merge: while checking for unknown files don't follow symlinks (issue5027)

Previously, we were using Python's native 'os.path.isfile' method which follows
symlinks. In this case, since we're operating on repo contents, we don't want
to follow symlinks.

There's a behaviour change here, as shown by the second part of the added test.
Consider a symlink 'f' pointing to a file containing 'abc'. If we try and
replace it with a file with contents 'abc', previously we would have let it
though. Now we don't. Although this breaks naive inspection with tools like
'cat' and 'diff', on balance I believe this is the right change.

mercurial/merge.py

@@ -1,1344 +1,1344
 # merge.py - directory-level update/merge handling for Mercurial
 #
 # Copyright 2006, 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 errno
 import os
 import shutil
 import struct
 
 from .i18n import _
 from .node import (
     bin,
     hex,
     nullid,
     nullrev,
 )
 from . import (
     copies,
     destutil,
     error,
     filemerge,
     obsolete,
     subrepo,
     util,
     worker,
 )
 
 _pack = struct.pack
 _unpack = struct.unpack
 
 def _droponode(data):
     # used for compatibility for v1
     bits = data.split('\0')
     bits = bits[:-2] + bits[-1:]
     return '\0'.join(bits)
 
 class mergestate(object):
     '''track 3-way merge state of individual files
 
     it is stored on disk when needed. Two file are used, one with an old
     format, one with a new format. Both contains similar data, but the new
     format can store new kinds of field.
 
     Current new format is a list of arbitrary record of the form:
 
         [type][length][content]
 
     Type is a single character, length is a 4 bytes integer, content is an
     arbitrary suites of bytes of length `length`.
 
     Type should be a letter. Capital letter are mandatory record, Mercurial
     should abort if they are unknown. lower case record can be safely ignored.
 
     Currently known record:
 
     L: the node of the "local" part of the merge (hexified version)
     O: the node of the "other" part of the merge (hexified version)
     F: a file to be merged entry
     D: a file that the external merge driver will merge internally
        (experimental)
     m: the external merge driver defined for this merge plus its run state
        (experimental)
 
     Merge driver run states (experimental):
     u: driver-resolved files unmarked -- needs to be run next time we're about
        to resolve or commit
     m: driver-resolved files marked -- only needs to be run before commit
     s: success/skipped -- does not need to be run any more
     '''
     statepathv1 = 'merge/state'
     statepathv2 = 'merge/state2'
 
     def __init__(self, repo):
         self._repo = repo
         self._dirty = False
         self._read()
 
     def reset(self, node=None, other=None):
         self._state = {}
         self._local = None
         self._other = None
         if 'otherctx' in vars(self):
             del self.otherctx
         if node:
             self._local = node
             self._other = other
         self._readmergedriver = None
         if self.mergedriver:
             self._mdstate = 's'
         else:
             self._mdstate = 'u'
         shutil.rmtree(self._repo.join('merge'), True)
         self._dirty = False
 
     def _read(self):
         """Analyse each record content to restore a serialized state from disk
 
         This function process "record" entry produced by the de-serialization
         of on disk file.
         """
         self._state = {}
         self._local = None
         self._other = None
         if 'otherctx' in vars(self):
             del self.otherctx
         self._readmergedriver = None
         self._mdstate = 's'
         records = self._readrecords()
         for rtype, record in records:
             if rtype == 'L':
                 self._local = bin(record)
             elif rtype == 'O':
                 self._other = bin(record)
             elif rtype == 'm':
                 bits = record.split('\0', 1)
                 mdstate = bits[1]
                 if len(mdstate) != 1 or mdstate not in 'ums':
                     # the merge driver should be idempotent, so just rerun it
                     mdstate = 'u'
 
                 self._readmergedriver = bits[0]
                 self._mdstate = mdstate
             elif rtype in 'FD':
                 bits = record.split('\0')
                 self._state[bits[0]] = bits[1:]
             elif not rtype.islower():
                 raise error.Abort(_('unsupported merge state record: %s')
                                    % rtype)
         self._dirty = False
 
     def _readrecords(self):
         """Read merge state from disk and return a list of record (TYPE, data)
 
         We read data from both v1 and v2 files and decide which one to use.
 
         V1 has been used by version prior to 2.9.1 and contains less data than
         v2. We read both versions and check if no data in v2 contradicts
         v1. If there is not contradiction we can safely assume that both v1
         and v2 were written at the same time and use the extract data in v2. If
         there is contradiction we ignore v2 content as we assume an old version
         of Mercurial has overwritten the mergestate file and left an old v2
         file around.
 
         returns list of record [(TYPE, data), ...]"""
         v1records = self._readrecordsv1()
         v2records = self._readrecordsv2()
         if self._v1v2match(v1records, v2records):
             return v2records
         else:
             # v1 file is newer than v2 file, use it
             # we have to infer the "other" changeset of the merge
             # we cannot do better than that with v1 of the format
             mctx = self._repo[None].parents()[-1]
             v1records.append(('O', mctx.hex()))
             # add place holder "other" file node information
             # nobody is using it yet so we do no need to fetch the data
             # if mctx was wrong `mctx[bits[-2]]` may fails.
             for idx, r in enumerate(v1records):
                 if r[0] == 'F':
                     bits = r[1].split('\0')
                     bits.insert(-2, '')
                     v1records[idx] = (r[0], '\0'.join(bits))
             return v1records
 
     def _v1v2match(self, v1records, v2records):
         oldv2 = set() # old format version of v2 record
         for rec in v2records:
             if rec[0] == 'L':
                 oldv2.add(rec)
             elif rec[0] == 'F':
                 # drop the onode data (not contained in v1)
                 oldv2.add(('F', _droponode(rec[1])))
         for rec in v1records:
             if rec not in oldv2:
                 return False
         else:
             return True
 
     def _readrecordsv1(self):
         """read on disk merge state for version 1 file
 
         returns list of record [(TYPE, data), ...]
 
         Note: the "F" data from this file are one entry short
               (no "other file node" entry)
         """
         records = []
         try:
             f = self._repo.vfs(self.statepathv1)
             for i, l in enumerate(f):
                 if i == 0:
                     records.append(('L', l[:-1]))
                 else:
                     records.append(('F', l[:-1]))
             f.close()
         except IOError as err:
             if err.errno != errno.ENOENT:
                 raise
         return records
 
     def _readrecordsv2(self):
         """read on disk merge state for version 2 file
 
         returns list of record [(TYPE, data), ...]
         """
         records = []
         try:
             f = self._repo.vfs(self.statepathv2)
             data = f.read()
             off = 0
             end = len(data)
             while off < end:
                 rtype = data[off]
                 off += 1
                 length = _unpack('>I', data[off:(off + 4)])[0]
                 off += 4
                 record = data[off:(off + length)]
                 off += length
                 records.append((rtype, record))
             f.close()
         except IOError as err:
             if err.errno != errno.ENOENT:
                 raise
         return records
 
     @util.propertycache
     def mergedriver(self):
         # protect against the following:
         # - A configures a malicious merge driver in their hgrc, then
         #   pauses the merge
         # - A edits their hgrc to remove references to the merge driver
         # - A gives a copy of their entire repo, including .hg, to B
         # - B inspects .hgrc and finds it to be clean
         # - B then continues the merge and the malicious merge driver
         #  gets invoked
         configmergedriver = self._repo.ui.config('experimental', 'mergedriver')
         if (self._readmergedriver is not None
             and self._readmergedriver != configmergedriver):
             raise error.ConfigError(
                 _("merge driver changed since merge started"),
                 hint=_("revert merge driver change or abort merge"))
 
         return configmergedriver
 
     @util.propertycache
     def otherctx(self):
         return self._repo[self._other]
 
     def active(self):
         """Whether mergestate is active.
 
         Returns True if there appears to be mergestate. This is a rough proxy
         for "is a merge in progress."
         """
         # Check local variables before looking at filesystem for performance
         # reasons.
         return bool(self._local) or bool(self._state) or \
                self._repo.vfs.exists(self.statepathv1) or \
                self._repo.vfs.exists(self.statepathv2)
 
     def commit(self):
         """Write current state on disk (if necessary)"""
         if self._dirty:
             records = []
             records.append(('L', hex(self._local)))
             records.append(('O', hex(self._other)))
             if self.mergedriver:
                 records.append(('m', '\0'.join([
                     self.mergedriver, self._mdstate])))
             for d, v in self._state.iteritems():
                 if v[0] == 'd':
                     records.append(('D', '\0'.join([d] + v)))
                 else:
                     records.append(('F', '\0'.join([d] + v)))
             self._writerecords(records)
             self._dirty = False
 
     def _writerecords(self, records):
         """Write current state on disk (both v1 and v2)"""
         self._writerecordsv1(records)
         self._writerecordsv2(records)
 
     def _writerecordsv1(self, records):
         """Write current state on disk in a version 1 file"""
         f = self._repo.vfs(self.statepathv1, 'w')
         irecords = iter(records)
         lrecords = irecords.next()
         assert lrecords[0] == 'L'
         f.write(hex(self._local) + '\n')
         for rtype, data in irecords:
             if rtype == 'F':
                 f.write('%s\n' % _droponode(data))
         f.close()
 
     def _writerecordsv2(self, records):
         """Write current state on disk in a version 2 file"""
         f = self._repo.vfs(self.statepathv2, 'w')
         for key, data in records:
             assert len(key) == 1
             format = '>sI%is' % len(data)
             f.write(_pack(format, key, len(data), data))
         f.close()
 
     def add(self, fcl, fco, fca, fd):
         """add a new (potentially?) conflicting file the merge state
         fcl: file context for local,
         fco: file context for remote,
         fca: file context for ancestors,
         fd:  file path of the resulting merge.
 
         note: also write the local version to the `.hg/merge` directory.
         """
         hash = util.sha1(fcl.path()).hexdigest()
         self._repo.vfs.write('merge/' + hash, fcl.data())
         self._state[fd] = ['u', hash, fcl.path(),
                            fca.path(), hex(fca.filenode()),
                            fco.path(), hex(fco.filenode()),
                            fcl.flags()]
         self._dirty = True
 
     def __contains__(self, dfile):
         return dfile in self._state
 
     def __getitem__(self, dfile):
         return self._state[dfile][0]
 
     def __iter__(self):
         return iter(sorted(self._state))
 
     def files(self):
         return self._state.keys()
 
     def mark(self, dfile, state):
         self._state[dfile][0] = state
         self._dirty = True
 
     def mdstate(self):
         return self._mdstate
 
     def unresolved(self):
         """Obtain the paths of unresolved files."""
 
         for f, entry in self._state.items():
             if entry[0] == 'u':
                 yield f
 
     def driverresolved(self):
         """Obtain the paths of driver-resolved files."""
 
         for f, entry in self._state.items():
             if entry[0] == 'd':
                 yield f
 
     def _resolve(self, preresolve, dfile, wctx, labels=None):
         """rerun merge process for file path `dfile`"""
         if self[dfile] in 'rd':
             return True, 0
         stateentry = self._state[dfile]
         state, hash, lfile, afile, anode, ofile, onode, flags = stateentry
         octx = self._repo[self._other]
         fcd = wctx[dfile]
         fco = octx[ofile]
         fca = self._repo.filectx(afile, fileid=anode)
         # "premerge" x flags
         flo = fco.flags()
         fla = fca.flags()
         if 'x' in flags + flo + fla and 'l' not in flags + flo + fla:
             if fca.node() == nullid:
                 if preresolve:
                     self._repo.ui.warn(
                         _('warning: cannot merge flags for %s\n') % afile)
             elif flags == fla:
                 flags = flo
         if preresolve:
             # restore local
             f = self._repo.vfs('merge/' + hash)
             self._repo.wwrite(dfile, f.read(), flags)
             f.close()
             complete, r = filemerge.premerge(self._repo, self._local, lfile,
                                              fcd, fco, fca, labels=labels)
         else:
             complete, r = filemerge.filemerge(self._repo, self._local, lfile,
                                               fcd, fco, fca, labels=labels)
         if r is None:
             # no real conflict
             del self._state[dfile]
             self._dirty = True
         elif not r:
             self.mark(dfile, 'r')
         return complete, r
 
     def preresolve(self, dfile, wctx, labels=None):
         return self._resolve(True, dfile, wctx, labels=labels)
 
     def resolve(self, dfile, wctx, labels=None):
         """rerun merge process for file path `dfile`"""
         return self._resolve(False, dfile, wctx, labels=labels)[1]
 
 def _checkunknownfile(repo, wctx, mctx, f, f2=None):
     if f2 is None:
         f2 = f
-    return (os.path.isfile(repo.wjoin(f))
+    return (repo.wvfs.isfileorlink(f)
         and repo.wvfs.audit.check(f)
         and repo.dirstate.normalize(f) not in repo.dirstate
         and mctx[f2].cmp(wctx[f]))
 
 def _checkunknownfiles(repo, wctx, mctx, force, actions):
     """
     Considers any actions that care about the presence of conflicting unknown
     files. For some actions, the result is to abort; for others, it is to
     choose a different action.
     """
     aborts = []
     if not force:
         for f, (m, args, msg) in actions.iteritems():
             if m in ('c', 'dc'):
                 if _checkunknownfile(repo, wctx, mctx, f):
                     aborts.append(f)
             elif m == 'dg':
                 if _checkunknownfile(repo, wctx, mctx, f, args[0]):
                     aborts.append(f)
 
     for f in sorted(aborts):
         repo.ui.warn(_("%s: untracked file differs\n") % f)
     if aborts:
         raise error.Abort(_("untracked files in working directory differ "
                            "from files in requested revision"))
 
     for f, (m, args, msg) in actions.iteritems():
         if m == 'c':
             actions[f] = ('g', args, msg)
         elif m == 'cm':
             fl2, anc = args
             different = _checkunknownfile(repo, wctx, mctx, f)
             if different:
                 actions[f] = ('m', (f, f, None, False, anc),
                               "remote differs from untracked local")
             else:
                 actions[f] = ('g', (fl2,), "remote created")
 
 def _forgetremoved(wctx, mctx, branchmerge):
     """
     Forget removed files
 
     If we're jumping between revisions (as opposed to merging), and if
     neither the working directory nor the target rev has the file,
     then we need to remove it from the dirstate, to prevent the
     dirstate from listing the file when it is no longer in the
     manifest.
 
     If we're merging, and the other revision has removed a file
     that is not present in the working directory, we need to mark it
     as removed.
     """
 
     actions = {}
     m = 'f'
     if branchmerge:
         m = 'r'
     for f in wctx.deleted():
         if f not in mctx:
             actions[f] = m, None, "forget deleted"
 
     if not branchmerge:
         for f in wctx.removed():
             if f not in mctx:
                 actions[f] = 'f', None, "forget removed"
 
     return actions
 
 def _checkcollision(repo, wmf, actions):
     # build provisional merged manifest up
     pmmf = set(wmf)
 
     if actions:
         # k, dr, e and rd are no-op
         for m in 'a', 'f', 'g', 'cd', 'dc':
             for f, args, msg in actions[m]:
                 pmmf.add(f)
         for f, args, msg in actions['r']:
             pmmf.discard(f)
         for f, args, msg in actions['dm']:
             f2, flags = args
             pmmf.discard(f2)
             pmmf.add(f)
         for f, args, msg in actions['dg']:
             pmmf.add(f)
         for f, args, msg in actions['m']:
             f1, f2, fa, move, anc = args
             if move:
                 pmmf.discard(f1)
             pmmf.add(f)
 
     # check case-folding collision in provisional merged manifest
     foldmap = {}
     for f in sorted(pmmf):
         fold = util.normcase(f)
         if fold in foldmap:
             raise error.Abort(_("case-folding collision between %s and %s")
                              % (f, foldmap[fold]))
         foldmap[fold] = f
 
     # check case-folding of directories
     foldprefix = unfoldprefix = lastfull = ''
     for fold, f in sorted(foldmap.items()):
         if fold.startswith(foldprefix) and not f.startswith(unfoldprefix):
             # the folded prefix matches but actual casing is different
             raise error.Abort(_("case-folding collision between "
                                 "%s and directory of %s") % (lastfull, f))
         foldprefix = fold + '/'
         unfoldprefix = f + '/'
         lastfull = f
 
 def driverpreprocess(repo, ms, wctx, labels=None):
     """run the preprocess step of the merge driver, if any
 
     This is currently not implemented -- it's an extension point."""
     return True
 
 def driverconclude(repo, ms, wctx, labels=None):
     """run the conclude step of the merge driver, if any
 
     This is currently not implemented -- it's an extension point."""
     return True
 
 def manifestmerge(repo, wctx, p2, pa, branchmerge, force, partial,
                   acceptremote, followcopies):
     """
     Merge p1 and p2 with ancestor pa and generate merge action list
 
     branchmerge and force are as passed in to update
     partial = function to filter file lists
     acceptremote = accept the incoming changes without prompting
     """
 
     copy, movewithdir, diverge, renamedelete = {}, {}, {}, {}
 
     # manifests fetched in order are going to be faster, so prime the caches
     [x.manifest() for x in
      sorted(wctx.parents() + [p2, pa], key=lambda x: x.rev())]
 
     if followcopies:
         ret = copies.mergecopies(repo, wctx, p2, pa)
         copy, movewithdir, diverge, renamedelete = ret
 
     repo.ui.note(_("resolving manifests\n"))
     repo.ui.debug(" branchmerge: %s, force: %s, partial: %s\n"
                   % (bool(branchmerge), bool(force), bool(partial)))
     repo.ui.debug(" ancestor: %s, local: %s, remote: %s\n" % (pa, wctx, p2))
 
     m1, m2, ma = wctx.manifest(), p2.manifest(), pa.manifest()
     copied = set(copy.values())
     copied.update(movewithdir.values())
 
     if '.hgsubstate' in m1:
         # check whether sub state is modified
         for s in sorted(wctx.substate):
             if wctx.sub(s).dirty():
                 m1['.hgsubstate'] += '+'
                 break
 
     # Compare manifests
     diff = m1.diff(m2)
 
     actions = {}
     for f, ((n1, fl1), (n2, fl2)) in diff.iteritems():
         if partial and not partial(f):
             continue
         if n1 and n2: # file exists on both local and remote side
             if f not in ma:
                 fa = copy.get(f, None)
                 if fa is not None:
                     actions[f] = ('m', (f, f, fa, False, pa.node()),
                                   "both renamed from " + fa)
                 else:
                     actions[f] = ('m', (f, f, None, False, pa.node()),
                                   "both created")
             else:
                 a = ma[f]
                 fla = ma.flags(f)
                 nol = 'l' not in fl1 + fl2 + fla
                 if n2 == a and fl2 == fla:
                     actions[f] = ('k' , (), "remote unchanged")
                 elif n1 == a and fl1 == fla: # local unchanged - use remote
                     if n1 == n2: # optimization: keep local content
                         actions[f] = ('e', (fl2,), "update permissions")
                     else:
                         actions[f] = ('g', (fl2,), "remote is newer")
                 elif nol and n2 == a: # remote only changed 'x'
                     actions[f] = ('e', (fl2,), "update permissions")
                 elif nol and n1 == a: # local only changed 'x'
                     actions[f] = ('g', (fl1,), "remote is newer")
                 else: # both changed something
                     actions[f] = ('m', (f, f, f, False, pa.node()),
                                    "versions differ")
         elif n1: # file exists only on local side
             if f in copied:
                 pass # we'll deal with it on m2 side
             elif f in movewithdir: # directory rename, move local
                 f2 = movewithdir[f]
                 if f2 in m2:
                     actions[f2] = ('m', (f, f2, None, True, pa.node()),
                                    "remote directory rename, both created")
                 else:
                     actions[f2] = ('dm', (f, fl1),
                                    "remote directory rename - move from " + f)
             elif f in copy:
                 f2 = copy[f]
                 actions[f] = ('m', (f, f2, f2, False, pa.node()),
                               "local copied/moved from " + f2)
             elif f in ma: # clean, a different, no remote
                 if n1 != ma[f]:
                     if acceptremote:
                         actions[f] = ('r', None, "remote delete")
                     else:
                         actions[f] = ('cd', None,  "prompt changed/deleted")
                 elif n1[20:] == 'a':
                     # This extra 'a' is added by working copy manifest to mark
                     # the file as locally added. We should forget it instead of
                     # deleting it.
                     actions[f] = ('f', None, "remote deleted")
                 else:
                     actions[f] = ('r', None, "other deleted")
         elif n2: # file exists only on remote side
             if f in copied:
                 pass # we'll deal with it on m1 side
             elif f in movewithdir:
                 f2 = movewithdir[f]
                 if f2 in m1:
                     actions[f2] = ('m', (f2, f, None, False, pa.node()),
                                    "local directory rename, both created")
                 else:
                     actions[f2] = ('dg', (f, fl2),
                                    "local directory rename - get from " + f)
             elif f in copy:
                 f2 = copy[f]
                 if f2 in m2:
                     actions[f] = ('m', (f2, f, f2, False, pa.node()),
                                   "remote copied from " + f2)
                 else:
                     actions[f] = ('m', (f2, f, f2, True, pa.node()),
                                   "remote moved from " + f2)
             elif f not in ma:
                 # local unknown, remote created: the logic is described by the
                 # following table:
                 #
                 # force  branchmerge  different  |  action
                 #   n         *           *      |   create
                 #   y         n           *      |   create
                 #   y         y           n      |   create
                 #   y         y           y      |   merge
                 #
                 # Checking whether the files are different is expensive, so we
                 # don't do that when we can avoid it.
                 if not force:
                     actions[f] = ('c', (fl2,), "remote created")
                 elif not branchmerge:
                     actions[f] = ('c', (fl2,), "remote created")
                 else:
                     actions[f] = ('cm', (fl2, pa.node()),
                                   "remote created, get or merge")
             elif n2 != ma[f]:
                 if acceptremote:
                     actions[f] = ('c', (fl2,), "remote recreating")
                 else:
                     actions[f] = ('dc', (fl2,), "prompt deleted/changed")
 
     return actions, diverge, renamedelete
 
 def _resolvetrivial(repo, wctx, mctx, ancestor, actions):
     """Resolves false conflicts where the nodeid changed but the content
        remained the same."""
 
     for f, (m, args, msg) in actions.items():
         if m == 'cd' and f in ancestor and not wctx[f].cmp(ancestor[f]):
             # local did change but ended up with same content
             actions[f] = 'r', None, "prompt same"
         elif m == 'dc' and f in ancestor and not mctx[f].cmp(ancestor[f]):
             # remote did change but ended up with same content
             del actions[f] # don't get = keep local deleted
 
 def calculateupdates(repo, wctx, mctx, ancestors, branchmerge, force, partial,
                      acceptremote, followcopies):
     "Calculate the actions needed to merge mctx into wctx using ancestors"
 
     if len(ancestors) == 1: # default
         actions, diverge, renamedelete = manifestmerge(
             repo, wctx, mctx, ancestors[0], branchmerge, force, partial,
             acceptremote, followcopies)
         _checkunknownfiles(repo, wctx, mctx, force, actions)
 
     else: # only when merge.preferancestor=* - the default
         repo.ui.note(
             _("note: merging %s and %s using bids from ancestors %s\n") %
             (wctx, mctx, _(' and ').join(str(anc) for anc in ancestors)))
 
         # Call for bids
         fbids = {} # mapping filename to bids (action method to list af actions)
         diverge, renamedelete = None, None
         for ancestor in ancestors:
             repo.ui.note(_('\ncalculating bids for ancestor %s\n') % ancestor)
             actions, diverge1, renamedelete1 = manifestmerge(
                 repo, wctx, mctx, ancestor, branchmerge, force, partial,
                 acceptremote, followcopies)
             _checkunknownfiles(repo, wctx, mctx, force, actions)
 
             # Track the shortest set of warning on the theory that bid
             # merge will correctly incorporate more information
             if diverge is None or len(diverge1) < len(diverge):
                 diverge = diverge1
             if renamedelete is None or len(renamedelete) < len(renamedelete1):
                 renamedelete = renamedelete1
 
             for f, a in sorted(actions.iteritems()):
                 m, args, msg = a
                 repo.ui.debug(' %s: %s -> %s\n' % (f, msg, m))
                 if f in fbids:
                     d = fbids[f]
                     if m in d:
                         d[m].append(a)
                     else:
                         d[m] = [a]
                 else:
                     fbids[f] = {m: [a]}
 
         # Pick the best bid for each file
         repo.ui.note(_('\nauction for merging merge bids\n'))
         actions = {}
         for f, bids in sorted(fbids.items()):
             # bids is a mapping from action method to list af actions
             # Consensus?
             if len(bids) == 1: # all bids are the same kind of method
                 m, l = bids.items()[0]
                 if all(a == l[0] for a in l[1:]): # len(bids) is > 1
                     repo.ui.note(" %s: consensus for %s\n" % (f, m))
                     actions[f] = l[0]
                     continue
             # If keep is an option, just do it.
             if 'k' in bids:
                 repo.ui.note(" %s: picking 'keep' action\n" % f)
                 actions[f] = bids['k'][0]
                 continue
             # If there are gets and they all agree [how could they not?], do it.
             if 'g' in bids:
                 ga0 = bids['g'][0]
                 if all(a == ga0 for a in bids['g'][1:]):
                     repo.ui.note(" %s: picking 'get' action\n" % f)
                     actions[f] = ga0
                     continue
             # TODO: Consider other simple actions such as mode changes
             # Handle inefficient democrazy.
             repo.ui.note(_(' %s: multiple bids for merge action:\n') % f)
             for m, l in sorted(bids.items()):
                 for _f, args, msg in l:
                     repo.ui.note('  %s -> %s\n' % (msg, m))
             # Pick random action. TODO: Instead, prompt user when resolving
             m, l = bids.items()[0]
             repo.ui.warn(_(' %s: ambiguous merge - picked %s action\n') %
                          (f, m))
             actions[f] = l[0]
             continue
         repo.ui.note(_('end of auction\n\n'))
 
     _resolvetrivial(repo, wctx, mctx, ancestors[0], actions)
 
     if wctx.rev() is None:
         fractions = _forgetremoved(wctx, mctx, branchmerge)
         actions.update(fractions)
 
     return actions, diverge, renamedelete
 
 def batchremove(repo, actions):
     """apply removes to the working directory
 
     yields tuples for progress updates
     """
     verbose = repo.ui.verbose
     unlink = util.unlinkpath
     wjoin = repo.wjoin
     audit = repo.wvfs.audit
     i = 0
     for f, args, msg in actions:
         repo.ui.debug(" %s: %s -> r\n" % (f, msg))
         if verbose:
             repo.ui.note(_("removing %s\n") % f)
         audit(f)
         try:
             unlink(wjoin(f), ignoremissing=True)
         except OSError as inst:
             repo.ui.warn(_("update failed to remove %s: %s!\n") %
                          (f, inst.strerror))
         if i == 100:
             yield i, f
             i = 0
         i += 1
     if i > 0:
         yield i, f
 
 def batchget(repo, mctx, actions):
     """apply gets to the working directory
 
     mctx is the context to get from
 
     yields tuples for progress updates
     """
     verbose = repo.ui.verbose
     fctx = mctx.filectx
     wwrite = repo.wwrite
     i = 0
     for f, args, msg in actions:
         repo.ui.debug(" %s: %s -> g\n" % (f, msg))
         if verbose:
             repo.ui.note(_("getting %s\n") % f)
         wwrite(f, fctx(f).data(), args[0])
         if i == 100:
             yield i, f
             i = 0
         i += 1
     if i > 0:
         yield i, f
 
 def applyupdates(repo, actions, wctx, mctx, overwrite, labels=None):
     """apply the merge action list to the working directory
 
     wctx is the working copy context
     mctx is the context to be merged into the working copy
 
     Return a tuple of counts (updated, merged, removed, unresolved) that
     describes how many files were affected by the update.
     """
 
     updated, merged, removed, unresolved = 0, 0, 0, 0
     ms = mergestate(repo)
     ms.reset(wctx.p1().node(), mctx.node())
     moves = []
     for m, l in actions.items():
         l.sort()
 
     # prescan for merges
     for f, args, msg in actions['m']:
         f1, f2, fa, move, anc = args
         if f == '.hgsubstate': # merged internally
             continue
         repo.ui.debug(" preserving %s for resolve of %s\n" % (f1, f))
         fcl = wctx[f1]
         fco = mctx[f2]
         actx = repo[anc]
         if fa in actx:
             fca = actx[fa]
         else:
             fca = repo.filectx(f1, fileid=nullrev)
         ms.add(fcl, fco, fca, f)
         if f1 != f and move:
             moves.append(f1)
 
     audit = repo.wvfs.audit
     _updating = _('updating')
     _files = _('files')
     progress = repo.ui.progress
 
     # remove renamed files after safely stored
     for f in moves:
         if os.path.lexists(repo.wjoin(f)):
             repo.ui.debug("removing %s\n" % f)
             audit(f)
             util.unlinkpath(repo.wjoin(f))
 
     numupdates = sum(len(l) for m, l in actions.items() if m != 'k')
 
     if [a for a in actions['r'] if a[0] == '.hgsubstate']:
         subrepo.submerge(repo, wctx, mctx, wctx, overwrite)
 
     # remove in parallel (must come first)
     z = 0
     prog = worker.worker(repo.ui, 0.001, batchremove, (repo,), actions['r'])
     for i, item in prog:
         z += i
         progress(_updating, z, item=item, total=numupdates, unit=_files)
     removed = len(actions['r'])
 
     # get in parallel
     prog = worker.worker(repo.ui, 0.001, batchget, (repo, mctx), actions['g'])
     for i, item in prog:
         z += i
         progress(_updating, z, item=item, total=numupdates, unit=_files)
     updated = len(actions['g'])
 
     if [a for a in actions['g'] if a[0] == '.hgsubstate']:
         subrepo.submerge(repo, wctx, mctx, wctx, overwrite)
 
     # forget (manifest only, just log it) (must come first)
     for f, args, msg in actions['f']:
         repo.ui.debug(" %s: %s -> f\n" % (f, msg))
         z += 1
         progress(_updating, z, item=f, total=numupdates, unit=_files)
 
     # re-add (manifest only, just log it)
     for f, args, msg in actions['a']:
         repo.ui.debug(" %s: %s -> a\n" % (f, msg))
         z += 1
         progress(_updating, z, item=f, total=numupdates, unit=_files)
 
     # keep (noop, just log it)
     for f, args, msg in actions['k']:
         repo.ui.debug(" %s: %s -> k\n" % (f, msg))
         # no progress
 
     # directory rename, move local
     for f, args, msg in actions['dm']:
         repo.ui.debug(" %s: %s -> dm\n" % (f, msg))
         z += 1
         progress(_updating, z, item=f, total=numupdates, unit=_files)
         f0, flags = args
         repo.ui.note(_("moving %s to %s\n") % (f0, f))
         audit(f)
         repo.wwrite(f, wctx.filectx(f0).data(), flags)
         util.unlinkpath(repo.wjoin(f0))
         updated += 1
 
     # local directory rename, get
     for f, args, msg in actions['dg']:
         repo.ui.debug(" %s: %s -> dg\n" % (f, msg))
         z += 1
         progress(_updating, z, item=f, total=numupdates, unit=_files)
         f0, flags = args
         repo.ui.note(_("getting %s to %s\n") % (f0, f))
         repo.wwrite(f, mctx.filectx(f0).data(), flags)
         updated += 1
 
     # exec
     for f, args, msg in actions['e']:
         repo.ui.debug(" %s: %s -> e\n" % (f, msg))
         z += 1
         progress(_updating, z, item=f, total=numupdates, unit=_files)
         flags, = args
         audit(f)
         util.setflags(repo.wjoin(f), 'l' in flags, 'x' in flags)
         updated += 1
 
     mergeactions = actions['m']
     # the ordering is important here -- ms.mergedriver will raise if the merge
     # driver has changed, and we want to be able to bypass it when overwrite is
     # True
     usemergedriver = not overwrite and mergeactions and ms.mergedriver
 
     if usemergedriver:
         ms.commit()
         proceed = driverpreprocess(repo, ms, wctx, labels=labels)
         # the driver might leave some files unresolved
         unresolvedf = set(ms.unresolved())
         if not proceed:
             # XXX setting unresolved to at least 1 is a hack to make sure we
             # error out
             return updated, merged, removed, max(len(unresolvedf), 1)
         newactions = []
         for f, args, msg in mergeactions:
             if f in unresolvedf:
                 newactions.append((f, args, msg))
         mergeactions = newactions
 
     # premerge
     tocomplete = []
     for f, args, msg in actions['m']:
         repo.ui.debug(" %s: %s -> m (premerge)\n" % (f, msg))
         z += 1
         progress(_updating, z, item=f, total=numupdates, unit=_files)
         if f == '.hgsubstate': # subrepo states need updating
             subrepo.submerge(repo, wctx, mctx, wctx.ancestor(mctx),
                              overwrite)
             continue
         audit(f)
         complete, r = ms.preresolve(f, wctx, labels=labels)
         if complete:
             if r is not None and r > 0:
                 unresolved += 1
             else:
                 if r is None:
                     updated += 1
                 else:
                     merged += 1
         else:
             numupdates += 1
             tocomplete.append((f, args, msg))
 
     # merge
     for f, args, msg in tocomplete:
         repo.ui.debug(" %s: %s -> m (merge)\n" % (f, msg))
         z += 1
         progress(_updating, z, item=f, total=numupdates, unit=_files)
         r = ms.resolve(f, wctx, labels=labels)
         if r is not None and r > 0:
             unresolved += 1
         else:
             if r is None:
                 updated += 1
             else:
                 merged += 1
 
     ms.commit()
 
     if usemergedriver and not unresolved and ms.mdstate() != 's':
         if not driverconclude(repo, ms, wctx, labels=labels):
             # XXX setting unresolved to at least 1 is a hack to make sure we
             # error out
             return updated, merged, removed, max(unresolved, 1)
 
         ms.commit()
 
     progress(_updating, None, total=numupdates, unit=_files)
 
     return updated, merged, removed, unresolved
 
 def recordupdates(repo, actions, branchmerge):
     "record merge actions to the dirstate"
     # remove (must come first)
     for f, args, msg in actions['r']:
         if branchmerge:
             repo.dirstate.remove(f)
         else:
             repo.dirstate.drop(f)
 
     # forget (must come first)
     for f, args, msg in actions['f']:
         repo.dirstate.drop(f)
 
     # re-add
     for f, args, msg in actions['a']:
         if not branchmerge:
             repo.dirstate.add(f)
 
     # exec change
     for f, args, msg in actions['e']:
         repo.dirstate.normallookup(f)
 
     # keep
     for f, args, msg in actions['k']:
         pass
 
     # get
     for f, args, msg in actions['g']:
         if branchmerge:
             repo.dirstate.otherparent(f)
         else:
             repo.dirstate.normal(f)
 
     # merge
     for f, args, msg in actions['m']:
         f1, f2, fa, move, anc = args
         if branchmerge:
             # We've done a branch merge, mark this file as merged
             # so that we properly record the merger later
             repo.dirstate.merge(f)
             if f1 != f2: # copy/rename
                 if move:
                     repo.dirstate.remove(f1)
                 if f1 != f:
                     repo.dirstate.copy(f1, f)
                 else:
                     repo.dirstate.copy(f2, f)
         else:
             # We've update-merged a locally modified file, so
             # we set the dirstate to emulate a normal checkout
             # of that file some time in the past. Thus our
             # merge will appear as a normal local file
             # modification.
             if f2 == f: # file not locally copied/moved
                 repo.dirstate.normallookup(f)
             if move:
                 repo.dirstate.drop(f1)
 
     # directory rename, move local
     for f, args, msg in actions['dm']:
         f0, flag = args
         if branchmerge:
             repo.dirstate.add(f)
             repo.dirstate.remove(f0)
             repo.dirstate.copy(f0, f)
         else:
             repo.dirstate.normal(f)
             repo.dirstate.drop(f0)
 
     # directory rename, get
     for f, args, msg in actions['dg']:
         f0, flag = args
         if branchmerge:
             repo.dirstate.add(f)
             repo.dirstate.copy(f0, f)
         else:
             repo.dirstate.normal(f)
 
 def update(repo, node, branchmerge, force, partial, ancestor=None,
            mergeancestor=False, labels=None):
     """
     Perform a merge between the working directory and the given node
 
     node = the node to update to, or None if unspecified
     branchmerge = whether to merge between branches
     force = whether to force branch merging or file overwriting
     partial = a function to filter file lists (dirstate not updated)
     mergeancestor = whether it is merging with an ancestor. If true,
       we should accept the incoming changes for any prompts that occur.
       If false, merging with an ancestor (fast-forward) is only allowed
       between different named branches. This flag is used by rebase extension
       as a temporary fix and should be avoided in general.
 
     The table below shows all the behaviors of the update command
     given the -c and -C or no options, whether the working directory
     is dirty, whether a revision is specified, and the relationship of
     the parent rev to the target rev (linear, on the same named
     branch, or on another named branch).
 
     This logic is tested by test-update-branches.t.
 
     -c  -C  dirty  rev  |  linear      same    cross
      n   n    n     n   |    ok        (1)       x
      n   n    n     y   |    ok        ok       ok
      n   n    y     n   |   merge      (2)      (2)
      n   n    y     y   |   merge      (3)      (3)
      n   y    *     *   |   discard   discard   discard
      y   n    y     *   |    (4)       (4)      (4)
      y   n    n     *   |    ok        ok       ok
      y   y    *     *   |    (5)       (5)      (5)
 
     x = can't happen
     * = don't-care
     1 = abort: not a linear update (merge or update --check to force update)
     2 = abort: uncommitted changes (commit and merge, or update --clean to
                  discard changes)
     3 = abort: uncommitted changes (commit or update --clean to discard changes)
     4 = abort: uncommitted changes (checked in commands.py)
     5 = incompatible options (checked in commands.py)
 
     Return the same tuple as applyupdates().
     """
 
     onode = node
     wlock = repo.wlock()
     try:
         wc = repo[None]
         pl = wc.parents()
         p1 = pl[0]
         pas = [None]
         if ancestor is not None:
             pas = [repo[ancestor]]
 
         if node is None:
             if (repo.ui.configbool('devel', 'all-warnings')
                     or repo.ui.configbool('devel', 'oldapi')):
                 repo.ui.develwarn('update with no target')
             rev, _mark, _act = destutil.destupdate(repo)
             node = repo[rev].node()
 
         overwrite = force and not branchmerge
 
         p2 = repo[node]
         if pas[0] is None:
             if repo.ui.configlist('merge', 'preferancestor', ['*']) == ['*']:
                 cahs = repo.changelog.commonancestorsheads(p1.node(), p2.node())
                 pas = [repo[anc] for anc in (sorted(cahs) or [nullid])]
             else:
                 pas = [p1.ancestor(p2, warn=branchmerge)]
 
         fp1, fp2, xp1, xp2 = p1.node(), p2.node(), str(p1), str(p2)
 
         ### check phase
         if not overwrite and len(pl) > 1:
             raise error.Abort(_("outstanding uncommitted merge"))
         if branchmerge:
             if pas == [p2]:
                 raise error.Abort(_("merging with a working directory ancestor"
                                    " has no effect"))
             elif pas == [p1]:
                 if not mergeancestor and p1.branch() == p2.branch():
                     raise error.Abort(_("nothing to merge"),
                                      hint=_("use 'hg update' "
                                             "or check 'hg heads'"))
             if not force and (wc.files() or wc.deleted()):
                 raise error.Abort(_("uncommitted changes"),
                                  hint=_("use 'hg status' to list changes"))
             for s in sorted(wc.substate):
                 wc.sub(s).bailifchanged()
 
         elif not overwrite:
             if p1 == p2: # no-op update
                 # call the hooks and exit early
                 repo.hook('preupdate', throw=True, parent1=xp2, parent2='')
                 repo.hook('update', parent1=xp2, parent2='', error=0)
                 return 0, 0, 0, 0
 
             if pas not in ([p1], [p2]):  # nonlinear
                 dirty = wc.dirty(missing=True)
                 if dirty or onode is None:
                     # Branching is a bit strange to ensure we do the minimal
                     # amount of call to obsolete.background.
                     foreground = obsolete.foreground(repo, [p1.node()])
                     # note: the <node> variable contains a random identifier
                     if repo[node].node() in foreground:
                         pas = [p1]  # allow updating to successors
                     elif dirty:
                         msg = _("uncommitted changes")
                         if onode is None:
                             hint = _("commit and merge, or update --clean to"
                                      " discard changes")
                         else:
                             hint = _("commit or update --clean to discard"
                                      " changes")
                         raise error.Abort(msg, hint=hint)
                     else:  # node is none
                         msg = _("not a linear update")
                         hint = _("merge or update --check to force update")
                         raise error.Abort(msg, hint=hint)
                 else:
                     # Allow jumping branches if clean and specific rev given
                     pas = [p1]
 
         # deprecated config: merge.followcopies
         followcopies = False
         if overwrite:
             pas = [wc]
         elif pas == [p2]: # backwards
             pas = [wc.p1()]
         elif not branchmerge and not wc.dirty(missing=True):
             pass
         elif pas[0] and repo.ui.configbool('merge', 'followcopies', True):
             followcopies = True
 
         ### calculate phase
         actionbyfile, diverge, renamedelete = calculateupdates(
             repo, wc, p2, pas, branchmerge, force, partial, mergeancestor,
             followcopies)
         # Convert to dictionary-of-lists format
         actions = dict((m, []) for m in 'a f g cd dc r dm dg m e k'.split())
         for f, (m, args, msg) in actionbyfile.iteritems():
             if m not in actions:
                 actions[m] = []
             actions[m].append((f, args, msg))
 
         if not util.checkcase(repo.path):
             # check collision between files only in p2 for clean update
             if (not branchmerge and
                 (force or not wc.dirty(missing=True, branch=False))):
                 _checkcollision(repo, p2.manifest(), None)
             else:
                 _checkcollision(repo, wc.manifest(), actions)
 
         # Prompt and create actions. TODO: Move this towards resolve phase.
         for f, args, msg in sorted(actions['cd']):
             if repo.ui.promptchoice(
                 _("local changed %s which remote deleted\n"
                   "use (c)hanged version or (d)elete?"
                   "$$ &Changed $$ &Delete") % f, 0):
                 actions['r'].append((f, None, "prompt delete"))
             else:
                 actions['a'].append((f, None, "prompt keep"))
         del actions['cd'][:]
 
         for f, args, msg in sorted(actions['dc']):
             flags, = args
             if repo.ui.promptchoice(
                 _("remote changed %s which local deleted\n"
                   "use (c)hanged version or leave (d)eleted?"
                   "$$ &Changed $$ &Deleted") % f, 0) == 0:
                 actions['g'].append((f, (flags,), "prompt recreating"))
         del actions['dc'][:]
 
         ### apply phase
         if not branchmerge: # just jump to the new rev
             fp1, fp2, xp1, xp2 = fp2, nullid, xp2, ''
         if not partial:
             repo.hook('preupdate', throw=True, parent1=xp1, parent2=xp2)
             # note that we're in the middle of an update
             repo.vfs.write('updatestate', p2.hex())
 
         stats = applyupdates(repo, actions, wc, p2, overwrite, labels=labels)
 
         # divergent renames
         for f, fl in sorted(diverge.iteritems()):
             repo.ui.warn(_("note: possible conflict - %s was renamed "
                            "multiple times to:\n") % f)
             for nf in fl:
                 repo.ui.warn(" %s\n" % nf)
 
         # rename and delete
         for f, fl in sorted(renamedelete.iteritems()):
             repo.ui.warn(_("note: possible conflict - %s was deleted "
                            "and renamed to:\n") % f)
             for nf in fl:
                 repo.ui.warn(" %s\n" % nf)
 
         if not partial:
             repo.dirstate.beginparentchange()
             repo.setparents(fp1, fp2)
             recordupdates(repo, actions, branchmerge)
             # update completed, clear state
             util.unlink(repo.join('updatestate'))
 
             if not branchmerge:
                 repo.dirstate.setbranch(p2.branch())
             repo.dirstate.endparentchange()
     finally:
         wlock.release()
 
     if not partial:
         repo.hook('update', parent1=xp1, parent2=xp2, error=stats[3])
     return stats
 
 def graft(repo, ctx, pctx, labels):
     """Do a graft-like merge.
 
     This is a merge where the merge ancestor is chosen such that one
     or more changesets are grafted onto the current changeset. In
     addition to the merge, this fixes up the dirstate to include only
     a single parent and tries to duplicate any renames/copies
     appropriately.
 
     ctx - changeset to rebase
     pctx - merge base, usually ctx.p1()
     labels - merge labels eg ['local', 'graft']
 
     """
     # If we're grafting a descendant onto an ancestor, be sure to pass
     # mergeancestor=True to update. This does two things: 1) allows the merge if
     # the destination is the same as the parent of the ctx (so we can use graft
     # to copy commits), and 2) informs update that the incoming changes are
     # newer than the destination so it doesn't prompt about "remote changed foo
     # which local deleted".
     mergeancestor = repo.changelog.isancestor(repo['.'].node(), ctx.node())
 
     stats = update(repo, ctx.node(), True, True, False, pctx.node(),
                    mergeancestor=mergeancestor, labels=labels)
 
     # drop the second merge parent
     repo.dirstate.beginparentchange()
     repo.setparents(repo['.'].node(), nullid)
     repo.dirstate.write(repo.currenttransaction())
     # fix up dirstate for copies and renames
     copies.duplicatecopies(repo, ctx.rev(), pctx.rev())
     repo.dirstate.endparentchange()
     return stats

mercurial/scmutil.py

@@ -1,1172 +1,1183
 # scmutil.py - Mercurial core utility functions
 #
 #  Copyright 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 i18n import _
 from mercurial.node import wdirrev
 import util, error, osutil, revset, similar, encoding, phases
 import pathutil
 import match as matchmod
 import os, errno, re, glob, tempfile, shutil, stat
 
 if os.name == 'nt':
     import scmwindows as scmplatform
 else:
     import scmposix as scmplatform
 
 systemrcpath = scmplatform.systemrcpath
 userrcpath = scmplatform.userrcpath
 
 class status(tuple):
     '''Named tuple with a list of files per status. The 'deleted', 'unknown'
        and 'ignored' properties are only relevant to the working copy.
     '''
 
     __slots__ = ()
 
     def __new__(cls, modified, added, removed, deleted, unknown, ignored,
                 clean):
         return tuple.__new__(cls, (modified, added, removed, deleted, unknown,
                                    ignored, clean))
 
     @property
     def modified(self):
         '''files that have been modified'''
         return self[0]
 
     @property
     def added(self):
         '''files that have been added'''
         return self[1]
 
     @property
     def removed(self):
         '''files that have been removed'''
         return self[2]
 
     @property
     def deleted(self):
         '''files that are in the dirstate, but have been deleted from the
            working copy (aka "missing")
         '''
         return self[3]
 
     @property
     def unknown(self):
         '''files not in the dirstate that are not ignored'''
         return self[4]
 
     @property
     def ignored(self):
         '''files not in the dirstate that are ignored (by _dirignore())'''
         return self[5]
 
     @property
     def clean(self):
         '''files that have not been modified'''
         return self[6]
 
     def __repr__(self, *args, **kwargs):
         return (('<status modified=%r, added=%r, removed=%r, deleted=%r, '
                  'unknown=%r, ignored=%r, clean=%r>') % self)
 
 def itersubrepos(ctx1, ctx2):
     """find subrepos in ctx1 or ctx2"""
     # Create a (subpath, ctx) mapping where we prefer subpaths from
     # ctx1. The subpaths from ctx2 are important when the .hgsub file
     # has been modified (in ctx2) but not yet committed (in ctx1).
     subpaths = dict.fromkeys(ctx2.substate, ctx2)
     subpaths.update(dict.fromkeys(ctx1.substate, ctx1))
 
     missing = set()
 
     for subpath in ctx2.substate:
         if subpath not in ctx1.substate:
             del subpaths[subpath]
             missing.add(subpath)
 
     for subpath, ctx in sorted(subpaths.iteritems()):
         yield subpath, ctx.sub(subpath)
 
     # Yield an empty subrepo based on ctx1 for anything only in ctx2.  That way,
     # status and diff will have an accurate result when it does
     # 'sub.{status|diff}(rev2)'.  Otherwise, the ctx2 subrepo is compared
     # against itself.
     for subpath in missing:
         yield subpath, ctx2.nullsub(subpath, ctx1)
 
 def nochangesfound(ui, repo, excluded=None):
     '''Report no changes for push/pull, excluded is None or a list of
     nodes excluded from the push/pull.
     '''
     secretlist = []
     if excluded:
         for n in excluded:
             if n not in repo:
                 # discovery should not have included the filtered revision,
                 # we have to explicitly exclude it until discovery is cleanup.
                 continue
             ctx = repo[n]
             if ctx.phase() >= phases.secret and not ctx.extinct():
                 secretlist.append(n)
 
     if secretlist:
         ui.status(_("no changes found (ignored %d secret changesets)\n")
                   % len(secretlist))
     else:
         ui.status(_("no changes found\n"))
 
 def checknewlabel(repo, lbl, kind):
     # Do not use the "kind" parameter in ui output.
     # It makes strings difficult to translate.
     if lbl in ['tip', '.', 'null']:
         raise error.Abort(_("the name '%s' is reserved") % lbl)
     for c in (':', '\0', '\n', '\r'):
         if c in lbl:
             raise error.Abort(_("%r cannot be used in a name") % c)
     try:
         int(lbl)
         raise error.Abort(_("cannot use an integer as a name"))
     except ValueError:
         pass
 
 def checkfilename(f):
     '''Check that the filename f is an acceptable filename for a tracked file'''
     if '\r' in f or '\n' in f:
         raise error.Abort(_("'\\n' and '\\r' disallowed in filenames: %r") % f)
 
 def checkportable(ui, f):
     '''Check if filename f is portable and warn or abort depending on config'''
     checkfilename(f)
     abort, warn = checkportabilityalert(ui)
     if abort or warn:
         msg = util.checkwinfilename(f)
         if msg:
             msg = "%s: %r" % (msg, f)
             if abort:
                 raise error.Abort(msg)
             ui.warn(_("warning: %s\n") % msg)
 
 def checkportabilityalert(ui):
     '''check if the user's config requests nothing, a warning, or abort for
     non-portable filenames'''
     val = ui.config('ui', 'portablefilenames', 'warn')
     lval = val.lower()
     bval = util.parsebool(val)
     abort = os.name == 'nt' or lval == 'abort'
     warn = bval or lval == 'warn'
     if bval is None and not (warn or abort or lval == 'ignore'):
         raise error.ConfigError(
             _("ui.portablefilenames value is invalid ('%s')") % val)
     return abort, warn
 
 class casecollisionauditor(object):
     def __init__(self, ui, abort, dirstate):
         self._ui = ui
         self._abort = abort
         allfiles = '\0'.join(dirstate._map)
         self._loweredfiles = set(encoding.lower(allfiles).split('\0'))
         self._dirstate = dirstate
         # The purpose of _newfiles is so that we don't complain about
         # case collisions if someone were to call this object with the
         # same filename twice.
         self._newfiles = set()
 
     def __call__(self, f):
         if f in self._newfiles:
             return
         fl = encoding.lower(f)
         if fl in self._loweredfiles and f not in self._dirstate:
             msg = _('possible case-folding collision for %s') % f
             if self._abort:
                 raise error.Abort(msg)
             self._ui.warn(_("warning: %s\n") % msg)
         self._loweredfiles.add(fl)
         self._newfiles.add(f)
 
 def filteredhash(repo, maxrev):
     """build hash of filtered revisions in the current repoview.
 
     Multiple caches perform up-to-date validation by checking that the
     tiprev and tipnode stored in the cache file match the current repository.
     However, this is not sufficient for validating repoviews because the set
     of revisions in the view may change without the repository tiprev and
     tipnode changing.
 
     This function hashes all the revs filtered from the view and returns
     that SHA-1 digest.
     """
     cl = repo.changelog
     if not cl.filteredrevs:
         return None
     key = None
     revs = sorted(r for r in cl.filteredrevs if r <= maxrev)
     if revs:
         s = util.sha1()
         for rev in revs:
             s.update('%s;' % rev)
         key = s.digest()
     return key
 
 class abstractvfs(object):
     """Abstract base class; cannot be instantiated"""
 
     def __init__(self, *args, **kwargs):
         '''Prevent instantiation; don't call this from subclasses.'''
         raise NotImplementedError('attempted instantiating ' + str(type(self)))
 
     def tryread(self, path):
         '''gracefully return an empty string for missing files'''
         try:
             return self.read(path)
         except IOError as inst:
             if inst.errno != errno.ENOENT:
                 raise
         return ""
 
     def tryreadlines(self, path, mode='rb'):
         '''gracefully return an empty array for missing files'''
         try:
             return self.readlines(path, mode=mode)
         except IOError as inst:
             if inst.errno != errno.ENOENT:
                 raise
         return []
 
     def open(self, path, mode="r", text=False, atomictemp=False,
              notindexed=False):
         '''Open ``path`` file, which is relative to vfs root.
 
         Newly created directories are marked as "not to be indexed by
         the content indexing service", if ``notindexed`` is specified
         for "write" mode access.
         '''
         self.open = self.__call__
         return self.__call__(path, mode, text, atomictemp, notindexed)
 
     def read(self, path):
         fp = self(path, 'rb')
         try:
             return fp.read()
         finally:
             fp.close()
 
     def readlines(self, path, mode='rb'):
         fp = self(path, mode=mode)
         try:
             return fp.readlines()
         finally:
             fp.close()
 
     def write(self, path, data):
         fp = self(path, 'wb')
         try:
             return fp.write(data)
         finally:
             fp.close()
 
     def writelines(self, path, data, mode='wb', notindexed=False):
         fp = self(path, mode=mode, notindexed=notindexed)
         try:
             return fp.writelines(data)
         finally:
             fp.close()
 
     def append(self, path, data):
         fp = self(path, 'ab')
         try:
             return fp.write(data)
         finally:
             fp.close()
 
     def basename(self, path):
         """return base element of a path (as os.path.basename would do)
 
         This exists to allow handling of strange encoding if needed."""
         return os.path.basename(path)
 
     def chmod(self, path, mode):
         return os.chmod(self.join(path), mode)
 
     def dirname(self, path):
         """return dirname element of a path (as os.path.dirname would do)
 
         This exists to allow handling of strange encoding if needed."""
         return os.path.dirname(path)
 
     def exists(self, path=None):
         return os.path.exists(self.join(path))
 
     def fstat(self, fp):
         return util.fstat(fp)
 
     def isdir(self, path=None):
         return os.path.isdir(self.join(path))
 
     def isfile(self, path=None):
         return os.path.isfile(self.join(path))
 
     def islink(self, path=None):
         return os.path.islink(self.join(path))
 
+    def isfileorlink(self, path=None):
+        '''return whether path is a regular file or a symlink
+
+        Unlike isfile, this doesn't follow symlinks.'''
+        try:
+            st = self.lstat(path)
+        except OSError:
+            return False
+        mode = st.st_mode
+        return stat.S_ISREG(mode) or stat.S_ISLNK(mode)
+
     def reljoin(self, *paths):
         """join various elements of a path together (as os.path.join would do)
 
         The vfs base is not injected so that path stay relative. This exists
         to allow handling of strange encoding if needed."""
         return os.path.join(*paths)
 
     def split(self, path):
         """split top-most element of a path (as os.path.split would do)
 
         This exists to allow handling of strange encoding if needed."""
         return os.path.split(path)
 
     def lexists(self, path=None):
         return os.path.lexists(self.join(path))
 
     def lstat(self, path=None):
         return os.lstat(self.join(path))
 
     def listdir(self, path=None):
         return os.listdir(self.join(path))
 
     def makedir(self, path=None, notindexed=True):
         return util.makedir(self.join(path), notindexed)
 
     def makedirs(self, path=None, mode=None):
         return util.makedirs(self.join(path), mode)
 
     def makelock(self, info, path):
         return util.makelock(info, self.join(path))
 
     def mkdir(self, path=None):
         return os.mkdir(self.join(path))
 
     def mkstemp(self, suffix='', prefix='tmp', dir=None, text=False):
         fd, name = tempfile.mkstemp(suffix=suffix, prefix=prefix,
                                     dir=self.join(dir), text=text)
         dname, fname = util.split(name)
         if dir:
             return fd, os.path.join(dir, fname)
         else:
             return fd, fname
 
     def readdir(self, path=None, stat=None, skip=None):
         return osutil.listdir(self.join(path), stat, skip)
 
     def readlock(self, path):
         return util.readlock(self.join(path))
 
     def rename(self, src, dst):
         return util.rename(self.join(src), self.join(dst))
 
     def readlink(self, path):
         return os.readlink(self.join(path))
 
     def removedirs(self, path=None):
         """Remove a leaf directory and all empty intermediate ones
         """
         return util.removedirs(self.join(path))
 
     def rmtree(self, path=None, ignore_errors=False, forcibly=False):
         """Remove a directory tree recursively
 
         If ``forcibly``, this tries to remove READ-ONLY files, too.
         """
         if forcibly:
             def onerror(function, path, excinfo):
                 if function is not os.remove:
                     raise
                 # read-only files cannot be unlinked under Windows
                 s = os.stat(path)
                 if (s.st_mode & stat.S_IWRITE) != 0:
                     raise
                 os.chmod(path, stat.S_IMODE(s.st_mode) | stat.S_IWRITE)
                 os.remove(path)
         else:
             onerror = None
         return shutil.rmtree(self.join(path),
                              ignore_errors=ignore_errors, onerror=onerror)
 
     def setflags(self, path, l, x):
         return util.setflags(self.join(path), l, x)
 
     def stat(self, path=None):
         return os.stat(self.join(path))
 
     def unlink(self, path=None):
         return util.unlink(self.join(path))
 
     def unlinkpath(self, path=None, ignoremissing=False):
         return util.unlinkpath(self.join(path), ignoremissing)
 
     def utime(self, path=None, t=None):
         return os.utime(self.join(path), t)
 
     def walk(self, path=None, onerror=None):
         """Yield (dirpath, dirs, files) tuple for each directories under path
 
         ``dirpath`` is relative one from the root of this vfs. This
         uses ``os.sep`` as path separator, even you specify POSIX
         style ``path``.
 
         "The root of this vfs" is represented as empty ``dirpath``.
         """
         root = os.path.normpath(self.join(None))
         # when dirpath == root, dirpath[prefixlen:] becomes empty
         # because len(dirpath) < prefixlen.
         prefixlen = len(pathutil.normasprefix(root))
         for dirpath, dirs, files in os.walk(self.join(path), onerror=onerror):
             yield (dirpath[prefixlen:], dirs, files)
 
 class vfs(abstractvfs):
     '''Operate files relative to a base directory
 
     This class is used to hide the details of COW semantics and
     remote file access from higher level code.
     '''
     def __init__(self, base, audit=True, expandpath=False, realpath=False):
         if expandpath:
             base = util.expandpath(base)
         if realpath:
             base = os.path.realpath(base)
         self.base = base
         self._setmustaudit(audit)
         self.createmode = None
         self._trustnlink = None
 
     def _getmustaudit(self):
         return self._audit
 
     def _setmustaudit(self, onoff):
         self._audit = onoff
         if onoff:
             self.audit = pathutil.pathauditor(self.base)
         else:
             self.audit = util.always
 
     mustaudit = property(_getmustaudit, _setmustaudit)
 
     @util.propertycache
     def _cansymlink(self):
         return util.checklink(self.base)
 
     @util.propertycache
     def _chmod(self):
         return util.checkexec(self.base)
 
     def _fixfilemode(self, name):
         if self.createmode is None or not self._chmod:
             return
         os.chmod(name, self.createmode & 0o666)
 
     def __call__(self, path, mode="r", text=False, atomictemp=False,
                  notindexed=False):
         '''Open ``path`` file, which is relative to vfs root.
 
         Newly created directories are marked as "not to be indexed by
         the content indexing service", if ``notindexed`` is specified
         for "write" mode access.
         '''
         if self._audit:
             r = util.checkosfilename(path)
             if r:
                 raise error.Abort("%s: %r" % (r, path))
         self.audit(path)
         f = self.join(path)
 
         if not text and "b" not in mode:
             mode += "b" # for that other OS
 
         nlink = -1
         if mode not in ('r', 'rb'):
             dirname, basename = util.split(f)
             # If basename is empty, then the path is malformed because it points
             # to a directory. Let the posixfile() call below raise IOError.
             if basename:
                 if atomictemp:
                     util.ensuredirs(dirname, self.createmode, notindexed)
                     return util.atomictempfile(f, mode, self.createmode)
                 try:
                     if 'w' in mode:
                         util.unlink(f)
                         nlink = 0
                     else:
                         # nlinks() may behave differently for files on Windows
                         # shares if the file is open.
                         fd = util.posixfile(f)
                         nlink = util.nlinks(f)
                         if nlink < 1:
                             nlink = 2 # force mktempcopy (issue1922)
                         fd.close()
                 except (OSError, IOError) as e:
                     if e.errno != errno.ENOENT:
                         raise
                     nlink = 0
                     util.ensuredirs(dirname, self.createmode, notindexed)
                 if nlink > 0:
                     if self._trustnlink is None:
                         self._trustnlink = nlink > 1 or util.checknlink(f)
                     if nlink > 1 or not self._trustnlink:
                         util.rename(util.mktempcopy(f), f)
         fp = util.posixfile(f, mode)
         if nlink == 0:
             self._fixfilemode(f)
         return fp
 
     def symlink(self, src, dst):
         self.audit(dst)
         linkname = self.join(dst)
         try:
             os.unlink(linkname)
         except OSError:
             pass
 
         util.ensuredirs(os.path.dirname(linkname), self.createmode)
 
         if self._cansymlink:
             try:
                 os.symlink(src, linkname)
             except OSError as err:
                 raise OSError(err.errno, _('could not symlink to %r: %s') %
                               (src, err.strerror), linkname)
         else:
             self.write(dst, src)
 
     def join(self, path, *insidef):
         if path:
             return os.path.join(self.base, path, *insidef)
         else:
             return self.base
 
 opener = vfs
 
 class auditvfs(object):
     def __init__(self, vfs):
         self.vfs = vfs
 
     def _getmustaudit(self):
         return self.vfs.mustaudit
 
     def _setmustaudit(self, onoff):
         self.vfs.mustaudit = onoff
 
     mustaudit = property(_getmustaudit, _setmustaudit)
 
 class filtervfs(abstractvfs, auditvfs):
     '''Wrapper vfs for filtering filenames with a function.'''
 
     def __init__(self, vfs, filter):
         auditvfs.__init__(self, vfs)
         self._filter = filter
 
     def __call__(self, path, *args, **kwargs):
         return self.vfs(self._filter(path), *args, **kwargs)
 
     def join(self, path, *insidef):
         if path:
             return self.vfs.join(self._filter(self.vfs.reljoin(path, *insidef)))
         else:
             return self.vfs.join(path)
 
 filteropener = filtervfs
 
 class readonlyvfs(abstractvfs, auditvfs):
     '''Wrapper vfs preventing any writing.'''
 
     def __init__(self, vfs):
         auditvfs.__init__(self, vfs)
 
     def __call__(self, path, mode='r', *args, **kw):
         if mode not in ('r', 'rb'):
             raise error.Abort('this vfs is read only')
         return self.vfs(path, mode, *args, **kw)
 
     def join(self, path, *insidef):
         return self.vfs.join(path, *insidef)
 
 def walkrepos(path, followsym=False, seen_dirs=None, recurse=False):
     '''yield every hg repository under path, always recursively.
     The recurse flag will only control recursion into repo working dirs'''
     def errhandler(err):
         if err.filename == path:
             raise err
     samestat = getattr(os.path, 'samestat', None)
     if followsym and samestat is not None:
         def adddir(dirlst, dirname):
             match = False
             dirstat = os.stat(dirname)
             for lstdirstat in dirlst:
                 if samestat(dirstat, lstdirstat):
                     match = True
                     break
             if not match:
                 dirlst.append(dirstat)
             return not match
     else:
         followsym = False
 
     if (seen_dirs is None) and followsym:
         seen_dirs = []
         adddir(seen_dirs, path)
     for root, dirs, files in os.walk(path, topdown=True, onerror=errhandler):
         dirs.sort()
         if '.hg' in dirs:
             yield root # found a repository
             qroot = os.path.join(root, '.hg', 'patches')
             if os.path.isdir(os.path.join(qroot, '.hg')):
                 yield qroot # we have a patch queue repo here
             if recurse:
                 # avoid recursing inside the .hg directory
                 dirs.remove('.hg')
             else:
                 dirs[:] = [] # don't descend further
         elif followsym:
             newdirs = []
             for d in dirs:
                 fname = os.path.join(root, d)
                 if adddir(seen_dirs, fname):
                     if os.path.islink(fname):
                         for hgname in walkrepos(fname, True, seen_dirs):
                             yield hgname
                     else:
                         newdirs.append(d)
             dirs[:] = newdirs
 
 def osrcpath():
     '''return default os-specific hgrc search path'''
     path = []
     defaultpath = os.path.join(util.datapath, 'default.d')
     if os.path.isdir(defaultpath):
         for f, kind in osutil.listdir(defaultpath):
             if f.endswith('.rc'):
                 path.append(os.path.join(defaultpath, f))
     path.extend(systemrcpath())
     path.extend(userrcpath())
     path = [os.path.normpath(f) for f in path]
     return path
 
 _rcpath = None
 
 def rcpath():
     '''return hgrc search path. if env var HGRCPATH is set, use it.
     for each item in path, if directory, use files ending in .rc,
     else use item.
     make HGRCPATH empty to only look in .hg/hgrc of current repo.
     if no HGRCPATH, use default os-specific path.'''
     global _rcpath
     if _rcpath is None:
         if 'HGRCPATH' in os.environ:
             _rcpath = []
             for p in os.environ['HGRCPATH'].split(os.pathsep):
                 if not p:
                     continue
                 p = util.expandpath(p)
                 if os.path.isdir(p):
                     for f, kind in osutil.listdir(p):
                         if f.endswith('.rc'):
                             _rcpath.append(os.path.join(p, f))
                 else:
                     _rcpath.append(p)
         else:
             _rcpath = osrcpath()
     return _rcpath
 
 def intrev(rev):
     """Return integer for a given revision that can be used in comparison or
     arithmetic operation"""
     if rev is None:
         return wdirrev
     return rev
 
 def revsingle(repo, revspec, default='.'):
     if not revspec and revspec != 0:
         return repo[default]
 
     l = revrange(repo, [revspec])
     if not l:
         raise error.Abort(_('empty revision set'))
     return repo[l.last()]
 
 def _pairspec(revspec):
     tree = revset.parse(revspec)
     tree = revset.optimize(tree, True)[1]  # fix up "x^:y" -> "(x^):y"
     return tree and tree[0] in ('range', 'rangepre', 'rangepost', 'rangeall')
 
 def revpair(repo, revs):
     if not revs:
         return repo.dirstate.p1(), None
 
     l = revrange(repo, revs)
 
     if not l:
         first = second = None
     elif l.isascending():
         first = l.min()
         second = l.max()
     elif l.isdescending():
         first = l.max()
         second = l.min()
     else:
         first = l.first()
         second = l.last()
 
     if first is None:
         raise error.Abort(_('empty revision range'))
     if (first == second and len(revs) >= 2
         and not all(revrange(repo, [r]) for r in revs)):
         raise error.Abort(_('empty revision on one side of range'))
 
     # if top-level is range expression, the result must always be a pair
     if first == second and len(revs) == 1 and not _pairspec(revs[0]):
         return repo.lookup(first), None
 
     return repo.lookup(first), repo.lookup(second)
 
 def revrange(repo, revs):
     """Yield revision as strings from a list of revision specifications."""
     allspecs = []
     for spec in revs:
         if isinstance(spec, int):
             spec = revset.formatspec('rev(%d)', spec)
         allspecs.append(spec)
     m = revset.matchany(repo.ui, allspecs, repo)
     return m(repo)
 
 def meaningfulparents(repo, ctx):
     """Return list of meaningful (or all if debug) parentrevs for rev.
 
     For merges (two non-nullrev revisions) both parents are meaningful.
     Otherwise the first parent revision is considered meaningful if it
     is not the preceding revision.
     """
     parents = ctx.parents()
     if len(parents) > 1:
         return parents
     if repo.ui.debugflag:
         return [parents[0], repo['null']]
     if parents[0].rev() >= intrev(ctx.rev()) - 1:
         return []
     return parents
 
 def expandpats(pats):
     '''Expand bare globs when running on windows.
     On posix we assume it already has already been done by sh.'''
     if not util.expandglobs:
         return list(pats)
     ret = []
     for kindpat in pats:
         kind, pat = matchmod._patsplit(kindpat, None)
         if kind is None:
             try:
                 globbed = glob.glob(pat)
             except re.error:
                 globbed = [pat]
             if globbed:
                 ret.extend(globbed)
                 continue
         ret.append(kindpat)
     return ret
 
 def matchandpats(ctx, pats=(), opts=None, globbed=False, default='relpath',
                  badfn=None):
     '''Return a matcher and the patterns that were used.
     The matcher will warn about bad matches, unless an alternate badfn callback
     is provided.'''
     if pats == ("",):
         pats = []
     if opts is None:
         opts = {}
     if not globbed and default == 'relpath':
         pats = expandpats(pats or [])
 
     def bad(f, msg):
         ctx.repo().ui.warn("%s: %s\n" % (m.rel(f), msg))
 
     if badfn is None:
         badfn = bad
 
     m = ctx.match(pats, opts.get('include'), opts.get('exclude'),
                   default, listsubrepos=opts.get('subrepos'), badfn=badfn)
 
     if m.always():
         pats = []
     return m, pats
 
 def match(ctx, pats=(), opts=None, globbed=False, default='relpath',
           badfn=None):
     '''Return a matcher that will warn about bad matches.'''
     return matchandpats(ctx, pats, opts, globbed, default, badfn=badfn)[0]
 
 def matchall(repo):
     '''Return a matcher that will efficiently match everything.'''
     return matchmod.always(repo.root, repo.getcwd())
 
 def matchfiles(repo, files, badfn=None):
     '''Return a matcher that will efficiently match exactly these files.'''
     return matchmod.exact(repo.root, repo.getcwd(), files, badfn=badfn)
 
 def addremove(repo, matcher, prefix, opts=None, dry_run=None, similarity=None):
     if opts is None:
         opts = {}
     m = matcher
     if dry_run is None:
         dry_run = opts.get('dry_run')
     if similarity is None:
         similarity = float(opts.get('similarity') or 0)
 
     ret = 0
     join = lambda f: os.path.join(prefix, f)
 
     def matchessubrepo(matcher, subpath):
         if matcher.exact(subpath):
             return True
         for f in matcher.files():
             if f.startswith(subpath):
                 return True
         return False
 
     wctx = repo[None]
     for subpath in sorted(wctx.substate):
         if opts.get('subrepos') or matchessubrepo(m, subpath):
             sub = wctx.sub(subpath)
             try:
                 submatch = matchmod.narrowmatcher(subpath, m)
                 if sub.addremove(submatch, prefix, opts, dry_run, similarity):
                     ret = 1
             except error.LookupError:
                 repo.ui.status(_("skipping missing subrepository: %s\n")
                                  % join(subpath))
 
     rejected = []
     def badfn(f, msg):
         if f in m.files():
             m.bad(f, msg)
         rejected.append(f)
 
     badmatch = matchmod.badmatch(m, badfn)
     added, unknown, deleted, removed, forgotten = _interestingfiles(repo,
                                                                     badmatch)
 
     unknownset = set(unknown + forgotten)
     toprint = unknownset.copy()
     toprint.update(deleted)
     for abs in sorted(toprint):
         if repo.ui.verbose or not m.exact(abs):
             if abs in unknownset:
                 status = _('adding %s\n') % m.uipath(abs)
             else:
                 status = _('removing %s\n') % m.uipath(abs)
             repo.ui.status(status)
 
     renames = _findrenames(repo, m, added + unknown, removed + deleted,
                            similarity)
 
     if not dry_run:
         _markchanges(repo, unknown + forgotten, deleted, renames)
 
     for f in rejected:
         if f in m.files():
             return 1
     return ret
 
 def marktouched(repo, files, similarity=0.0):
     '''Assert that files have somehow been operated upon. files are relative to
     the repo root.'''
     m = matchfiles(repo, files, badfn=lambda x, y: rejected.append(x))
     rejected = []
 
     added, unknown, deleted, removed, forgotten = _interestingfiles(repo, m)
 
     if repo.ui.verbose:
         unknownset = set(unknown + forgotten)
         toprint = unknownset.copy()
         toprint.update(deleted)
         for abs in sorted(toprint):
             if abs in unknownset:
                 status = _('adding %s\n') % abs
             else:
                 status = _('removing %s\n') % abs
             repo.ui.status(status)
 
     renames = _findrenames(repo, m, added + unknown, removed + deleted,
                            similarity)
 
     _markchanges(repo, unknown + forgotten, deleted, renames)
 
     for f in rejected:
         if f in m.files():
             return 1
     return 0
 
 def _interestingfiles(repo, matcher):
     '''Walk dirstate with matcher, looking for files that addremove would care
     about.
 
     This is different from dirstate.status because it doesn't care about
     whether files are modified or clean.'''
     added, unknown, deleted, removed, forgotten = [], [], [], [], []
     audit_path = pathutil.pathauditor(repo.root)
 
     ctx = repo[None]
     dirstate = repo.dirstate
     walkresults = dirstate.walk(matcher, sorted(ctx.substate), True, False,
                                 full=False)
     for abs, st in walkresults.iteritems():
         dstate = dirstate[abs]
         if dstate == '?' and audit_path.check(abs):
             unknown.append(abs)
         elif dstate != 'r' and not st:
             deleted.append(abs)
         elif dstate == 'r' and st:
             forgotten.append(abs)
         # for finding renames
         elif dstate == 'r' and not st:
             removed.append(abs)
         elif dstate == 'a':
             added.append(abs)
 
     return added, unknown, deleted, removed, forgotten
 
 def _findrenames(repo, matcher, added, removed, similarity):
     '''Find renames from removed files to added ones.'''
     renames = {}
     if similarity > 0:
         for old, new, score in similar.findrenames(repo, added, removed,
                                                    similarity):
             if (repo.ui.verbose or not matcher.exact(old)
                 or not matcher.exact(new)):
                 repo.ui.status(_('recording removal of %s as rename to %s '
                                  '(%d%% similar)\n') %
                                (matcher.rel(old), matcher.rel(new),
                                 score * 100))
             renames[new] = old
     return renames
 
 def _markchanges(repo, unknown, deleted, renames):
     '''Marks the files in unknown as added, the files in deleted as removed,
     and the files in renames as copied.'''
     wctx = repo[None]
     wlock = repo.wlock()
     try:
         wctx.forget(deleted)
         wctx.add(unknown)
         for new, old in renames.iteritems():
             wctx.copy(old, new)
     finally:
         wlock.release()
 
 def dirstatecopy(ui, repo, wctx, src, dst, dryrun=False, cwd=None):
     """Update the dirstate to reflect the intent of copying src to dst. For
     different reasons it might not end with dst being marked as copied from src.
     """
     origsrc = repo.dirstate.copied(src) or src
     if dst == origsrc: # copying back a copy?
         if repo.dirstate[dst] not in 'mn' and not dryrun:
             repo.dirstate.normallookup(dst)
     else:
         if repo.dirstate[origsrc] == 'a' and origsrc == src:
             if not ui.quiet:
                 ui.warn(_("%s has not been committed yet, so no copy "
                           "data will be stored for %s.\n")
                         % (repo.pathto(origsrc, cwd), repo.pathto(dst, cwd)))
             if repo.dirstate[dst] in '?r' and not dryrun:
                 wctx.add([dst])
         elif not dryrun:
             wctx.copy(origsrc, dst)
 
 def readrequires(opener, supported):
     '''Reads and parses .hg/requires and checks if all entries found
     are in the list of supported features.'''
     requirements = set(opener.read("requires").splitlines())
     missings = []
     for r in requirements:
         if r not in supported:
             if not r or not r[0].isalnum():
                 raise error.RequirementError(_(".hg/requires file is corrupt"))
             missings.append(r)
     missings.sort()
     if missings:
         raise error.RequirementError(
             _("repository requires features unknown to this Mercurial: %s")
             % " ".join(missings),
             hint=_("see https://mercurial-scm.org/wiki/MissingRequirement"
                    " for more information"))
     return requirements
 
 def writerequires(opener, requirements):
     reqfile = opener("requires", "w")
     for r in sorted(requirements):
         reqfile.write("%s\n" % r)
     reqfile.close()
 
 class filecachesubentry(object):
     def __init__(self, path, stat):
         self.path = path
         self.cachestat = None
         self._cacheable = None
 
         if stat:
             self.cachestat = filecachesubentry.stat(self.path)
 
             if self.cachestat:
                 self._cacheable = self.cachestat.cacheable()
             else:
                 # None means we don't know yet
                 self._cacheable = None
 
     def refresh(self):
         if self.cacheable():
             self.cachestat = filecachesubentry.stat(self.path)
 
     def cacheable(self):
         if self._cacheable is not None:
             return self._cacheable
 
         # we don't know yet, assume it is for now
         return True
 
     def changed(self):
         # no point in going further if we can't cache it
         if not self.cacheable():
             return True
 
         newstat = filecachesubentry.stat(self.path)
 
         # we may not know if it's cacheable yet, check again now
         if newstat and self._cacheable is None:
             self._cacheable = newstat.cacheable()
 
             # check again
             if not self._cacheable:
                 return True
 
         if self.cachestat != newstat:
             self.cachestat = newstat
             return True
         else:
             return False
 
     @staticmethod
     def stat(path):
         try:
             return util.cachestat(path)
         except OSError as e:
             if e.errno != errno.ENOENT:
                 raise
 
 class filecacheentry(object):
     def __init__(self, paths, stat=True):
         self._entries = []
         for path in paths:
             self._entries.append(filecachesubentry(path, stat))
 
     def changed(self):
         '''true if any entry has changed'''
         for entry in self._entries:
             if entry.changed():
                 return True
         return False
 
     def refresh(self):
         for entry in self._entries:
             entry.refresh()
 
 class filecache(object):
     '''A property like decorator that tracks files under .hg/ for updates.
 
     Records stat info when called in _filecache.
 
     On subsequent calls, compares old stat info with new info, and recreates the
     object when any of the files changes, updating the new stat info in
     _filecache.
 
     Mercurial either atomic renames or appends for files under .hg,
     so to ensure the cache is reliable we need the filesystem to be able
     to tell us if a file has been replaced. If it can't, we fallback to
     recreating the object on every call (essentially the same behavior as
     propertycache).
 
     '''
     def __init__(self, *paths):
         self.paths = paths
 
     def join(self, obj, fname):
         """Used to compute the runtime path of a cached file.
 
         Users should subclass filecache and provide their own version of this
         function to call the appropriate join function on 'obj' (an instance
         of the class that its member function was decorated).
         """
         return obj.join(fname)
 
     def __call__(self, func):
         self.func = func
         self.name = func.__name__
         return self
 
     def __get__(self, obj, type=None):
         # do we need to check if the file changed?
         if self.name in obj.__dict__:
             assert self.name in obj._filecache, self.name
             return obj.__dict__[self.name]
 
         entry = obj._filecache.get(self.name)
 
         if entry:
             if entry.changed():
                 entry.obj = self.func(obj)
         else:
             paths = [self.join(obj, path) for path in self.paths]
 
             # We stat -before- creating the object so our cache doesn't lie if
             # a writer modified between the time we read and stat
             entry = filecacheentry(paths, True)
             entry.obj = self.func(obj)
 
             obj._filecache[self.name] = entry
 
         obj.__dict__[self.name] = entry.obj
         return entry.obj
 
     def __set__(self, obj, value):
         if self.name not in obj._filecache:
             # we add an entry for the missing value because X in __dict__
             # implies X in _filecache
             paths = [self.join(obj, path) for path in self.paths]
             ce = filecacheentry(paths, False)
             obj._filecache[self.name] = ce
         else:
             ce = obj._filecache[self.name]
 
         ce.obj = value # update cached copy
         obj.__dict__[self.name] = value # update copy returned by obj.x
 
     def __delete__(self, obj):
         try:
             del obj.__dict__[self.name]
         except KeyError:
             raise AttributeError(self.name)
 
 def _locksub(repo, lock, envvar, cmd, environ=None, *args, **kwargs):
     if lock is None:
         raise error.LockInheritanceContractViolation(
             'lock can only be inherited while held')
     if environ is None:
         environ = {}
     with lock.inherit() as locker:
         environ[envvar] = locker
         return repo.ui.system(cmd, environ=environ, *args, **kwargs)
 
 def wlocksub(repo, cmd, *args, **kwargs):
     """run cmd as a subprocess that allows inheriting repo's wlock
 
     This can only be called while the wlock is held. This takes all the
     arguments that ui.system does, and returns the exit code of the
     subprocess."""
     return _locksub(repo, repo.currentwlock(), 'HG_WLOCK_LOCKER', cmd, *args,
                     **kwargs)

tests/test-merge1.t

@@ -1,296 +1,318
   $ cat <<EOF > merge
   > import sys, os
   > 
   > try:
   >     import msvcrt
   >     msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY)
   >     msvcrt.setmode(sys.stderr.fileno(), os.O_BINARY)
   > except ImportError:
   >     pass
   > 
   > print "merging for", os.path.basename(sys.argv[1])
   > EOF
   $ HGMERGE="python ../merge"; export HGMERGE
 
   $ hg init t
   $ cd t
   $ echo This is file a1 > a
   $ hg add a
   $ hg commit -m "commit #0"
   $ echo This is file b1 > b
   $ hg add b
   $ hg commit -m "commit #1"
 
   $ hg update 0
   0 files updated, 0 files merged, 1 files removed, 0 files unresolved
 
 Test interrupted updates by exploiting our non-handling of directory collisions
 
   $ mkdir b
   $ hg up
   abort: *: '$TESTTMP/t/b' (glob)
   [255]
   $ hg ci
   abort: last update was interrupted
   (use 'hg update' to get a consistent checkout)
   [255]
   $ hg sum
   parent: 0:538afb845929 
    commit #0
   branch: default
   commit: (interrupted update)
   update: 1 new changesets (update)
   phases: 2 draft
   $ rmdir b
   $ hg up
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ hg sum
   parent: 1:b8bb4a988f25 tip
    commit #1
   branch: default
   commit: (clean)
   update: (current)
   phases: 2 draft
 
 Prepare a basic merge
 
   $ hg up 0
   0 files updated, 0 files merged, 1 files removed, 0 files unresolved
   $ echo This is file c1 > c
   $ hg add c
   $ hg commit -m "commit #2"
   created new head
   $ echo This is file b1 > b
 no merges expected
   $ hg merge -P 1
   changeset:   1:b8bb4a988f25
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   summary:     commit #1
   
   $ hg merge 1
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   (branch merge, don't forget to commit)
   $ hg diff --nodates
   diff -r 49035e18a8e6 b
   --- /dev/null
   +++ b/b
   @@ -0,0 +1,1 @@
   +This is file b1
   $ hg status
   M b
   $ cd ..; rm -r t
 
   $ hg init t
   $ cd t
   $ echo This is file a1 > a
   $ hg add a
   $ hg commit -m "commit #0"
   $ echo This is file b1 > b
   $ hg add b
   $ hg commit -m "commit #1"
 
   $ hg update 0
   0 files updated, 0 files merged, 1 files removed, 0 files unresolved
   $ echo This is file c1 > c
   $ hg add c
   $ hg commit -m "commit #2"
   created new head
   $ echo This is file b2 > b
 merge should fail
   $ hg merge 1
   b: untracked file differs
   abort: untracked files in working directory differ from files in requested revision
   [255]
+
+#if symlink
+symlinks to directories should be treated as regular files (issue5027)
+  $ rm b
+  $ ln -s 'This is file b2' b
+  $ hg merge 1
+  b: untracked file differs
+  abort: untracked files in working directory differ from files in requested revision
+  [255]
+symlinks shouldn't be followed
+  $ rm b
+  $ echo This is file b1 > .hg/b
+  $ ln -s .hg/b b
+  $ hg merge 1
+  b: untracked file differs
+  abort: untracked files in working directory differ from files in requested revision
+  [255]
+
+  $ rm b
+  $ echo This is file b2 > b
+#endif
+
 merge of b expected
   $ hg merge -f 1
   merging b
   merging for b
   0 files updated, 1 files merged, 0 files removed, 0 files unresolved
   (branch merge, don't forget to commit)
   $ hg diff --nodates
   diff -r 49035e18a8e6 b
   --- /dev/null
   +++ b/b
   @@ -0,0 +1,1 @@
   +This is file b2
   $ hg status
   M b
   $ cd ..; rm -r t
 
   $ hg init t
   $ cd t
   $ echo This is file a1 > a
   $ hg add a
   $ hg commit -m "commit #0"
   $ echo This is file b1 > b
   $ hg add b
   $ hg commit -m "commit #1"
   $ echo This is file b22 > b
   $ hg commit -m "commit #2"
   $ hg update 1
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ echo This is file c1 > c
   $ hg add c
   $ hg commit -m "commit #3"
   created new head
 
 Contents of b should be "this is file b1"
   $ cat b
   This is file b1
 
   $ echo This is file b22 > b
 merge fails
   $ hg merge 2
   abort: uncommitted changes
   (use 'hg status' to list changes)
   [255]
 merge expected!
   $ hg merge -f 2
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   (branch merge, don't forget to commit)
   $ hg diff --nodates
   diff -r 85de557015a8 b
   --- a/b
   +++ b/b
   @@ -1,1 +1,1 @@
   -This is file b1
   +This is file b22
   $ hg status
   M b
   $ cd ..; rm -r t
 
   $ hg init t
   $ cd t
   $ echo This is file a1 > a
   $ hg add a
   $ hg commit -m "commit #0"
   $ echo This is file b1 > b
   $ hg add b
   $ hg commit -m "commit #1"
   $ echo This is file b22 > b
   $ hg commit -m "commit #2"
   $ hg update 1
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ echo This is file c1 > c
   $ hg add c
   $ hg commit -m "commit #3"
   created new head
   $ echo This is file b33 > b
 merge of b should fail
   $ hg merge 2
   abort: uncommitted changes
   (use 'hg status' to list changes)
   [255]
 merge of b expected
   $ hg merge -f 2
   merging b
   merging for b
   0 files updated, 1 files merged, 0 files removed, 0 files unresolved
   (branch merge, don't forget to commit)
   $ hg diff --nodates
   diff -r 85de557015a8 b
   --- a/b
   +++ b/b
   @@ -1,1 +1,1 @@
   -This is file b1
   +This is file b33
   $ hg status
   M b
 
 Test for issue2364
 
   $ hg up -qC .
   $ hg rm b
   $ hg ci -md
   $ hg revert -r -2 b
   $ hg up -q -- -2
 
 Test that updated files are treated as "modified", when
 'merge.update()' is aborted before 'merge.recordupdates()' (= parents
 aren't changed), even if none of mode, size and timestamp of them
 isn't changed on the filesystem (see also issue4583).
 
   $ cat > $TESTTMP/abort.py <<EOF
   > # emulate aborting before "recordupdates()". in this case, files
   > # are changed without updating dirstate
   > from mercurial import extensions, merge, error
   > def applyupdates(orig, *args, **kwargs):
   >     orig(*args, **kwargs)
   >     raise error.Abort('intentional aborting')
   > def extsetup(ui):
   >     extensions.wrapfunction(merge, "applyupdates", applyupdates)
   > EOF
 
   $ cat >> .hg/hgrc <<EOF
   > [fakedirstatewritetime]
   > # emulate invoking dirstate.write() via repo.status()
   > # at 2000-01-01 00:00
   > fakenow = 200001010000
   > EOF
 
 (file gotten from other revision)
 
   $ hg update -q -C 2
   $ echo 'THIS IS FILE B5' > b
   $ hg commit -m 'commit #5'
 
   $ hg update -q -C 3
   $ cat b
   This is file b1
   $ touch -t 200001010000 b
   $ hg debugrebuildstate
 
   $ cat >> .hg/hgrc <<EOF
   > [extensions]
   > fakedirstatewritetime = $TESTDIR/fakedirstatewritetime.py
   > abort = $TESTTMP/abort.py
   > EOF
   $ hg merge 5
   abort: intentional aborting
   [255]
   $ cat >> .hg/hgrc <<EOF
   > [extensions]
   > fakedirstatewritetime = !
   > abort = !
   > EOF
 
   $ cat b
   THIS IS FILE B5
   $ touch -t 200001010000 b
   $ hg status -A b
   M b
 
 (file merged from other revision)
 
   $ hg update -q -C 3
   $ echo 'this is file b6' > b
   $ hg commit -m 'commit #6'
   created new head
 
   $ cat b
   this is file b6
   $ touch -t 200001010000 b
   $ hg debugrebuildstate
 
   $ cat >> .hg/hgrc <<EOF
   > [extensions]
   > fakedirstatewritetime = $TESTDIR/fakedirstatewritetime.py
   > abort = $TESTTMP/abort.py
   > EOF
   $ hg merge --tool internal:other 5
   abort: intentional aborting
   [255]
   $ cat >> .hg/hgrc <<EOF
   > [extensions]
   > fakedirstatewritetime = !
   > abort = !
   > EOF
 
   $ cat b
   THIS IS FILE B5
   $ touch -t 200001010000 b
   $ hg status -A b
   M b
 
   $ cd ..