
     def __init__(self, vars, start='?'):
         self._start = start
         self._vars = vars
 
     def __getitem__(self, key):
         return self._vars[key]
 
     def __setitem__(self, key, value):
         self._vars[key] = value
 
     def __copy__(self):
         return sessionvars(copy.copy(self._vars), self._start)
 
     def contains(self, context, mapping, item):
         item = templateutil.unwrapvalue(context, mapping, item)
         return item in self._vars
 
     def getmember(self, context, mapping, key):
         key = templateutil.unwrapvalue(context, mapping, key)
         return self._vars.get(key)
 
     def getmin(self, context, mapping):
         raise error.ParseError(_('not comparable'))
 
     def getmax(self, context, mapping):
         raise error.ParseError(_('not comparable'))
 
     def filter(self, context, mapping, select):
         # implement if necessary
         raise error.ParseError(_('not filterable'))
 
     def itermaps(self, context):
         separator = self._start
         for key, value in sorted(self._vars.iteritems()):
             yield {'name': key,
                    'value': pycompat.bytestr(value),
                    'separator': separator,
             }
             separator = '&'
 
     def join(self, context, mapping, sep):
         # could be '{separator}{name}={value|urlescape}'
         raise error.ParseError(_('not displayable without template'))
 
     def show(self, context, mapping):
         return self.join(context, '')
 
     def tobool(self, context, mapping):
         return bool(self._vars)
 
     def tovalue(self, context, mapping):
         return self._vars
 
 class wsgiui(uimod.ui):
     # default termwidth breaks under mod_wsgi
     def termwidth(self):
         return 80
 
 def getwebsubs(repo):
     websubtable = []
     websubdefs = repo.ui.configitems('websub')
     # we must maintain interhg backwards compatibility
     websubdefs += repo.ui.configitems('interhg')
     for key, pattern in websubdefs:
         # grab the delimiter from the character after the "s"
         unesc = pattern[1:2]
         delim = stringutil.reescape(unesc)
 
         # identify portions of the pattern, taking care to avoid escaped
         # delimiters. the replace format and flags are optional, but
         # delimiters are required.
         match = re.match(
             br'^s%s(.+)(?:(?<=\\\\)|(?<!\\))%s(.*)%s([ilmsux])*$'
             % (delim, delim, delim), pattern)
         if not match:
             repo.ui.warn(_("websub: invalid pattern for %s: %s\n")
                               % (key, pattern))
             continue
 
         # we need to unescape the delimiter for regexp and format
         delim_re = re.compile(br'(?<!\\)\\%s' % delim)
         regexp = delim_re.sub(unesc, match.group(1))
         format = delim_re.sub(unesc, match.group(2))
 
         # the pattern allows for 6 regexp flags, so set them if necessary
         flagin = match.group(3)
         flags = 0
         if flagin:
             for flag in flagin.upper():
                 flags |= re.__dict__[flag]
 
         try:
             regexp = re.compile(regexp, flags)
             websubtable.append((regexp, format))
         except re.error:
             repo.ui.warn(_("websub: invalid regexp for %s: %s\n")
                          % (key, regexp))
     return websubtable
 
 def getgraphnode(repo, ctx):
     return (templatekw.getgraphnodecurrent(repo, ctx) +
             templatekw.getgraphnodesymbol(ctx))