sidedatacopies: read rename information from sidedata

Repository using the new format now use changeset centric algorithm and read the
copies information from the changelog sidedata.

Differential Revision: https://phab.mercurial-scm.org/D6953

mercurial/changelog.py

@@ -1,754 +1,766 b''
 # changelog.py - changelog class for mercurial
 #
 # Copyright 2005-2007 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 from .i18n import _
 from .node import (
     bin,
     hex,
     nullid,
 )
 from .thirdparty import attr
 
 from . import (
     encoding,
     error,
     pycompat,
     revlog,
     util,
 )
 from .utils import (
     dateutil,
     stringutil,
 )
 
 from .revlogutils import sidedata as sidedatamod
 
 _defaultextra = {b'branch': b'default'}
 
 
 def _string_escape(text):
     """
     >>> from .pycompat import bytechr as chr
     >>> d = {b'nl': chr(10), b'bs': chr(92), b'cr': chr(13), b'nul': chr(0)}
     >>> s = b"ab%(nl)scd%(bs)s%(bs)sn%(nul)s12ab%(cr)scd%(bs)s%(nl)s" % d
     >>> s
     'ab\\ncd\\\\\\\\n\\x0012ab\\rcd\\\\\\n'
     >>> res = _string_escape(s)
     >>> s == _string_unescape(res)
     True
     """
     # subset of the string_escape codec
     text = (
         text.replace(b'\\', b'\\\\')
         .replace(b'\n', b'\\n')
         .replace(b'\r', b'\\r')
     )
     return text.replace(b'\0', b'\\0')
 
 
 def _string_unescape(text):
     if b'\\0' in text:
         # fix up \0 without getting into trouble with \\0
         text = text.replace(b'\\\\', b'\\\\\n')
         text = text.replace(b'\\0', b'\0')
         text = text.replace(b'\n', b'')
     return stringutil.unescapestr(text)
 
 
 def decodeextra(text):
     """
     >>> from .pycompat import bytechr as chr
     >>> sorted(decodeextra(encodeextra({b'foo': b'bar', b'baz': chr(0) + b'2'})
     ...                    ).items())
     [('baz', '\\x002'), ('branch', 'default'), ('foo', 'bar')]
     >>> sorted(decodeextra(encodeextra({b'foo': b'bar',
     ...                                 b'baz': chr(92) + chr(0) + b'2'})
     ...                    ).items())
     [('baz', '\\\\\\x002'), ('branch', 'default'), ('foo', 'bar')]
     """
     extra = _defaultextra.copy()
     for l in text.split(b'\0'):
         if l:
             k, v = _string_unescape(l).split(b':', 1)
             extra[k] = v
     return extra
 
 
 def encodeextra(d):
     # keys must be sorted to produce a deterministic changelog entry
     items = [
         _string_escape(b'%s:%s' % (k, pycompat.bytestr(d[k])))
         for k in sorted(d)
     ]
     return b"\0".join(items)
 
 
 def encodecopies(files, copies):
     items = []
     for i, dst in enumerate(files):
         if dst in copies:
             items.append(b'%d\0%s' % (i, copies[dst]))
     if len(items) != len(copies):
         raise error.ProgrammingError(
             b'some copy targets missing from file list'
         )
     return b"\n".join(items)
 
 
 def decodecopies(files, data):
     try:
         copies = {}
         if not data:
             return copies
         for l in data.split(b'\n'):
             strindex, src = l.split(b'\0')
             i = int(strindex)
             dst = files[i]
             copies[dst] = src
         return copies
     except (ValueError, IndexError):
         # Perhaps someone had chosen the same key name (e.g. "p1copies") and
         # used different syntax for the value.
         return None
 
 
 def encodefileindices(files, subset):
     subset = set(subset)
     indices = []
     for i, f in enumerate(files):
         if f in subset:
             indices.append(b'%d' % i)
     return b'\n'.join(indices)
 
 
 def decodefileindices(files, data):
     try:
         subset = []
         if not data:
             return subset
         for strindex in data.split(b'\n'):
             i = int(strindex)
             if i < 0 or i >= len(files):
                 return None
             subset.append(files[i])
         return subset
     except (ValueError, IndexError):
         # Perhaps someone had chosen the same key name (e.g. "added") and
         # used different syntax for the value.
         return None
 
 
 def stripdesc(desc):
     """strip trailing whitespace and leading and trailing empty lines"""
     return b'\n'.join([l.rstrip() for l in desc.splitlines()]).strip(b'\n')
 
 
 class appender(object):
     '''the changelog index must be updated last on disk, so we use this class
     to delay writes to it'''
 
     def __init__(self, vfs, name, mode, buf):
         self.data = buf
         fp = vfs(name, mode)
         self.fp = fp
         self.offset = fp.tell()
         self.size = vfs.fstat(fp).st_size
         self._end = self.size
 
     def end(self):
         return self._end
 
     def tell(self):
         return self.offset
 
     def flush(self):
         pass
 
     @property
     def closed(self):
         return self.fp.closed
 
     def close(self):
         self.fp.close()
 
     def seek(self, offset, whence=0):
         '''virtual file offset spans real file and data'''
         if whence == 0:
             self.offset = offset
         elif whence == 1:
             self.offset += offset
         elif whence == 2:
             self.offset = self.end() + offset
         if self.offset < self.size:
             self.fp.seek(self.offset)
 
     def read(self, count=-1):
         '''only trick here is reads that span real file and data'''
         ret = b""
         if self.offset < self.size:
             s = self.fp.read(count)
             ret = s
             self.offset += len(s)
             if count > 0:
                 count -= len(s)
         if count != 0:
             doff = self.offset - self.size
             self.data.insert(0, b"".join(self.data))
             del self.data[1:]
             s = self.data[0][doff : doff + count]
             self.offset += len(s)
             ret += s
         return ret
 
     def write(self, s):
         self.data.append(bytes(s))
         self.offset += len(s)
         self._end += len(s)
 
     def __enter__(self):
         self.fp.__enter__()
         return self
 
     def __exit__(self, *args):
         return self.fp.__exit__(*args)
 
 
 def _divertopener(opener, target):
     """build an opener that writes in 'target.a' instead of 'target'"""
 
     def _divert(name, mode=b'r', checkambig=False):
         if name != target:
             return opener(name, mode)
         return opener(name + b".a", mode)
 
     return _divert
 
 
 def _delayopener(opener, target, buf):
     """build an opener that stores chunks in 'buf' instead of 'target'"""
 
     def _delay(name, mode=b'r', checkambig=False):
         if name != target:
             return opener(name, mode)
         return appender(opener, name, mode, buf)
 
     return _delay
 
 
 @attr.s
 class _changelogrevision(object):
     # Extensions might modify _defaultextra, so let the constructor below pass
     # it in
     extra = attr.ib()
     manifest = attr.ib(default=nullid)
     user = attr.ib(default=b'')
     date = attr.ib(default=(0, 0))
     files = attr.ib(default=attr.Factory(list))
     filesadded = attr.ib(default=None)
     filesremoved = attr.ib(default=None)
     p1copies = attr.ib(default=None)
     p2copies = attr.ib(default=None)
     description = attr.ib(default=b'')
 
 
 class changelogrevision(object):
     """Holds results of a parsed changelog revision.
 
     Changelog revisions consist of multiple pieces of data, including
     the manifest node, user, and date. This object exposes a view into
     the parsed object.
     """
 
     __slots__ = (
         r'_offsets',
         r'_text',
         r'_sidedata',
     )
 
     def __new__(cls, text, sidedata):
         if not text:
             return _changelogrevision(extra=_defaultextra)
 
         self = super(changelogrevision, cls).__new__(cls)
         # We could return here and implement the following as an __init__.
         # But doing it here is equivalent and saves an extra function call.
 
         # format used:
         # nodeid\n        : manifest node in ascii
         # user\n          : user, no \n or \r allowed
         # time tz extra\n : date (time is int or float, timezone is int)
         #                 : extra is metadata, encoded and separated by '\0'
         #                 : older versions ignore it
         # files\n\n       : files modified by the cset, no \n or \r allowed
         # (.*)            : comment (free text, ideally utf-8)
         #
         # changelog v0 doesn't use extra
 
         nl1 = text.index(b'\n')
         nl2 = text.index(b'\n', nl1 + 1)
         nl3 = text.index(b'\n', nl2 + 1)
 
         # The list of files may be empty. Which means nl3 is the first of the
         # double newline that precedes the description.
         if text[nl3 + 1 : nl3 + 2] == b'\n':
             doublenl = nl3
         else:
             doublenl = text.index(b'\n\n', nl3 + 1)
 
         self._offsets = (nl1, nl2, nl3, doublenl)
         self._text = text
         self._sidedata = sidedata
 
         return self
 
     @property
     def manifest(self):
         return bin(self._text[0 : self._offsets[0]])
 
     @property
     def user(self):
         off = self._offsets
         return encoding.tolocal(self._text[off[0] + 1 : off[1]])
 
     @property
     def _rawdate(self):
         off = self._offsets
         dateextra = self._text[off[1] + 1 : off[2]]
         return dateextra.split(b' ', 2)[0:2]
 
     @property
     def _rawextra(self):
         off = self._offsets
         dateextra = self._text[off[1] + 1 : off[2]]
         fields = dateextra.split(b' ', 2)
         if len(fields) != 3:
             return None
 
         return fields[2]
 
     @property
     def date(self):
         raw = self._rawdate
         time = float(raw[0])
         # Various tools did silly things with the timezone.
         try:
             timezone = int(raw[1])
         except ValueError:
             timezone = 0
 
         return time, timezone
 
     @property
     def extra(self):
         raw = self._rawextra
         if raw is None:
             return _defaultextra
 
         return decodeextra(raw)
 
     @property
     def files(self):
         off = self._offsets
         if off[2] == off[3]:
             return []
 
         return self._text[off[2] + 1 : off[3]].split(b'\n')
 
     @property
     def filesadded(self):
+        if sidedatamod.SD_FILESADDED in self._sidedata:
+            rawindices = self._sidedata.get(sidedatamod.SD_FILESADDED)
+        else:
         rawindices = self.extra.get(b'filesadded')
         if rawindices is None:
             return None
         return decodefileindices(self.files, rawindices)
 
     @property
     def filesremoved(self):
+        if sidedatamod.SD_FILESREMOVED in self._sidedata:
+            rawindices = self._sidedata.get(sidedatamod.SD_FILESREMOVED)
+        else:
         rawindices = self.extra.get(b'filesremoved')
         if rawindices is None:
             return None
         return decodefileindices(self.files, rawindices)
 
     @property
     def p1copies(self):
+        if sidedatamod.SD_P1COPIES in self._sidedata:
+            rawcopies = self._sidedata.get(sidedatamod.SD_P1COPIES)
+        else:
         rawcopies = self.extra.get(b'p1copies')
         if rawcopies is None:
             return None
         return decodecopies(self.files, rawcopies)
 
     @property
     def p2copies(self):
+        if sidedatamod.SD_P2COPIES in self._sidedata:
+            rawcopies = self._sidedata.get(sidedatamod.SD_P2COPIES)
+        else:
         rawcopies = self.extra.get(b'p2copies')
         if rawcopies is None:
             return None
         return decodecopies(self.files, rawcopies)
 
     @property
     def description(self):
         return encoding.tolocal(self._text[self._offsets[3] + 2 :])
 
 
 class changelog(revlog.revlog):
     def __init__(self, opener, trypending=False):
         """Load a changelog revlog using an opener.
 
         If ``trypending`` is true, we attempt to load the index from a
         ``00changelog.i.a`` file instead of the default ``00changelog.i``.
         The ``00changelog.i.a`` file contains index (and possibly inline
         revision) data for a transaction that hasn't been finalized yet.
         It exists in a separate file to facilitate readers (such as
         hooks processes) accessing data before a transaction is finalized.
         """
         if trypending and opener.exists(b'00changelog.i.a'):
             indexfile = b'00changelog.i.a'
         else:
             indexfile = b'00changelog.i'
 
         datafile = b'00changelog.d'
         revlog.revlog.__init__(
             self,
             opener,
             indexfile,
             datafile=datafile,
             checkambig=True,
             mmaplargeindex=True,
         )
 
         if self._initempty and (self.version & 0xFFFF == revlog.REVLOGV1):
             # changelogs don't benefit from generaldelta.
 
             self.version &= ~revlog.FLAG_GENERALDELTA
             self._generaldelta = False
 
         # Delta chains for changelogs tend to be very small because entries
         # tend to be small and don't delta well with each. So disable delta
         # chains.
         self._storedeltachains = False
 
         self._realopener = opener
         self._delayed = False
         self._delaybuf = None
         self._divert = False
         self.filteredrevs = frozenset()
         self._copiesstorage = opener.options.get(b'copies-storage')
 
     def tiprev(self):
         for i in pycompat.xrange(len(self) - 1, -2, -1):
             if i not in self.filteredrevs:
                 return i
 
     def tip(self):
         """filtered version of revlog.tip"""
         return self.node(self.tiprev())
 
     def __contains__(self, rev):
         """filtered version of revlog.__contains__"""
         return 0 <= rev < len(self) and rev not in self.filteredrevs
 
     def __iter__(self):
         """filtered version of revlog.__iter__"""
         if len(self.filteredrevs) == 0:
             return revlog.revlog.__iter__(self)
 
         def filterediter():
             for i in pycompat.xrange(len(self)):
                 if i not in self.filteredrevs:
                     yield i
 
         return filterediter()
 
     def revs(self, start=0, stop=None):
         """filtered version of revlog.revs"""
         for i in super(changelog, self).revs(start, stop):
             if i not in self.filteredrevs:
                 yield i
 
     def _checknofilteredinrevs(self, revs):
         """raise the appropriate error if 'revs' contains a filtered revision
 
         This returns a version of 'revs' to be used thereafter by the caller.
         In particular, if revs is an iterator, it is converted into a set.
         """
         safehasattr = util.safehasattr
         if safehasattr(revs, '__next__'):
             # Note that inspect.isgenerator() is not true for iterators,
             revs = set(revs)
 
         filteredrevs = self.filteredrevs
         if safehasattr(revs, 'first'):  # smartset
             offenders = revs & filteredrevs
         else:
             offenders = filteredrevs.intersection(revs)
 
         for rev in offenders:
             raise error.FilteredIndexError(rev)
         return revs
 
     def headrevs(self, revs=None):
         if revs is None and self.filteredrevs:
             try:
                 return self.index.headrevsfiltered(self.filteredrevs)
             # AttributeError covers non-c-extension environments and
             # old c extensions without filter handling.
             except AttributeError:
                 return self._headrevs()
 
         if self.filteredrevs:
             revs = self._checknofilteredinrevs(revs)
         return super(changelog, self).headrevs(revs)
 
     def strip(self, *args, **kwargs):
         # XXX make something better than assert
         # We can't expect proper strip behavior if we are filtered.
         assert not self.filteredrevs
         super(changelog, self).strip(*args, **kwargs)
 
     def rev(self, node):
         """filtered version of revlog.rev"""
         r = super(changelog, self).rev(node)
         if r in self.filteredrevs:
             raise error.FilteredLookupError(
                 hex(node), self.indexfile, _(b'filtered node')
             )
         return r
 
     def node(self, rev):
         """filtered version of revlog.node"""
         if rev in self.filteredrevs:
             raise error.FilteredIndexError(rev)
         return super(changelog, self).node(rev)
 
     def linkrev(self, rev):
         """filtered version of revlog.linkrev"""
         if rev in self.filteredrevs:
             raise error.FilteredIndexError(rev)
         return super(changelog, self).linkrev(rev)
 
     def parentrevs(self, rev):
         """filtered version of revlog.parentrevs"""
         if rev in self.filteredrevs:
             raise error.FilteredIndexError(rev)
         return super(changelog, self).parentrevs(rev)
 
     def flags(self, rev):
         """filtered version of revlog.flags"""
         if rev in self.filteredrevs:
             raise error.FilteredIndexError(rev)
         return super(changelog, self).flags(rev)
 
     def delayupdate(self, tr):
         b"delay visibility of index updates to other readers"
 
         if not self._delayed:
             if len(self) == 0:
                 self._divert = True
                 if self._realopener.exists(self.indexfile + b'.a'):
                     self._realopener.unlink(self.indexfile + b'.a')
                 self.opener = _divertopener(self._realopener, self.indexfile)
             else:
                 self._delaybuf = []
                 self.opener = _delayopener(
                     self._realopener, self.indexfile, self._delaybuf
                 )
         self._delayed = True
         tr.addpending(b'cl-%i' % id(self), self._writepending)
         tr.addfinalize(b'cl-%i' % id(self), self._finalize)
 
     def _finalize(self, tr):
         b"finalize index updates"
         self._delayed = False
         self.opener = self._realopener
         # move redirected index data back into place
         if self._divert:
             assert not self._delaybuf
             tmpname = self.indexfile + b".a"
             nfile = self.opener.open(tmpname)
             nfile.close()
             self.opener.rename(tmpname, self.indexfile, checkambig=True)
         elif self._delaybuf:
             fp = self.opener(self.indexfile, b'a', checkambig=True)
             fp.write(b"".join(self._delaybuf))
             fp.close()
             self._delaybuf = None
         self._divert = False
         # split when we're done
         self._enforceinlinesize(tr)
 
     def _writepending(self, tr):
         b"create a file containing the unfinalized state for pretxnchangegroup"
         if self._delaybuf:
             # make a temporary copy of the index
             fp1 = self._realopener(self.indexfile)
             pendingfilename = self.indexfile + b".a"
             # register as a temp file to ensure cleanup on failure
             tr.registertmp(pendingfilename)
             # write existing data
             fp2 = self._realopener(pendingfilename, b"w")
             fp2.write(fp1.read())
             # add pending data
             fp2.write(b"".join(self._delaybuf))
             fp2.close()
             # switch modes so finalize can simply rename
             self._delaybuf = None
             self._divert = True
             self.opener = _divertopener(self._realopener, self.indexfile)
 
         if self._divert:
             return True
 
         return False
 
     def _enforceinlinesize(self, tr, fp=None):
         if not self._delayed:
             revlog.revlog._enforceinlinesize(self, tr, fp)
 
     def read(self, node):
         """Obtain data from a parsed changelog revision.
 
         Returns a 6-tuple of:
 
            - manifest node in binary
            - author/user as a localstr
            - date as a 2-tuple of (time, timezone)
            - list of files
            - commit message as a localstr
            - dict of extra metadata
 
         Unless you need to access all fields, consider calling
         ``changelogrevision`` instead, as it is faster for partial object
         access.
         """
         c = changelogrevision(*self._revisiondata(node))
         return (c.manifest, c.user, c.date, c.files, c.description, c.extra)
 
     def changelogrevision(self, nodeorrev):
         """Obtain a ``changelogrevision`` for a node or revision."""
         text, sidedata = self._revisiondata(nodeorrev)
         return changelogrevision(text, sidedata)
 
     def readfiles(self, node):
         """
         short version of read that only returns the files modified by the cset
         """
         text = self.revision(node)
         if not text:
             return []
         last = text.index(b"\n\n")
         l = text[:last].split(b'\n')
         return l[3:]
 
     def add(
         self,
         manifest,
         files,
         desc,
         transaction,
         p1,
         p2,
         user,
         date=None,
         extra=None,
         p1copies=None,
         p2copies=None,
         filesadded=None,
         filesremoved=None,
     ):
         # Convert to UTF-8 encoded bytestrings as the very first
         # thing: calling any method on a localstr object will turn it
         # into a str object and the cached UTF-8 string is thus lost.
         user, desc = encoding.fromlocal(user), encoding.fromlocal(desc)
 
         user = user.strip()
         # An empty username or a username with a "\n" will make the
         # revision text contain two "\n\n" sequences -> corrupt
         # repository since read cannot unpack the revision.
         if not user:
             raise error.StorageError(_(b"empty username"))
         if b"\n" in user:
             raise error.StorageError(
                 _(b"username %r contains a newline") % pycompat.bytestr(user)
             )
 
         desc = stripdesc(desc)
 
         if date:
             parseddate = b"%d %d" % dateutil.parsedate(date)
         else:
             parseddate = b"%d %d" % dateutil.makedate()
         if extra:
             branch = extra.get(b"branch")
             if branch in (b"default", b""):
                 del extra[b"branch"]
             elif branch in (b".", b"null", b"tip"):
                 raise error.StorageError(
                     _(b'the name \'%s\' is reserved') % branch
                 )
         sortedfiles = sorted(files)
         sidedata = None
         if extra is not None:
             for name in (
                 b'p1copies',
                 b'p2copies',
                 b'filesadded',
                 b'filesremoved',
             ):
                 extra.pop(name, None)
         if p1copies is not None:
             p1copies = encodecopies(sortedfiles, p1copies)
         if p2copies is not None:
             p2copies = encodecopies(sortedfiles, p2copies)
         if filesadded is not None:
             filesadded = encodefileindices(sortedfiles, filesadded)
         if filesremoved is not None:
             filesremoved = encodefileindices(sortedfiles, filesremoved)
         if self._copiesstorage == b'extra':
             extrasentries = p1copies, p2copies, filesadded, filesremoved
             if extra is None and any(x is not None for x in extrasentries):
                 extra = {}
             if p1copies is not None:
                 extra[b'p1copies'] = p1copies
             if p2copies is not None:
                 extra[b'p2copies'] = p2copies
             if filesadded is not None:
                 extra[b'filesadded'] = filesadded
             if filesremoved is not None:
                 extra[b'filesremoved'] = filesremoved
         elif self._copiesstorage == b'changeset-sidedata':
             sidedata = {}
             if p1copies is not None:
                 sidedata[sidedatamod.SD_P1COPIES] = p1copies
             if p2copies is not None:
                 sidedata[sidedatamod.SD_P2COPIES] = p2copies
             if filesadded is not None:
                 sidedata[sidedatamod.SD_FILESADDED] = filesadded
             if filesremoved is not None:
                 sidedata[sidedatamod.SD_FILESREMOVED] = filesremoved
 
         if extra:
             extra = encodeextra(extra)
             parseddate = b"%s %s" % (parseddate, extra)
         l = [hex(manifest), user, parseddate] + sortedfiles + [b"", desc]
         text = b"\n".join(l)
         return self.addrevision(
             text, transaction, len(self), p1, p2, sidedata=sidedata
         )
 
     def branchinfo(self, rev):
         """return the branch name and open/close state of a revision
 
         This function exists because creating a changectx object
         just to access this is costly."""
         extra = self.read(rev)[5]
         return encoding.tolocal(extra.get(b"branch")), b'close' in extra
 
     def _nodeduplicatecallback(self, transaction, node):
         # keep track of revisions that got "re-added", eg: unbunde of know rev.
         #
         # We track them in a list to preserve their order from the source bundle
         duplicates = transaction.changes.setdefault(b'revduplicates', [])
         duplicates.append(self.rev(node))

mercurial/context.py

@@ -1,2966 +1,2987 b''
 # context.py - changeset and file context objects 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 filecmp
 import os
 import stat
 
 from .i18n import _
 from .node import (
     addednodeid,
     hex,
     modifiednodeid,
     nullid,
     nullrev,
     short,
     wdirfilenodeids,
     wdirhex,
 )
 from .pycompat import (
     getattr,
     open,
 )
 from . import (
     copies,
     dagop,
     encoding,
     error,
     fileset,
     match as matchmod,
     obsolete as obsmod,
     patch,
     pathutil,
     phases,
     pycompat,
     repoview,
     scmutil,
     sparse,
     subrepo,
     subrepoutil,
     util,
 )
 from .utils import (
     dateutil,
     stringutil,
 )
 
 propertycache = util.propertycache
 
 
 class basectx(object):
     """A basectx object represents the common logic for its children:
     changectx: read-only context that is already present in the repo,
     workingctx: a context that represents the working directory and can
                 be committed,
     memctx: a context that represents changes in-memory and can also
             be committed."""
 
     def __init__(self, repo):
         self._repo = repo
 
     def __bytes__(self):
         return short(self.node())
 
     __str__ = encoding.strmethod(__bytes__)
 
     def __repr__(self):
         return r"<%s %s>" % (type(self).__name__, str(self))
 
     def __eq__(self, other):
         try:
             return type(self) == type(other) and self._rev == other._rev
         except AttributeError:
             return False
 
     def __ne__(self, other):
         return not (self == other)
 
     def __contains__(self, key):
         return key in self._manifest
 
     def __getitem__(self, key):
         return self.filectx(key)
 
     def __iter__(self):
         return iter(self._manifest)
 
     def _buildstatusmanifest(self, status):
         """Builds a manifest that includes the given status results, if this is
         a working copy context. For non-working copy contexts, it just returns
         the normal manifest."""
         return self.manifest()
 
     def _matchstatus(self, other, match):
         """This internal method provides a way for child objects to override the
         match operator.
         """
         return match
 
     def _buildstatus(
         self, other, s, match, listignored, listclean, listunknown
     ):
         """build a status with respect to another context"""
         # Load earliest manifest first for caching reasons. More specifically,
         # if you have revisions 1000 and 1001, 1001 is probably stored as a
         # delta against 1000. Thus, if you read 1000 first, we'll reconstruct
         # 1000 and cache it so that when you read 1001, we just need to apply a
         # delta to what's in the cache. So that's one full reconstruction + one
         # delta application.
         mf2 = None
         if self.rev() is not None and self.rev() < other.rev():
             mf2 = self._buildstatusmanifest(s)
         mf1 = other._buildstatusmanifest(s)
         if mf2 is None:
             mf2 = self._buildstatusmanifest(s)
 
         modified, added = [], []
         removed = []
         clean = []
         deleted, unknown, ignored = s.deleted, s.unknown, s.ignored
         deletedset = set(deleted)
         d = mf1.diff(mf2, match=match, clean=listclean)
         for fn, value in pycompat.iteritems(d):
             if fn in deletedset:
                 continue
             if value is None:
                 clean.append(fn)
                 continue
             (node1, flag1), (node2, flag2) = value
             if node1 is None:
                 added.append(fn)
             elif node2 is None:
                 removed.append(fn)
             elif flag1 != flag2:
                 modified.append(fn)
             elif node2 not in wdirfilenodeids:
                 # When comparing files between two commits, we save time by
                 # not comparing the file contents when the nodeids differ.
                 # Note that this means we incorrectly report a reverted change
                 # to a file as a modification.
                 modified.append(fn)
             elif self[fn].cmp(other[fn]):
                 modified.append(fn)
             else:
                 clean.append(fn)
 
         if removed:
             # need to filter files if they are already reported as removed
             unknown = [
                 fn
                 for fn in unknown
                 if fn not in mf1 and (not match or match(fn))
             ]
             ignored = [
                 fn
                 for fn in ignored
                 if fn not in mf1 and (not match or match(fn))
             ]
             # if they're deleted, don't report them as removed
             removed = [fn for fn in removed if fn not in deletedset]
 
         return scmutil.status(
             modified, added, removed, deleted, unknown, ignored, clean
         )
 
     @propertycache
     def substate(self):
         return subrepoutil.state(self, self._repo.ui)
 
     def subrev(self, subpath):
         return self.substate[subpath][1]
 
     def rev(self):
         return self._rev
 
     def node(self):
         return self._node
 
     def hex(self):
         return hex(self.node())
 
     def manifest(self):
         return self._manifest
 
     def manifestctx(self):
         return self._manifestctx
 
     def repo(self):
         return self._repo
 
     def phasestr(self):
         return phases.phasenames[self.phase()]
 
     def mutable(self):
         return self.phase() > phases.public
 
     def matchfileset(self, expr, badfn=None):
         return fileset.match(self, expr, badfn=badfn)
 
     def obsolete(self):
         """True if the changeset is obsolete"""
         return self.rev() in obsmod.getrevs(self._repo, b'obsolete')
 
     def extinct(self):
         """True if the changeset is extinct"""
         return self.rev() in obsmod.getrevs(self._repo, b'extinct')
 
     def orphan(self):
         """True if the changeset is not obsolete, but its ancestor is"""
         return self.rev() in obsmod.getrevs(self._repo, b'orphan')
 
     def phasedivergent(self):
         """True if the changeset tries to be a successor of a public changeset
 
         Only non-public and non-obsolete changesets may be phase-divergent.
         """
         return self.rev() in obsmod.getrevs(self._repo, b'phasedivergent')
 
     def contentdivergent(self):
         """Is a successor of a changeset with multiple possible successor sets
 
         Only non-public and non-obsolete changesets may be content-divergent.
         """
         return self.rev() in obsmod.getrevs(self._repo, b'contentdivergent')
 
     def isunstable(self):
         """True if the changeset is either orphan, phase-divergent or
         content-divergent"""
         return self.orphan() or self.phasedivergent() or self.contentdivergent()
 
     def instabilities(self):
         """return the list of instabilities affecting this changeset.
 
         Instabilities are returned as strings. possible values are:
         - orphan,
         - phase-divergent,
         - content-divergent.
         """
         instabilities = []
         if self.orphan():
             instabilities.append(b'orphan')
         if self.phasedivergent():
             instabilities.append(b'phase-divergent')
         if self.contentdivergent():
             instabilities.append(b'content-divergent')
         return instabilities
 
     def parents(self):
         """return contexts for each parent changeset"""
         return self._parents
 
     def p1(self):
         return self._parents[0]
 
     def p2(self):
         parents = self._parents
         if len(parents) == 2:
             return parents[1]
         return self._repo[nullrev]
 
     def _fileinfo(self, path):
         if r'_manifest' in self.__dict__:
             try:
                 return self._manifest[path], self._manifest.flags(path)
             except KeyError:
                 raise error.ManifestLookupError(
                     self._node, path, _(b'not found in manifest')
                 )
         if r'_manifestdelta' in self.__dict__ or path in self.files():
             if path in self._manifestdelta:
                 return (
                     self._manifestdelta[path],
                     self._manifestdelta.flags(path),
                 )
         mfl = self._repo.manifestlog
         try:
             node, flag = mfl[self._changeset.manifest].find(path)
         except KeyError:
             raise error.ManifestLookupError(
                 self._node, path, _(b'not found in manifest')
             )
 
         return node, flag
 
     def filenode(self, path):
         return self._fileinfo(path)[0]
 
     def flags(self, path):
         try:
             return self._fileinfo(path)[1]
         except error.LookupError:
             return b''
 
     @propertycache
     def _copies(self):
         return copies.computechangesetcopies(self)
 
     def p1copies(self):
         return self._copies[0]
 
     def p2copies(self):
         return self._copies[1]
 
     def sub(self, path, allowcreate=True):
         '''return a subrepo for the stored revision of path, never wdir()'''
         return subrepo.subrepo(self, path, allowcreate=allowcreate)
 
     def nullsub(self, path, pctx):
         return subrepo.nullsubrepo(self, path, pctx)
 
     def workingsub(self, path):
         '''return a subrepo for the stored revision, or wdir if this is a wdir
         context.
         '''
         return subrepo.subrepo(self, path, allowwdir=True)
 
     def match(
         self,
         pats=None,
         include=None,
         exclude=None,
         default=b'glob',
         listsubrepos=False,
         badfn=None,
     ):
         r = self._repo
         return matchmod.match(
             r.root,
             r.getcwd(),
             pats,
             include,
             exclude,
             default,
             auditor=r.nofsauditor,
             ctx=self,
             listsubrepos=listsubrepos,
             badfn=badfn,
         )
 
     def diff(
         self,
         ctx2=None,
         match=None,
         changes=None,
         opts=None,
         losedatafn=None,
         pathfn=None,
         copy=None,
         copysourcematch=None,
         hunksfilterfn=None,
     ):
         """Returns a diff generator for the given contexts and matcher"""
         if ctx2 is None:
             ctx2 = self.p1()
         if ctx2 is not None:
             ctx2 = self._repo[ctx2]
         return patch.diff(
             self._repo,
             ctx2,
             self,
             match=match,
             changes=changes,
             opts=opts,
             losedatafn=losedatafn,
             pathfn=pathfn,
             copy=copy,
             copysourcematch=copysourcematch,
             hunksfilterfn=hunksfilterfn,
         )
 
     def dirs(self):
         return self._manifest.dirs()
 
     def hasdir(self, dir):
         return self._manifest.hasdir(dir)
 
     def status(
         self,
         other=None,
         match=None,
         listignored=False,
         listclean=False,
         listunknown=False,
         listsubrepos=False,
     ):
         """return status of files between two nodes or node and working
         directory.
 
         If other is None, compare this node with working directory.
 
         returns (modified, added, removed, deleted, unknown, ignored, clean)
         """
 
         ctx1 = self
         ctx2 = self._repo[other]
 
         # This next code block is, admittedly, fragile logic that tests for
         # reversing the contexts and wouldn't need to exist if it weren't for
         # the fast (and common) code path of comparing the working directory
         # with its first parent.
         #
         # What we're aiming for here is the ability to call:
         #
         # workingctx.status(parentctx)
         #
         # If we always built the manifest for each context and compared those,
         # then we'd be done. But the special case of the above call means we
         # just copy the manifest of the parent.
         reversed = False
         if not isinstance(ctx1, changectx) and isinstance(ctx2, changectx):
             reversed = True
             ctx1, ctx2 = ctx2, ctx1
 
         match = self._repo.narrowmatch(match)
         match = ctx2._matchstatus(ctx1, match)
         r = scmutil.status([], [], [], [], [], [], [])
         r = ctx2._buildstatus(
             ctx1, r, match, listignored, listclean, listunknown
         )
 
         if reversed:
             # Reverse added and removed. Clear deleted, unknown and ignored as
             # these make no sense to reverse.
             r = scmutil.status(
                 r.modified, r.removed, r.added, [], [], [], r.clean
             )
 
         if listsubrepos:
             for subpath, sub in scmutil.itersubrepos(ctx1, ctx2):
                 try:
                     rev2 = ctx2.subrev(subpath)
                 except KeyError:
                     # A subrepo that existed in node1 was deleted between
                     # node1 and node2 (inclusive). Thus, ctx2's substate
                     # won't contain that subpath. The best we can do ignore it.
                     rev2 = None
                 submatch = matchmod.subdirmatcher(subpath, match)
                 s = sub.status(
                     rev2,
                     match=submatch,
                     ignored=listignored,
                     clean=listclean,
                     unknown=listunknown,
                     listsubrepos=True,
                 )
                 for rfiles, sfiles in zip(r, s):
                     rfiles.extend(b"%s/%s" % (subpath, f) for f in sfiles)
 
         for l in r:
             l.sort()
 
         return r
 
 
 class changectx(basectx):
     """A changecontext object makes access to data related to a particular
     changeset convenient. It represents a read-only context already present in
     the repo."""
 
     def __init__(self, repo, rev, node):
         super(changectx, self).__init__(repo)
         self._rev = rev
         self._node = node
 
     def __hash__(self):
         try:
             return hash(self._rev)
         except AttributeError:
             return id(self)
 
     def __nonzero__(self):
         return self._rev != nullrev
 
     __bool__ = __nonzero__
 
     @propertycache
     def _changeset(self):
         return self._repo.changelog.changelogrevision(self.rev())
 
     @propertycache
     def _manifest(self):
         return self._manifestctx.read()
 
     @property
     def _manifestctx(self):
         return self._repo.manifestlog[self._changeset.manifest]
 
     @propertycache
     def _manifestdelta(self):
         return self._manifestctx.readdelta()
 
     @propertycache
     def _parents(self):
         repo = self._repo
         p1, p2 = repo.changelog.parentrevs(self._rev)
         if p2 == nullrev:
             return [repo[p1]]
         return [repo[p1], repo[p2]]
 
     def changeset(self):
         c = self._changeset
         return (
             c.manifest,
             c.user,
             c.date,
             c.files,
             c.description,
             c.extra,
         )
 
     def manifestnode(self):
         return self._changeset.manifest
 
     def user(self):
         return self._changeset.user
 
     def date(self):
         return self._changeset.date
 
     def files(self):
         return self._changeset.files
 
     def filesmodified(self):
         modified = set(self.files())
         modified.difference_update(self.filesadded())
         modified.difference_update(self.filesremoved())
         return sorted(modified)
 
     def filesadded(self):
+        filesadded = self._changeset.filesadded
+        compute_on_none = True
+        if self._repo.filecopiesmode == b'changeset-sidedata':
+            compute_on_none = False
+        else:
         source = self._repo.ui.config(b'experimental', b'copies.read-from')
-        filesadded = self._changeset.filesadded
         if source == b'changeset-only':
+                compute_on_none = False
+            elif source != b'compatibility':
+                # filelog mode, ignore any changelog content
+                filesadded = None
             if filesadded is None:
-                filesadded = []
-        elif source == b'compatibility':
-            if filesadded is None:
+            if compute_on_none:
                 filesadded = scmutil.computechangesetfilesadded(self)
         else:
-            filesadded = scmutil.computechangesetfilesadded(self)
+                filesadded = []
         return filesadded
 
     def filesremoved(self):
+        filesremoved = self._changeset.filesremoved
+        compute_on_none = True
+        if self._repo.filecopiesmode == b'changeset-sidedata':
+            compute_on_none = False
+        else:
         source = self._repo.ui.config(b'experimental', b'copies.read-from')
-        filesremoved = self._changeset.filesremoved
         if source == b'changeset-only':
+                compute_on_none = False
+            elif source != b'compatibility':
+                # filelog mode, ignore any changelog content
+                filesremoved = None
             if filesremoved is None:
-                filesremoved = []
-        elif source == b'compatibility':
-            if filesremoved is None:
+            if compute_on_none:
                 filesremoved = scmutil.computechangesetfilesremoved(self)
         else:
-            filesremoved = scmutil.computechangesetfilesremoved(self)
+                filesremoved = []
         return filesremoved
 
     @propertycache
     def _copies(self):
-        source = self._repo.ui.config(b'experimental', b'copies.read-from')
         p1copies = self._changeset.p1copies
         p2copies = self._changeset.p2copies
-        # If config says to get copy metadata only from changeset, then return
-        # that, defaulting to {} if there was no copy metadata.
-        # In compatibility mode, we return copy data from the changeset if
-        # it was recorded there, and otherwise we fall back to getting it from
+        compute_on_none = True
+        if self._repo.filecopiesmode == b'changeset-sidedata':
+            compute_on_none = False
+        else:
+            source = self._repo.ui.config(b'experimental', b'copies.read-from')
+            # If config says to get copy metadata only from changeset, then
+            # return that, defaulting to {} if there was no copy metadata.  In
+            # compatibility mode, we return copy data from the changeset if it
+            # was recorded there, and otherwise we fall back to getting it from
         # the filelogs (below).
+            #
+            # If we are in compatiblity mode and there is not data in the
+            # changeset), we get the copy metadata from the filelogs.
+            #
+            # otherwise, when config said to read only from filelog, we get the
+            # copy metadata from the filelogs.
         if source == b'changeset-only':
+                compute_on_none = False
+            elif source != b'compatibility':
+                # filelog mode, ignore any changelog content
+                p1copies = p2copies = None
+        if p1copies is None:
+            if compute_on_none:
+                p1copies, p2copies = super(changectx, self)._copies
+            else:
             if p1copies is None:
                 p1copies = {}
             if p2copies is None:
                 p2copies = {}
-        elif source == b'compatibility':
-            if p1copies is None:
-                # we are in compatiblity mode and there is not data in the
-                # changeset), we get the copy metadata from the filelogs.
-                p1copies, p2copies = super(changectx, self)._copies
-        else:
-            # config said to read only from filelog, we get the copy metadata
-            # from the filelogs.
-            p1copies, p2copies = super(changectx, self)._copies
         return p1copies, p2copies
 
     def description(self):
         return self._changeset.description
 
     def branch(self):
         return encoding.tolocal(self._changeset.extra.get(b"branch"))
 
     def closesbranch(self):
         return b'close' in self._changeset.extra
 
     def extra(self):
         """Return a dict of extra information."""
         return self._changeset.extra
 
     def tags(self):
         """Return a list of byte tag names"""
         return self._repo.nodetags(self._node)
 
     def bookmarks(self):
         """Return a list of byte bookmark names."""
         return self._repo.nodebookmarks(self._node)
 
     def phase(self):
         return self._repo._phasecache.phase(self._repo, self._rev)
 
     def hidden(self):
         return self._rev in repoview.filterrevs(self._repo, b'visible')
 
     def isinmemory(self):
         return False
 
     def children(self):
         """return list of changectx contexts for each child changeset.
 
         This returns only the immediate child changesets. Use descendants() to
         recursively walk children.
         """
         c = self._repo.changelog.children(self._node)
         return [self._repo[x] for x in c]
 
     def ancestors(self):
         for a in self._repo.changelog.ancestors([self._rev]):
             yield self._repo[a]
 
     def descendants(self):
         """Recursively yield all children of the changeset.
 
         For just the immediate children, use children()
         """
         for d in self._repo.changelog.descendants([self._rev]):
             yield self._repo[d]
 
     def filectx(self, path, fileid=None, filelog=None):
         """get a file context from this changeset"""
         if fileid is None:
             fileid = self.filenode(path)
         return filectx(
             self._repo, path, fileid=fileid, changectx=self, filelog=filelog
         )
 
     def ancestor(self, c2, warn=False):
         """return the "best" ancestor context of self and c2
 
         If there are multiple candidates, it will show a message and check
         merge.preferancestor configuration before falling back to the
         revlog ancestor."""
         # deal with workingctxs
         n2 = c2._node
         if n2 is None:
             n2 = c2._parents[0]._node
         cahs = self._repo.changelog.commonancestorsheads(self._node, n2)
         if not cahs:
             anc = nullid
         elif len(cahs) == 1:
             anc = cahs[0]
         else:
             # experimental config: merge.preferancestor
             for r in self._repo.ui.configlist(b'merge', b'preferancestor'):
                 try:
                     ctx = scmutil.revsymbol(self._repo, r)
                 except error.RepoLookupError:
                     continue
                 anc = ctx.node()
                 if anc in cahs:
                     break
             else:
                 anc = self._repo.changelog.ancestor(self._node, n2)
             if warn:
                 self._repo.ui.status(
                     (
                         _(b"note: using %s as ancestor of %s and %s\n")
                         % (short(anc), short(self._node), short(n2))
                     )
                     + b''.join(
                         _(
                             b"      alternatively, use --config "
                             b"merge.preferancestor=%s\n"
                         )
                         % short(n)
                         for n in sorted(cahs)
                         if n != anc
                     )
                 )
         return self._repo[anc]
 
     def isancestorof(self, other):
         """True if this changeset is an ancestor of other"""
         return self._repo.changelog.isancestorrev(self._rev, other._rev)
 
     def walk(self, match):
         '''Generates matching file names.'''
 
         # Wrap match.bad method to have message with nodeid
         def bad(fn, msg):
             # The manifest doesn't know about subrepos, so don't complain about
             # paths into valid subrepos.
             if any(fn == s or fn.startswith(s + b'/') for s in self.substate):
                 return
             match.bad(fn, _(b'no such file in rev %s') % self)
 
         m = matchmod.badmatch(self._repo.narrowmatch(match), bad)
         return self._manifest.walk(m)
 
     def matches(self, match):
         return self.walk(match)
 
 
 class basefilectx(object):
     """A filecontext object represents the common logic for its children:
     filectx: read-only access to a filerevision that is already present
              in the repo,
     workingfilectx: a filecontext that represents files from the working
                     directory,
     memfilectx: a filecontext that represents files in-memory,
     """
 
     @propertycache
     def _filelog(self):
         return self._repo.file(self._path)
 
     @propertycache
     def _changeid(self):
         if r'_changectx' in self.__dict__:
             return self._changectx.rev()
         elif r'_descendantrev' in self.__dict__:
             # this file context was created from a revision with a known
             # descendant, we can (lazily) correct for linkrev aliases
             return self._adjustlinkrev(self._descendantrev)
         else:
             return self._filelog.linkrev(self._filerev)
 
     @propertycache
     def _filenode(self):
         if r'_fileid' in self.__dict__:
             return self._filelog.lookup(self._fileid)
         else:
             return self._changectx.filenode(self._path)
 
     @propertycache
     def _filerev(self):
         return self._filelog.rev(self._filenode)
 
     @propertycache
     def _repopath(self):
         return self._path
 
     def __nonzero__(self):
         try:
             self._filenode
             return True
         except error.LookupError:
             # file is missing
             return False
 
     __bool__ = __nonzero__
 
     def __bytes__(self):
         try:
             return b"%s@%s" % (self.path(), self._changectx)
         except error.LookupError:
             return b"%s@???" % self.path()
 
     __str__ = encoding.strmethod(__bytes__)
 
     def __repr__(self):
         return r"<%s %s>" % (type(self).__name__, str(self))
 
     def __hash__(self):
         try:
             return hash((self._path, self._filenode))
         except AttributeError:
             return id(self)
 
     def __eq__(self, other):
         try:
             return (
                 type(self) == type(other)
                 and self._path == other._path
                 and self._filenode == other._filenode
             )
         except AttributeError:
             return False
 
     def __ne__(self, other):
         return not (self == other)
 
     def filerev(self):
         return self._filerev
 
     def filenode(self):
         return self._filenode
 
     @propertycache
     def _flags(self):
         return self._changectx.flags(self._path)
 
     def flags(self):
         return self._flags
 
     def filelog(self):
         return self._filelog
 
     def rev(self):
         return self._changeid
 
     def linkrev(self):
         return self._filelog.linkrev(self._filerev)
 
     def node(self):
         return self._changectx.node()
 
     def hex(self):
         return self._changectx.hex()
 
     def user(self):
         return self._changectx.user()
 
     def date(self):
         return self._changectx.date()
 
     def files(self):
         return self._changectx.files()
 
     def description(self):
         return self._changectx.description()
 
     def branch(self):
         return self._changectx.branch()
 
     def extra(self):
         return self._changectx.extra()
 
     def phase(self):
         return self._changectx.phase()
 
     def phasestr(self):
         return self._changectx.phasestr()
 
     def obsolete(self):
         return self._changectx.obsolete()
 
     def instabilities(self):
         return self._changectx.instabilities()
 
     def manifest(self):
         return self._changectx.manifest()
 
     def changectx(self):
         return self._changectx
 
     def renamed(self):
         return self._copied
 
     def copysource(self):
         return self._copied and self._copied[0]
 
     def repo(self):
         return self._repo
 
     def size(self):
         return len(self.data())
 
     def path(self):
         return self._path
 
     def isbinary(self):
         try:
             return stringutil.binary(self.data())
         except IOError:
             return False
 
     def isexec(self):
         return b'x' in self.flags()
 
     def islink(self):
         return b'l' in self.flags()
 
     def isabsent(self):
         """whether this filectx represents a file not in self._changectx
 
         This is mainly for merge code to detect change/delete conflicts. This is
         expected to be True for all subclasses of basectx."""
         return False
 
     _customcmp = False
 
     def cmp(self, fctx):
         """compare with other file context
 
         returns True if different than fctx.
         """
         if fctx._customcmp:
             return fctx.cmp(self)
 
         if self._filenode is None:
             raise error.ProgrammingError(
                 b'filectx.cmp() must be reimplemented if not backed by revlog'
             )
 
         if fctx._filenode is None:
             if self._repo._encodefilterpats:
                 # can't rely on size() because wdir content may be decoded
                 return self._filelog.cmp(self._filenode, fctx.data())
             if self.size() - 4 == fctx.size():
                 # size() can match:
                 # if file data starts with '\1\n', empty metadata block is
                 # prepended, which adds 4 bytes to filelog.size().
                 return self._filelog.cmp(self._filenode, fctx.data())
         if self.size() == fctx.size():
             # size() matches: need to compare content
             return self._filelog.cmp(self._filenode, fctx.data())
 
         # size() differs
         return True
 
     def _adjustlinkrev(self, srcrev, inclusive=False, stoprev=None):
         """return the first ancestor of <srcrev> introducing <fnode>
 
         If the linkrev of the file revision does not point to an ancestor of
         srcrev, we'll walk down the ancestors until we find one introducing
         this file revision.
 
         :srcrev: the changeset revision we search ancestors from
         :inclusive: if true, the src revision will also be checked
         :stoprev: an optional revision to stop the walk at. If no introduction
                   of this file content could be found before this floor
                   revision, the function will returns "None" and stops its
                   iteration.
         """
         repo = self._repo
         cl = repo.unfiltered().changelog
         mfl = repo.manifestlog
         # fetch the linkrev
         lkr = self.linkrev()
         if srcrev == lkr:
             return lkr
         # hack to reuse ancestor computation when searching for renames
         memberanc = getattr(self, '_ancestrycontext', None)
         iteranc = None
         if srcrev is None:
             # wctx case, used by workingfilectx during mergecopy
             revs = [p.rev() for p in self._repo[None].parents()]
             inclusive = True  # we skipped the real (revless) source
         else:
             revs = [srcrev]
         if memberanc is None:
             memberanc = iteranc = cl.ancestors(revs, lkr, inclusive=inclusive)
         # check if this linkrev is an ancestor of srcrev
         if lkr not in memberanc:
             if iteranc is None:
                 iteranc = cl.ancestors(revs, lkr, inclusive=inclusive)
             fnode = self._filenode
             path = self._path
             for a in iteranc:
                 if stoprev is not None and a < stoprev:
                     return None
                 ac = cl.read(a)  # get changeset data (we avoid object creation)
                 if path in ac[3]:  # checking the 'files' field.
                     # The file has been touched, check if the content is
                     # similar to the one we search for.
                     if fnode == mfl[ac[0]].readfast().get(path):
                         return a
             # In theory, we should never get out of that loop without a result.
             # But if manifest uses a buggy file revision (not children of the
             # one it replaces) we could. Such a buggy situation will likely
             # result is crash somewhere else at to some point.
         return lkr
 
     def isintroducedafter(self, changelogrev):
         """True if a filectx has been introduced after a given floor revision
         """
         if self.linkrev() >= changelogrev:
             return True
         introrev = self._introrev(stoprev=changelogrev)
         if introrev is None:
             return False
         return introrev >= changelogrev
 
     def introrev(self):
         """return the rev of the changeset which introduced this file revision
 
         This method is different from linkrev because it take into account the
         changeset the filectx was created from. It ensures the returned
         revision is one of its ancestors. This prevents bugs from
         'linkrev-shadowing' when a file revision is used by multiple
         changesets.
         """
         return self._introrev()
 
     def _introrev(self, stoprev=None):
         """
         Same as `introrev` but, with an extra argument to limit changelog
         iteration range in some internal usecase.
 
         If `stoprev` is set, the `introrev` will not be searched past that
         `stoprev` revision and "None" might be returned. This is useful to
         limit the iteration range.
         """
         toprev = None
         attrs = vars(self)
         if r'_changeid' in attrs:
             # We have a cached value already
             toprev = self._changeid
         elif r'_changectx' in attrs:
             # We know which changelog entry we are coming from
             toprev = self._changectx.rev()
 
         if toprev is not None:
             return self._adjustlinkrev(toprev, inclusive=True, stoprev=stoprev)
         elif r'_descendantrev' in attrs:
             introrev = self._adjustlinkrev(self._descendantrev, stoprev=stoprev)
             # be nice and cache the result of the computation
             if introrev is not None:
                 self._changeid = introrev
             return introrev
         else:
             return self.linkrev()
 
     def introfilectx(self):
         """Return filectx having identical contents, but pointing to the
         changeset revision where this filectx was introduced"""
         introrev = self.introrev()
         if self.rev() == introrev:
             return self
         return self.filectx(self.filenode(), changeid=introrev)
 
     def _parentfilectx(self, path, fileid, filelog):
         """create parent filectx keeping ancestry info for _adjustlinkrev()"""
         fctx = filectx(self._repo, path, fileid=fileid, filelog=filelog)
         if r'_changeid' in vars(self) or r'_changectx' in vars(self):
             # If self is associated with a changeset (probably explicitly
             # fed), ensure the created filectx is associated with a
             # changeset that is an ancestor of self.changectx.
             # This lets us later use _adjustlinkrev to get a correct link.
             fctx._descendantrev = self.rev()
             fctx._ancestrycontext = getattr(self, '_ancestrycontext', None)
         elif r'_descendantrev' in vars(self):
             # Otherwise propagate _descendantrev if we have one associated.
             fctx._descendantrev = self._descendantrev
             fctx._ancestrycontext = getattr(self, '_ancestrycontext', None)
         return fctx
 
     def parents(self):
         _path = self._path
         fl = self._filelog
         parents = self._filelog.parents(self._filenode)
         pl = [(_path, node, fl) for node in parents if node != nullid]
 
         r = fl.renamed(self._filenode)
         if r:
             # - In the simple rename case, both parent are nullid, pl is empty.
             # - In case of merge, only one of the parent is null id and should
             # be replaced with the rename information. This parent is -always-
             # the first one.
             #
             # As null id have always been filtered out in the previous list
             # comprehension, inserting to 0 will always result in "replacing
             # first nullid parent with rename information.
             pl.insert(0, (r[0], r[1], self._repo.file(r[0])))
 
         return [self._parentfilectx(path, fnode, l) for path, fnode, l in pl]
 
     def p1(self):
         return self.parents()[0]
 
     def p2(self):
         p = self.parents()
         if len(p) == 2:
             return p[1]
         return filectx(self._repo, self._path, fileid=-1, filelog=self._filelog)
 
     def annotate(self, follow=False, skiprevs=None, diffopts=None):
         """Returns a list of annotateline objects for each line in the file
 
         - line.fctx is the filectx of the node where that line was last changed
         - line.lineno is the line number at the first appearance in the managed
           file
         - line.text is the data on that line (including newline character)
         """
         getlog = util.lrucachefunc(lambda x: self._repo.file(x))
 
         def parents(f):
             # Cut _descendantrev here to mitigate the penalty of lazy linkrev
             # adjustment. Otherwise, p._adjustlinkrev() would walk changelog
             # from the topmost introrev (= srcrev) down to p.linkrev() if it
             # isn't an ancestor of the srcrev.
             f._changeid
             pl = f.parents()
 
             # Don't return renamed parents if we aren't following.
             if not follow:
                 pl = [p for p in pl if p.path() == f.path()]
 
             # renamed filectx won't have a filelog yet, so set it
             # from the cache to save time
             for p in pl:
                 if not r'_filelog' in p.__dict__:
                     p._filelog = getlog(p.path())
 
             return pl
 
         # use linkrev to find the first changeset where self appeared
         base = self.introfilectx()
         if getattr(base, '_ancestrycontext', None) is None:
             cl = self._repo.changelog
             if base.rev() is None:
                 # wctx is not inclusive, but works because _ancestrycontext
                 # is used to test filelog revisions
                 ac = cl.ancestors(
                     [p.rev() for p in base.parents()], inclusive=True
                 )
             else:
                 ac = cl.ancestors([base.rev()], inclusive=True)
             base._ancestrycontext = ac
 
         return dagop.annotate(
             base, parents, skiprevs=skiprevs, diffopts=diffopts
         )
 
     def ancestors(self, followfirst=False):
         visit = {}
         c = self
         if followfirst:
             cut = 1
         else:
             cut = None
 
         while True:
             for parent in c.parents()[:cut]:
                 visit[(parent.linkrev(), parent.filenode())] = parent
             if not visit:
                 break
             c = visit.pop(max(visit))
             yield c
 
     def decodeddata(self):
         """Returns `data()` after running repository decoding filters.
 
         This is often equivalent to how the data would be expressed on disk.
         """
         return self._repo.wwritedata(self.path(), self.data())
 
 
 class filectx(basefilectx):
     """A filecontext object makes access to data related to a particular
        filerevision convenient."""
 
     def __init__(
         self,
         repo,
         path,
         changeid=None,
         fileid=None,
         filelog=None,
         changectx=None,
     ):
         """changeid must be a revision number, if specified.
            fileid can be a file revision or node."""
         self._repo = repo
         self._path = path
 
         assert (
             changeid is not None or fileid is not None or changectx is not None
         ), b"bad args: changeid=%r, fileid=%r, changectx=%r" % (
             changeid,
             fileid,
             changectx,
         )
 
         if filelog is not None:
             self._filelog = filelog
 
         if changeid is not None:
             self._changeid = changeid
         if changectx is not None:
             self._changectx = changectx
         if fileid is not None:
             self._fileid = fileid
 
     @propertycache
     def _changectx(self):
         try:
             return self._repo[self._changeid]
         except error.FilteredRepoLookupError:
             # Linkrev may point to any revision in the repository.  When the
             # repository is filtered this may lead to `filectx` trying to build
             # `changectx` for filtered revision. In such case we fallback to
             # creating `changectx` on the unfiltered version of the reposition.
             # This fallback should not be an issue because `changectx` from
             # `filectx` are not used in complex operations that care about
             # filtering.
             #
             # This fallback is a cheap and dirty fix that prevent several
             # crashes. It does not ensure the behavior is correct. However the
             # behavior was not correct before filtering either and "incorrect
             # behavior" is seen as better as "crash"
             #
             # Linkrevs have several serious troubles with filtering that are
             # complicated to solve. Proper handling of the issue here should be
             # considered when solving linkrev issue are on the table.
             return self._repo.unfiltered()[self._changeid]
 
     def filectx(self, fileid, changeid=None):
         '''opens an arbitrary revision of the file without
         opening a new filelog'''
         return filectx(
             self._repo,
             self._path,
             fileid=fileid,
             filelog=self._filelog,
             changeid=changeid,
         )
 
     def rawdata(self):
         return self._filelog.rawdata(self._filenode)
 
     def rawflags(self):
         """low-level revlog flags"""
         return self._filelog.flags(self._filerev)
 
     def data(self):
         try:
             return self._filelog.read(self._filenode)
         except error.CensoredNodeError:
             if self._repo.ui.config(b"censor", b"policy") == b"ignore":
                 return b""
             raise error.Abort(
                 _(b"censored node: %s") % short(self._filenode),
                 hint=_(b"set censor.policy to ignore errors"),
             )
 
     def size(self):
         return self._filelog.size(self._filerev)
 
     @propertycache
     def _copied(self):
         """check if file was actually renamed in this changeset revision
 
         If rename logged in file revision, we report copy for changeset only
         if file revisions linkrev points back to the changeset in question
         or both changeset parents contain different file revisions.
         """
 
         renamed = self._filelog.renamed(self._filenode)
         if not renamed:
             return None
 
         if self.rev() == self.linkrev():
             return renamed
 
         name = self.path()
         fnode = self._filenode
         for p in self._changectx.parents():
             try:
                 if fnode == p.filenode(name):
                     return None
             except error.LookupError:
                 pass
         return renamed
 
     def children(self):
         # hard for renames
         c = self._filelog.children(self._filenode)
         return [
             filectx(self._repo, self._path, fileid=x, filelog=self._filelog)
             for x in c
         ]
 
 
 class committablectx(basectx):
     """A committablectx object provides common functionality for a context that
     wants the ability to commit, e.g. workingctx or memctx."""
 
     def __init__(
         self,
         repo,
         text=b"",
         user=None,
         date=None,
         extra=None,
         changes=None,
         branch=None,
     ):
         super(committablectx, self).__init__(repo)
         self._rev = None
         self._node = None
         self._text = text
         if date:
             self._date = dateutil.parsedate(date)
         if user:
             self._user = user
         if changes:
             self._status = changes
 
         self._extra = {}
         if extra:
             self._extra = extra.copy()
         if branch is not None:
             self._extra[b'branch'] = encoding.fromlocal(branch)
         if not self._extra.get(b'branch'):
             self._extra[b'branch'] = b'default'
 
     def __bytes__(self):
         return bytes(self._parents[0]) + b"+"
 
     __str__ = encoding.strmethod(__bytes__)
 
     def __nonzero__(self):
         return True
 
     __bool__ = __nonzero__
 
     @propertycache
     def _status(self):
         return self._repo.status()
 
     @propertycache
     def _user(self):
         return self._repo.ui.username()
 
     @propertycache
     def _date(self):
         ui = self._repo.ui
         date = ui.configdate(b'devel', b'default-date')
         if date is None:
             date = dateutil.makedate()
         return date
 
     def subrev(self, subpath):
         return None
 
     def manifestnode(self):
         return None
 
     def user(self):
         return self._user or self._repo.ui.username()
 
     def date(self):
         return self._date
 
     def description(self):
         return self._text
 
     def files(self):
         return sorted(
             self._status.modified + self._status.added + self._status.removed
         )
 
     def modified(self):
         return self._status.modified
 
     def added(self):
         return self._status.added
 
     def removed(self):
         return self._status.removed
 
     def deleted(self):
         return self._status.deleted
 
     filesmodified = modified
     filesadded = added
     filesremoved = removed
 
     def branch(self):
         return encoding.tolocal(self._extra[b'branch'])
 
     def closesbranch(self):
         return b'close' in self._extra
 
     def extra(self):
         return self._extra
 
     def isinmemory(self):
         return False
 
     def tags(self):
         return []
 
     def bookmarks(self):
         b = []
         for p in self.parents():
             b.extend(p.bookmarks())
         return b
 
     def phase(self):
         phase = phases.draft  # default phase to draft
         for p in self.parents():
             phase = max(phase, p.phase())
         return phase
 
     def hidden(self):
         return False
 
     def children(self):
         return []
 
     def ancestor(self, c2):
         """return the "best" ancestor context of self and c2"""
         return self._parents[0].ancestor(c2)  # punt on two parents for now
 
     def ancestors(self):
         for p in self._parents:
             yield p
         for a in self._repo.changelog.ancestors(
             [p.rev() for p in self._parents]
         ):
             yield self._repo[a]
 
     def markcommitted(self, node):
         """Perform post-commit cleanup necessary after committing this ctx
 
         Specifically, this updates backing stores this working context
         wraps to reflect the fact that the changes reflected by this
         workingctx have been committed.  For example, it marks
         modified and added files as normal in the dirstate.
 
         """
 
     def dirty(self, missing=False, merge=True, branch=True):
         return False
 
 
 class workingctx(committablectx):
     """A workingctx object makes access to data related to
     the current working directory convenient.
     date - any valid date string or (unixtime, offset), or None.
     user - username string, or None.
     extra - a dictionary of extra values, or None.
     changes - a list of file lists as returned by localrepo.status()
                or None to use the repository status.
     """
 
     def __init__(
         self, repo, text=b"", user=None, date=None, extra=None, changes=None
     ):
         branch = None
         if not extra or b'branch' not in extra:
             try:
                 branch = repo.dirstate.branch()
             except UnicodeDecodeError:
                 raise error.Abort(_(b'branch name not in UTF-8!'))
         super(workingctx, self).__init__(
             repo, text, user, date, extra, changes, branch=branch
         )
 
     def __iter__(self):
         d = self._repo.dirstate
         for f in d:
             if d[f] != b'r':
                 yield f
 
     def __contains__(self, key):
         return self._repo.dirstate[key] not in b"?r"
 
     def hex(self):
         return wdirhex
 
     @propertycache
     def _parents(self):
         p = self._repo.dirstate.parents()
         if p[1] == nullid:
             p = p[:-1]
         # use unfiltered repo to delay/avoid loading obsmarkers
         unfi = self._repo.unfiltered()
         return [changectx(self._repo, unfi.changelog.rev(n), n) for n in p]
 
     def _fileinfo(self, path):
         # populate __dict__['_manifest'] as workingctx has no _manifestdelta
         self._manifest
         return super(workingctx, self)._fileinfo(path)
 
     def _buildflagfunc(self):
         # Create a fallback function for getting file flags when the
         # filesystem doesn't support them
 
         copiesget = self._repo.dirstate.copies().get
         parents = self.parents()
         if len(parents) < 2:
             # when we have one parent, it's easy: copy from parent
             man = parents[0].manifest()
 
             def func(f):
                 f = copiesget(f, f)
                 return man.flags(f)
 
         else:
             # merges are tricky: we try to reconstruct the unstored
             # result from the merge (issue1802)
             p1, p2 = parents
             pa = p1.ancestor(p2)
             m1, m2, ma = p1.manifest(), p2.manifest(), pa.manifest()
 
             def func(f):
                 f = copiesget(f, f)  # may be wrong for merges with copies
                 fl1, fl2, fla = m1.flags(f), m2.flags(f), ma.flags(f)
                 if fl1 == fl2:
                     return fl1
                 if fl1 == fla:
                     return fl2
                 if fl2 == fla:
                     return fl1
                 return b''  # punt for conflicts
 
         return func
 
     @propertycache
     def _flagfunc(self):
         return self._repo.dirstate.flagfunc(self._buildflagfunc)
 
     def flags(self, path):
         if r'_manifest' in self.__dict__:
             try:
                 return self._manifest.flags(path)
             except KeyError:
                 return b''
 
         try:
             return self._flagfunc(path)
         except OSError:
             return b''
 
     def filectx(self, path, filelog=None):
         """get a file context from the working directory"""
         return workingfilectx(
             self._repo, path, workingctx=self, filelog=filelog
         )
 
     def dirty(self, missing=False, merge=True, branch=True):
         b"check whether a working directory is modified"
         # check subrepos first
         for s in sorted(self.substate):
             if self.sub(s).dirty(missing=missing):
                 return True
         # check current working dir
         return (
             (merge and self.p2())
             or (branch and self.branch() != self.p1().branch())
             or self.modified()
             or self.added()
             or self.removed()
             or (missing and self.deleted())
         )
 
     def add(self, list, prefix=b""):
         with self._repo.wlock():
             ui, ds = self._repo.ui, self._repo.dirstate
             uipath = lambda f: ds.pathto(pathutil.join(prefix, f))
             rejected = []
             lstat = self._repo.wvfs.lstat
             for f in list:
                 # ds.pathto() returns an absolute file when this is invoked from
                 # the keyword extension.  That gets flagged as non-portable on
                 # Windows, since it contains the drive letter and colon.
                 scmutil.checkportable(ui, os.path.join(prefix, f))
                 try:
                     st = lstat(f)
                 except OSError:
                     ui.warn(_(b"%s does not exist!\n") % uipath(f))
                     rejected.append(f)
                     continue
                 limit = ui.configbytes(b'ui', b'large-file-limit')
                 if limit != 0 and st.st_size > limit:
                     ui.warn(
                         _(
                             b"%s: up to %d MB of RAM may be required "
                             b"to manage this file\n"
                             b"(use 'hg revert %s' to cancel the "
                             b"pending addition)\n"
                         )
                         % (f, 3 * st.st_size // 1000000, uipath(f))
                     )
                 if not (stat.S_ISREG(st.st_mode) or stat.S_ISLNK(st.st_mode)):
                     ui.warn(
                         _(
                             b"%s not added: only files and symlinks "
                             b"supported currently\n"
                         )
                         % uipath(f)
                     )
                     rejected.append(f)
                 elif ds[f] in b'amn':
                     ui.warn(_(b"%s already tracked!\n") % uipath(f))
                 elif ds[f] == b'r':
                     ds.normallookup(f)
                 else:
                     ds.add(f)
             return rejected
 
     def forget(self, files, prefix=b""):
         with self._repo.wlock():
             ds = self._repo.dirstate
             uipath = lambda f: ds.pathto(pathutil.join(prefix, f))
             rejected = []
             for f in files:
                 if f not in ds:
                     self._repo.ui.warn(_(b"%s not tracked!\n") % uipath(f))
                     rejected.append(f)
                 elif ds[f] != b'a':
                     ds.remove(f)
                 else:
                     ds.drop(f)
             return rejected
 
     def copy(self, source, dest):
         try:
             st = self._repo.wvfs.lstat(dest)
         except OSError as err:
             if err.errno != errno.ENOENT:
                 raise
             self._repo.ui.warn(
                 _(b"%s does not exist!\n") % self._repo.dirstate.pathto(dest)
             )
             return
         if not (stat.S_ISREG(st.st_mode) or stat.S_ISLNK(st.st_mode)):
             self._repo.ui.warn(
                 _(b"copy failed: %s is not a file or a symbolic link\n")
                 % self._repo.dirstate.pathto(dest)
             )
         else:
             with self._repo.wlock():
                 ds = self._repo.dirstate
                 if ds[dest] in b'?':
                     ds.add(dest)
                 elif ds[dest] in b'r':
                     ds.normallookup(dest)
                 ds.copy(source, dest)
 
     def match(
         self,
         pats=None,
         include=None,
         exclude=None,
         default=b'glob',
         listsubrepos=False,
         badfn=None,
     ):
         r = self._repo
 
         # Only a case insensitive filesystem needs magic to translate user input
         # to actual case in the filesystem.
         icasefs = not util.fscasesensitive(r.root)
         return matchmod.match(
             r.root,
             r.getcwd(),
             pats,
             include,
             exclude,
             default,
             auditor=r.auditor,
             ctx=self,
             listsubrepos=listsubrepos,
             badfn=badfn,
             icasefs=icasefs,
         )
 
     def _filtersuspectsymlink(self, files):
         if not files or self._repo.dirstate._checklink:
             return files
 
         # Symlink placeholders may get non-symlink-like contents
         # via user error or dereferencing by NFS or Samba servers,
         # so we filter out any placeholders that don't look like a
         # symlink
         sane = []
         for f in files:
             if self.flags(f) == b'l':
                 d = self[f].data()
                 if (
                     d == b''
                     or len(d) >= 1024
                     or b'\n' in d
                     or stringutil.binary(d)
                 ):
                     self._repo.ui.debug(
                         b'ignoring suspect symlink placeholder "%s"\n' % f
                     )
                     continue
             sane.append(f)
         return sane
 
     def _checklookup(self, files):
         # check for any possibly clean files
         if not files:
             return [], [], []
 
         modified = []
         deleted = []
         fixup = []
         pctx = self._parents[0]
         # do a full compare of any files that might have changed
         for f in sorted(files):
             try:
                 # This will return True for a file that got replaced by a
                 # directory in the interim, but fixing that is pretty hard.
                 if (
                     f not in pctx
                     or self.flags(f) != pctx.flags(f)
                     or pctx[f].cmp(self[f])
                 ):
                     modified.append(f)
                 else:
                     fixup.append(f)
             except (IOError, OSError):
                 # A file become inaccessible in between? Mark it as deleted,
                 # matching dirstate behavior (issue5584).
                 # The dirstate has more complex behavior around whether a
                 # missing file matches a directory, etc, but we don't need to
                 # bother with that: if f has made it to this point, we're sure
                 # it's in the dirstate.
                 deleted.append(f)
 
         return modified, deleted, fixup
 
     def _poststatusfixup(self, status, fixup):
         """update dirstate for files that are actually clean"""
         poststatus = self._repo.postdsstatus()
         if fixup or poststatus:
             try:
                 oldid = self._repo.dirstate.identity()
 
                 # updating the dirstate is optional
                 # so we don't wait on the lock
                 # wlock can invalidate the dirstate, so cache normal _after_
                 # taking the lock
                 with self._repo.wlock(False):
                     if self._repo.dirstate.identity() == oldid:
                         if fixup:
                             normal = self._repo.dirstate.normal
                             for f in fixup:
                                 normal(f)
                             # write changes out explicitly, because nesting
                             # wlock at runtime may prevent 'wlock.release()'
                             # after this block from doing so for subsequent
                             # changing files
                             tr = self._repo.currenttransaction()
                             self._repo.dirstate.write(tr)
 
                         if poststatus:
                             for ps in poststatus:
                                 ps(self, status)
                     else:
                         # in this case, writing changes out breaks
                         # consistency, because .hg/dirstate was
                         # already changed simultaneously after last
                         # caching (see also issue5584 for detail)
                         self._repo.ui.debug(
                             b'skip updating dirstate: identity mismatch\n'
                         )
             except error.LockError:
                 pass
             finally:
                 # Even if the wlock couldn't be grabbed, clear out the list.
                 self._repo.clearpostdsstatus()
 
     def _dirstatestatus(self, match, ignored=False, clean=False, unknown=False):
         '''Gets the status from the dirstate -- internal use only.'''
         subrepos = []
         if b'.hgsub' in self:
             subrepos = sorted(self.substate)
         cmp, s = self._repo.dirstate.status(
             match, subrepos, ignored=ignored, clean=clean, unknown=unknown
         )
 
         # check for any possibly clean files
         fixup = []
         if cmp:
             modified2, deleted2, fixup = self._checklookup(cmp)
             s.modified.extend(modified2)
             s.deleted.extend(deleted2)
 
             if fixup and clean:
                 s.clean.extend(fixup)
 
         self._poststatusfixup(s, fixup)
 
         if match.always():
             # cache for performance
             if s.unknown or s.ignored or s.clean:
                 # "_status" is cached with list*=False in the normal route
                 self._status = scmutil.status(
                     s.modified, s.added, s.removed, s.deleted, [], [], []
                 )
             else:
                 self._status = s
 
         return s
 
     @propertycache
     def _copies(self):
         p1copies = {}
         p2copies = {}
         parents = self._repo.dirstate.parents()
         p1manifest = self._repo[parents[0]].manifest()
         p2manifest = self._repo[parents[1]].manifest()
         changedset = set(self.added()) | set(self.modified())
         narrowmatch = self._repo.narrowmatch()
         for dst, src in self._repo.dirstate.copies().items():
             if dst not in changedset or not narrowmatch(dst):
                 continue
             if src in p1manifest:
                 p1copies[dst] = src
             elif src in p2manifest:
                 p2copies[dst] = src
         return p1copies, p2copies
 
     @propertycache
     def _manifest(self):
         """generate a manifest corresponding to the values in self._status
 
         This reuse the file nodeid from parent, but we use special node
         identifiers for added and modified files. This is used by manifests
         merge to see that files are different and by update logic to avoid
         deleting newly added files.
         """
         return self._buildstatusmanifest(self._status)
 
     def _buildstatusmanifest(self, status):
         """Builds a manifest that includes the given status results."""
         parents = self.parents()
 
         man = parents[0].manifest().copy()
 
         ff = self._flagfunc
         for i, l in (
             (addednodeid, status.added),
             (modifiednodeid, status.modified),
         ):
             for f in l:
                 man[f] = i
                 try:
                     man.setflag(f, ff(f))
                 except OSError:
                     pass
 
         for f in status.deleted + status.removed:
             if f in man:
                 del man[f]
 
         return man
 
     def _buildstatus(
         self, other, s, match, listignored, listclean, listunknown
     ):
         """build a status with respect to another context
 
         This includes logic for maintaining the fast path of status when
         comparing the working directory against its parent, which is to skip
         building a new manifest if self (working directory) is not comparing
         against its parent (repo['.']).
         """
         s = self._dirstatestatus(match, listignored, listclean, listunknown)
         # Filter out symlinks that, in the case of FAT32 and NTFS filesystems,
         # might have accidentally ended up with the entire contents of the file
         # they are supposed to be linking to.
         s.modified[:] = self._filtersuspectsymlink(s.modified)
         if other != self._repo[b'.']:
             s = super(workingctx, self)._buildstatus(
                 other, s, match, listignored, listclean, listunknown
             )
         return s
 
     def _matchstatus(self, other, match):
         """override the match method with a filter for directory patterns
 
         We use inheritance to customize the match.bad method only in cases of
         workingctx since it belongs only to the working directory when
         comparing against the parent changeset.
 
         If we aren't comparing against the working directory's parent, then we
         just use the default match object sent to us.
         """
         if other != self._repo[b'.']:
 
             def bad(f, msg):
                 # 'f' may be a directory pattern from 'match.files()',
                 # so 'f not in ctx1' is not enough
                 if f not in other and not other.hasdir(f):
                     self._repo.ui.warn(
                         b'%s: %s\n' % (self._repo.dirstate.pathto(f), msg)
                     )
 
             match.bad = bad
         return match
 
     def walk(self, match):
         '''Generates matching file names.'''
         return sorted(
             self._repo.dirstate.walk(
                 self._repo.narrowmatch(match),
                 subrepos=sorted(self.substate),
                 unknown=True,
                 ignored=False,
             )
         )
 
     def matches(self, match):
         match = self._repo.narrowmatch(match)
         ds = self._repo.dirstate
         return sorted(f for f in ds.matches(match) if ds[f] != b'r')
 
     def markcommitted(self, node):
         with self._repo.dirstate.parentchange():
             for f in self.modified() + self.added():
                 self._repo.dirstate.normal(f)
             for f in self.removed():
                 self._repo.dirstate.drop(f)
             self._repo.dirstate.setparents(node)
 
         # write changes out explicitly, because nesting wlock at
         # runtime may prevent 'wlock.release()' in 'repo.commit()'
         # from immediately doing so for subsequent changing files
         self._repo.dirstate.write(self._repo.currenttransaction())
 
         sparse.aftercommit(self._repo, node)
 
 
 class committablefilectx(basefilectx):
     """A committablefilectx provides common functionality for a file context
     that wants the ability to commit, e.g. workingfilectx or memfilectx."""
 
     def __init__(self, repo, path, filelog=None, ctx=None):
         self._repo = repo
         self._path = path
         self._changeid = None
         self._filerev = self._filenode = None
 
         if filelog is not None:
             self._filelog = filelog
         if ctx:
             self._changectx = ctx
 
     def __nonzero__(self):
         return True
 
     __bool__ = __nonzero__
 
     def linkrev(self):
         # linked to self._changectx no matter if file is modified or not
         return self.rev()
 
     def renamed(self):
         path = self.copysource()
         if not path:
             return None
         return path, self._changectx._parents[0]._manifest.get(path, nullid)
 
     def parents(self):
         '''return parent filectxs, following copies if necessary'''
 
         def filenode(ctx, path):
             return ctx._manifest.get(path, nullid)
 
         path = self._path
         fl = self._filelog
         pcl = self._changectx._parents
         renamed = self.renamed()
 
         if renamed:
             pl = [renamed + (None,)]
         else:
             pl = [(path, filenode(pcl[0], path), fl)]
 
         for pc in pcl[1:]:
             pl.append((path, filenode(pc, path), fl))
 
         return [
             self._parentfilectx(p, fileid=n, filelog=l)
             for p, n, l in pl
             if n != nullid
         ]
 
     def children(self):
         return []
 
 
 class workingfilectx(committablefilectx):
     """A workingfilectx object makes access to data related to a particular
        file in the working directory convenient."""
 
     def __init__(self, repo, path, filelog=None, workingctx=None):
         super(workingfilectx, self).__init__(repo, path, filelog, workingctx)
 
     @propertycache
     def _changectx(self):
         return workingctx(self._repo)
 
     def data(self):
         return self._repo.wread(self._path)
 
     def copysource(self):
         return self._repo.dirstate.copied(self._path)
 
     def size(self):
         return self._repo.wvfs.lstat(self._path).st_size
 
     def lstat(self):
         return self._repo.wvfs.lstat(self._path)
 
     def date(self):
         t, tz = self._changectx.date()
         try:
             return (self._repo.wvfs.lstat(self._path)[stat.ST_MTIME], tz)
         except OSError as err:
             if err.errno != errno.ENOENT:
                 raise
             return (t, tz)
 
     def exists(self):
         return self._repo.wvfs.exists(self._path)
 
     def lexists(self):
         return self._repo.wvfs.lexists(self._path)
 
     def audit(self):
         return self._repo.wvfs.audit(self._path)
 
     def cmp(self, fctx):
         """compare with other file context
 
         returns True if different than fctx.
         """
         # fctx should be a filectx (not a workingfilectx)
         # invert comparison to reuse the same code path
         return fctx.cmp(self)
 
     def remove(self, ignoremissing=False):
         """wraps unlink for a repo's working directory"""
         rmdir = self._repo.ui.configbool(b'experimental', b'removeemptydirs')
         self._repo.wvfs.unlinkpath(
             self._path, ignoremissing=ignoremissing, rmdir=rmdir
         )
 
     def write(self, data, flags, backgroundclose=False, **kwargs):
         """wraps repo.wwrite"""
         return self._repo.wwrite(
             self._path, data, flags, backgroundclose=backgroundclose, **kwargs
         )
 
     def markcopied(self, src):
         """marks this file a copy of `src`"""
         self._repo.dirstate.copy(src, self._path)
 
     def clearunknown(self):
         """Removes conflicting items in the working directory so that
         ``write()`` can be called successfully.
         """
         wvfs = self._repo.wvfs
         f = self._path
         wvfs.audit(f)
         if self._repo.ui.configbool(
             b'experimental', b'merge.checkpathconflicts'
         ):
             # remove files under the directory as they should already be
             # warned and backed up
             if wvfs.isdir(f) and not wvfs.islink(f):
                 wvfs.rmtree(f, forcibly=True)
             for p in reversed(list(util.finddirs(f))):
                 if wvfs.isfileorlink(p):
                     wvfs.unlink(p)
                     break
         else:
             # don't remove files if path conflicts are not processed
             if wvfs.isdir(f) and not wvfs.islink(f):
                 wvfs.removedirs(f)
 
     def setflags(self, l, x):
         self._repo.wvfs.setflags(self._path, l, x)
 
 
 class overlayworkingctx(committablectx):
     """Wraps another mutable context with a write-back cache that can be
     converted into a commit context.
 
     self._cache[path] maps to a dict with keys: {
         'exists': bool?
         'date': date?
         'data': str?
         'flags': str?
         'copied': str? (path or None)
     }
     If `exists` is True, `flags` must be non-None and 'date' is non-None. If it
     is `False`, the file was deleted.
     """
 
     def __init__(self, repo):
         super(overlayworkingctx, self).__init__(repo)
         self.clean()
 
     def setbase(self, wrappedctx):
         self._wrappedctx = wrappedctx
         self._parents = [wrappedctx]
         # Drop old manifest cache as it is now out of date.
         # This is necessary when, e.g., rebasing several nodes with one
         # ``overlayworkingctx`` (e.g. with --collapse).
         util.clearcachedproperty(self, b'_manifest')
 
     def data(self, path):
         if self.isdirty(path):
             if self._cache[path][b'exists']:
                 if self._cache[path][b'data'] is not None:
                     return self._cache[path][b'data']
                 else:
                     # Must fallback here, too, because we only set flags.
                     return self._wrappedctx[path].data()
             else:
                 raise error.ProgrammingError(
                     b"No such file or directory: %s" % path
                 )
         else:
             return self._wrappedctx[path].data()
 
     @propertycache
     def _manifest(self):
         parents = self.parents()
         man = parents[0].manifest().copy()
 
         flag = self._flagfunc
         for path in self.added():
             man[path] = addednodeid
             man.setflag(path, flag(path))
         for path in self.modified():
             man[path] = modifiednodeid
             man.setflag(path, flag(path))
         for path in self.removed():
             del man[path]
         return man
 
     @propertycache
     def _flagfunc(self):
         def f(path):
             return self._cache[path][b'flags']
 
         return f
 
     def files(self):
         return sorted(self.added() + self.modified() + self.removed())
 
     def modified(self):
         return [
             f
             for f in self._cache.keys()
             if self._cache[f][b'exists'] and self._existsinparent(f)
         ]
 
     def added(self):
         return [
             f
             for f in self._cache.keys()
             if self._cache[f][b'exists'] and not self._existsinparent(f)
         ]
 
     def removed(self):
         return [
             f
             for f in self._cache.keys()
             if not self._cache[f][b'exists'] and self._existsinparent(f)
         ]
 
     def p1copies(self):
         copies = self._repo._wrappedctx.p1copies().copy()
         narrowmatch = self._repo.narrowmatch()
         for f in self._cache.keys():
             if not narrowmatch(f):
                 continue
             copies.pop(f, None)  # delete if it exists
             source = self._cache[f][b'copied']
             if source:
                 copies[f] = source
         return copies
 
     def p2copies(self):
         copies = self._repo._wrappedctx.p2copies().copy()
         narrowmatch = self._repo.narrowmatch()
         for f in self._cache.keys():
             if not narrowmatch(f):
                 continue
             copies.pop(f, None)  # delete if it exists
             source = self._cache[f][b'copied']
             if source:
                 copies[f] = source
         return copies
 
     def isinmemory(self):
         return True
 
     def filedate(self, path):
         if self.isdirty(path):
             return self._cache[path][b'date']
         else:
             return self._wrappedctx[path].date()
 
     def markcopied(self, path, origin):
         self._markdirty(
             path,
             exists=True,
             date=self.filedate(path),
             flags=self.flags(path),
             copied=origin,
         )
 
     def copydata(self, path):
         if self.isdirty(path):
             return self._cache[path][b'copied']
         else:
             return None
 
     def flags(self, path):
         if self.isdirty(path):
             if self._cache[path][b'exists']:
                 return self._cache[path][b'flags']
             else:
                 raise error.ProgrammingError(
                     b"No such file or directory: %s" % self._path
                 )
         else:
             return self._wrappedctx[path].flags()
 
     def __contains__(self, key):
         if key in self._cache:
             return self._cache[key][b'exists']
         return key in self.p1()
 
     def _existsinparent(self, path):
         try:
             # ``commitctx` raises a ``ManifestLookupError`` if a path does not
             # exist, unlike ``workingctx``, which returns a ``workingfilectx``
             # with an ``exists()`` function.
             self._wrappedctx[path]
             return True
         except error.ManifestLookupError:
             return False
 
     def _auditconflicts(self, path):
         """Replicates conflict checks done by wvfs.write().
 
         Since we never write to the filesystem and never call `applyupdates` in
         IMM, we'll never check that a path is actually writable -- e.g., because
         it adds `a/foo`, but `a` is actually a file in the other commit.
         """
 
         def fail(path, component):
             # p1() is the base and we're receiving "writes" for p2()'s
             # files.
             if b'l' in self.p1()[component].flags():
                 raise error.Abort(
                     b"error: %s conflicts with symlink %s "
                     b"in %d." % (path, component, self.p1().rev())
                 )
             else:
                 raise error.Abort(
                     b"error: '%s' conflicts with file '%s' in "
                     b"%d." % (path, component, self.p1().rev())
                 )
 
         # Test that each new directory to be created to write this path from p2
         # is not a file in p1.
         components = path.split(b'/')
         for i in pycompat.xrange(len(components)):
             component = b"/".join(components[0:i])
             if component in self:
                 fail(path, component)
 
         # Test the other direction -- that this path from p2 isn't a directory
         # in p1 (test that p1 doesn't have any paths matching `path/*`).
         match = self.match([path], default=b'path')
         matches = self.p1().manifest().matches(match)
         mfiles = matches.keys()
         if len(mfiles) > 0:
             if len(mfiles) == 1 and mfiles[0] == path:
                 return
             # omit the files which are deleted in current IMM wctx
             mfiles = [m for m in mfiles if m in self]
             if not mfiles:
                 return
             raise error.Abort(
                 b"error: file '%s' cannot be written because "
                 b" '%s/' is a directory in %s (containing %d "
                 b"entries: %s)"
                 % (path, path, self.p1(), len(mfiles), b', '.join(mfiles))
             )
 
     def write(self, path, data, flags=b'', **kwargs):
         if data is None:
             raise error.ProgrammingError(b"data must be non-None")
         self._auditconflicts(path)
         self._markdirty(
             path, exists=True, data=data, date=dateutil.makedate(), flags=flags
         )
 
     def setflags(self, path, l, x):
         flag = b''
         if l:
             flag = b'l'
         elif x:
             flag = b'x'
         self._markdirty(path, exists=True, date=dateutil.makedate(), flags=flag)
 
     def remove(self, path):
         self._markdirty(path, exists=False)
 
     def exists(self, path):
         """exists behaves like `lexists`, but needs to follow symlinks and
         return False if they are broken.
         """
         if self.isdirty(path):
             # If this path exists and is a symlink, "follow" it by calling
             # exists on the destination path.
             if (
                 self._cache[path][b'exists']
                 and b'l' in self._cache[path][b'flags']
             ):
                 return self.exists(self._cache[path][b'data'].strip())
             else:
                 return self._cache[path][b'exists']
 
         return self._existsinparent(path)
 
     def lexists(self, path):
         """lexists returns True if the path exists"""
         if self.isdirty(path):
             return self._cache[path][b'exists']
 
         return self._existsinparent(path)
 
     def size(self, path):
         if self.isdirty(path):
             if self._cache[path][b'exists']:
                 return len(self._cache[path][b'data'])
             else:
                 raise error.ProgrammingError(
                     b"No such file or directory: %s" % self._path
                 )
         return self._wrappedctx[path].size()
 
     def tomemctx(
         self,
         text,
         branch=None,
         extra=None,
         date=None,
         parents=None,
         user=None,
         editor=None,
     ):
         """Converts this ``overlayworkingctx`` into a ``memctx`` ready to be
         committed.
 
         ``text`` is the commit message.
         ``parents`` (optional) are rev numbers.
         """
         # Default parents to the wrapped contexts' if not passed.
         if parents is None:
             parents = self._wrappedctx.parents()
             if len(parents) == 1:
                 parents = (parents[0], None)
 
         # ``parents`` is passed as rev numbers; convert to ``commitctxs``.
         if parents[1] is None:
             parents = (self._repo[parents[0]], None)
         else:
             parents = (self._repo[parents[0]], self._repo[parents[1]])
 
         files = self.files()
 
         def getfile(repo, memctx, path):
             if self._cache[path][b'exists']:
                 return memfilectx(
                     repo,
                     memctx,
                     path,
                     self._cache[path][b'data'],
                     b'l' in self._cache[path][b'flags'],
                     b'x' in self._cache[path][b'flags'],
                     self._cache[path][b'copied'],
                 )
             else:
                 # Returning None, but including the path in `files`, is
                 # necessary for memctx to register a deletion.
                 return None
 
         return memctx(
             self._repo,
             parents,
             text,
             files,
             getfile,
             date=date,
             extra=extra,
             user=user,
             branch=branch,
             editor=editor,
         )
 
     def isdirty(self, path):
         return path in self._cache
 
     def isempty(self):
         # We need to discard any keys that are actually clean before the empty
         # commit check.
         self._compact()
         return len(self._cache) == 0
 
     def clean(self):
         self._cache = {}
 
     def _compact(self):
         """Removes keys from the cache that are actually clean, by comparing
         them with the underlying context.
 
         This can occur during the merge process, e.g. by passing --tool :local
         to resolve a conflict.
         """
         keys = []
         # This won't be perfect, but can help performance significantly when
         # using things like remotefilelog.
         scmutil.prefetchfiles(
             self.repo(),
             [self.p1().rev()],
             scmutil.matchfiles(self.repo(), self._cache.keys()),
         )
 
         for path in self._cache.keys():
             cache = self._cache[path]
             try:
                 underlying = self._wrappedctx[path]
                 if (
                     underlying.data() == cache[b'data']
                     and underlying.flags() == cache[b'flags']
                 ):
                     keys.append(path)
             except error.ManifestLookupError:
                 # Path not in the underlying manifest (created).
                 continue
 
         for path in keys:
             del self._cache[path]
         return keys
 
     def _markdirty(
         self, path, exists, data=None, date=None, flags=b'', copied=None
     ):
         # data not provided, let's see if we already have some; if not, let's
         # grab it from our underlying context, so that we always have data if
         # the file is marked as existing.
         if exists and data is None:
             oldentry = self._cache.get(path) or {}
             data = oldentry.get(b'data')
             if data is None:
                 data = self._wrappedctx[path].data()
 
         self._cache[path] = {
             b'exists': exists,
             b'data': data,
             b'date': date,
             b'flags': flags,
             b'copied': copied,
         }
 
     def filectx(self, path, filelog=None):
         return overlayworkingfilectx(
             self._repo, path, parent=self, filelog=filelog
         )
 
 
 class overlayworkingfilectx(committablefilectx):
     """Wrap a ``workingfilectx`` but intercepts all writes into an in-memory
     cache, which can be flushed through later by calling ``flush()``."""
 
     def __init__(self, repo, path, filelog=None, parent=None):
         super(overlayworkingfilectx, self).__init__(repo, path, filelog, parent)
         self._repo = repo
         self._parent = parent
         self._path = path
 
     def cmp(self, fctx):
         return self.data() != fctx.data()
 
     def changectx(self):
         return self._parent
 
     def data(self):
         return self._parent.data(self._path)
 
     def date(self):
         return self._parent.filedate(self._path)
 
     def exists(self):
         return self.lexists()
 
     def lexists(self):
         return self._parent.exists(self._path)
 
     def copysource(self):
         return self._parent.copydata(self._path)
 
     def size(self):
         return self._parent.size(self._path)
 
     def markcopied(self, origin):
         self._parent.markcopied(self._path, origin)
 
     def audit(self):
         pass
 
     def flags(self):
         return self._parent.flags(self._path)
 
     def setflags(self, islink, isexec):
         return self._parent.setflags(self._path, islink, isexec)
 
     def write(self, data, flags, backgroundclose=False, **kwargs):
         return self._parent.write(self._path, data, flags, **kwargs)
 
     def remove(self, ignoremissing=False):
         return self._parent.remove(self._path)
 
     def clearunknown(self):
         pass
 
 
 class workingcommitctx(workingctx):
     """A workingcommitctx object makes access to data related to
     the revision being committed convenient.
 
     This hides changes in the working directory, if they aren't
     committed in this context.
     """
 
     def __init__(
         self, repo, changes, text=b"", user=None, date=None, extra=None
     ):
         super(workingcommitctx, self).__init__(
             repo, text, user, date, extra, changes
         )
 
     def _dirstatestatus(self, match, ignored=False, clean=False, unknown=False):
         """Return matched files only in ``self._status``
 
         Uncommitted files appear "clean" via this context, even if
         they aren't actually so in the working directory.
         """
         if clean:
             clean = [f for f in self._manifest if f not in self._changedset]
         else:
             clean = []
         return scmutil.status(
             [f for f in self._status.modified if match(f)],
             [f for f in self._status.added if match(f)],
             [f for f in self._status.removed if match(f)],
             [],
             [],
             [],
             clean,
         )
 
     @propertycache
     def _changedset(self):
         """Return the set of files changed in this context
         """
         changed = set(self._status.modified)
         changed.update(self._status.added)
         changed.update(self._status.removed)
         return changed
 
 
 def makecachingfilectxfn(func):
     """Create a filectxfn that caches based on the path.
 
     We can't use util.cachefunc because it uses all arguments as the cache
     key and this creates a cycle since the arguments include the repo and
     memctx.
     """
     cache = {}
 
     def getfilectx(repo, memctx, path):
         if path not in cache:
             cache[path] = func(repo, memctx, path)
         return cache[path]
 
     return getfilectx
 
 
 def memfilefromctx(ctx):
     """Given a context return a memfilectx for ctx[path]
 
     This is a convenience method for building a memctx based on another
     context.
     """
 
     def getfilectx(repo, memctx, path):
         fctx = ctx[path]
         copysource = fctx.copysource()
         return memfilectx(
             repo,
             memctx,
             path,
             fctx.data(),
             islink=fctx.islink(),
             isexec=fctx.isexec(),
             copysource=copysource,
         )
 
     return getfilectx
 
 
 def memfilefrompatch(patchstore):
     """Given a patch (e.g. patchstore object) return a memfilectx
 
     This is a convenience method for building a memctx based on a patchstore.
     """
 
     def getfilectx(repo, memctx, path):
         data, mode, copysource = patchstore.getfile(path)
         if data is None:
             return None
         islink, isexec = mode
         return memfilectx(
             repo,
             memctx,
             path,
             data,
             islink=islink,
             isexec=isexec,
             copysource=copysource,
         )
 
     return getfilectx
 
 
 class memctx(committablectx):
     """Use memctx to perform in-memory commits via localrepo.commitctx().
 
     Revision information is supplied at initialization time while
     related files data and is made available through a callback
     mechanism.  'repo' is the current localrepo, 'parents' is a
     sequence of two parent revisions identifiers (pass None for every
     missing parent), 'text' is the commit message and 'files' lists
     names of files touched by the revision (normalized and relative to
     repository root).
 
     filectxfn(repo, memctx, path) is a callable receiving the
     repository, the current memctx object and the normalized path of
     requested file, relative to repository root. It is fired by the
     commit function for every file in 'files', but calls order is
     undefined. If the file is available in the revision being
     committed (updated or added), filectxfn returns a memfilectx
     object. If the file was removed, filectxfn return None for recent
     Mercurial. Moved files are represented by marking the source file
     removed and the new file added with copy information (see
     memfilectx).
 
     user receives the committer name and defaults to current
     repository username, date is the commit date in any format
     supported by dateutil.parsedate() and defaults to current date, extra
     is a dictionary of metadata or is left empty.
     """
 
     # Mercurial <= 3.1 expects the filectxfn to raise IOError for missing files.
     # Extensions that need to retain compatibility across Mercurial 3.1 can use
     # this field to determine what to do in filectxfn.
     _returnnoneformissingfiles = True
 
     def __init__(
         self,
         repo,
         parents,
         text,
         files,
         filectxfn,
         user=None,
         date=None,
         extra=None,
         branch=None,
         editor=False,
     ):
         super(memctx, self).__init__(
             repo, text, user, date, extra, branch=branch
         )
         self._rev = None
         self._node = None
         parents = [(p or nullid) for p in parents]
         p1, p2 = parents
         self._parents = [self._repo[p] for p in (p1, p2)]
         files = sorted(set(files))
         self._files = files
         self.substate = {}
 
         if isinstance(filectxfn, patch.filestore):
             filectxfn = memfilefrompatch(filectxfn)
         elif not callable(filectxfn):
             # if store is not callable, wrap it in a function
             filectxfn = memfilefromctx(filectxfn)
 
         # memoizing increases performance for e.g. vcs convert scenarios.
         self._filectxfn = makecachingfilectxfn(filectxfn)
 
         if editor:
             self._text = editor(self._repo, self, [])
             self._repo.savecommitmessage(self._text)
 
     def filectx(self, path, filelog=None):
         """get a file context from the working directory
 
         Returns None if file doesn't exist and should be removed."""
         return self._filectxfn(self._repo, self, path)
 
     def commit(self):
         """commit context to the repo"""
         return self._repo.commitctx(self)
 
     @propertycache
     def _manifest(self):
         """generate a manifest based on the return values of filectxfn"""
 
         # keep this simple for now; just worry about p1
         pctx = self._parents[0]
         man = pctx.manifest().copy()
 
         for f in self._status.modified:
             man[f] = modifiednodeid
 
         for f in self._status.added:
             man[f] = addednodeid
 
         for f in self._status.removed:
             if f in man:
                 del man[f]
 
         return man
 
     @propertycache
     def _status(self):
         """Calculate exact status from ``files`` specified at construction
         """
         man1 = self.p1().manifest()
         p2 = self._parents[1]
         # "1 < len(self._parents)" can't be used for checking
         # existence of the 2nd parent, because "memctx._parents" is
         # explicitly initialized by the list, of which length is 2.
         if p2.node() != nullid:
             man2 = p2.manifest()
             managing = lambda f: f in man1 or f in man2
         else:
             managing = lambda f: f in man1
 
         modified, added, removed = [], [], []
         for f in self._files:
             if not managing(f):
                 added.append(f)
             elif self[f]:
                 modified.append(f)
             else:
                 removed.append(f)
 
         return scmutil.status(modified, added, removed, [], [], [], [])
 
 
 class memfilectx(committablefilectx):
     """memfilectx represents an in-memory file to commit.
 
     See memctx and committablefilectx for more details.
     """
 
     def __init__(
         self,
         repo,
         changectx,
         path,
         data,
         islink=False,
         isexec=False,
         copysource=None,
     ):
         """
         path is the normalized file path relative to repository root.
         data is the file content as a string.
         islink is True if the file is a symbolic link.
         isexec is True if the file is executable.
         copied is the source file path if current file was copied in the
         revision being committed, or None."""
         super(memfilectx, self).__init__(repo, path, None, changectx)
         self._data = data
         if islink:
             self._flags = b'l'
         elif isexec:
             self._flags = b'x'
         else:
             self._flags = b''
         self._copysource = copysource
 
     def copysource(self):
         return self._copysource
 
     def cmp(self, fctx):
         return self.data() != fctx.data()
 
     def data(self):
         return self._data
 
     def remove(self, ignoremissing=False):
         """wraps unlink for a repo's working directory"""
         # need to figure out what to do here
         del self._changectx[self._path]
 
     def write(self, data, flags, **kwargs):
         """wraps repo.wwrite"""
         self._data = data
 
 
 class metadataonlyctx(committablectx):
     """Like memctx but it's reusing the manifest of different commit.
     Intended to be used by lightweight operations that are creating
     metadata-only changes.
 
     Revision information is supplied at initialization time.  'repo' is the
     current localrepo, 'ctx' is original revision which manifest we're reuisng
     'parents' is a sequence of two parent revisions identifiers (pass None for
     every missing parent), 'text' is the commit.
 
     user receives the committer name and defaults to current repository
     username, date is the commit date in any format supported by
     dateutil.parsedate() and defaults to current date, extra is a dictionary of
     metadata or is left empty.
     """
 
     def __init__(
         self,
         repo,
         originalctx,
         parents=None,
         text=None,
         user=None,
         date=None,
         extra=None,
         editor=False,
     ):
         if text is None:
             text = originalctx.description()
         super(metadataonlyctx, self).__init__(repo, text, user, date, extra)
         self._rev = None
         self._node = None
         self._originalctx = originalctx
         self._manifestnode = originalctx.manifestnode()
         if parents is None:
             parents = originalctx.parents()
         else:
             parents = [repo[p] for p in parents if p is not None]
         parents = parents[:]
         while len(parents) < 2:
             parents.append(repo[nullid])
         p1, p2 = self._parents = parents
 
         # sanity check to ensure that the reused manifest parents are
         # manifests of our commit parents
         mp1, mp2 = self.manifestctx().parents
         if p1 != nullid and p1.manifestnode() != mp1:
             raise RuntimeError(
                 r"can't reuse the manifest: its p1 "
                 r"doesn't match the new ctx p1"
             )
         if p2 != nullid and p2.manifestnode() != mp2:
             raise RuntimeError(
                 r"can't reuse the manifest: "
                 r"its p2 doesn't match the new ctx p2"
             )
 
         self._files = originalctx.files()
         self.substate = {}
 
         if editor:
             self._text = editor(self._repo, self, [])
             self._repo.savecommitmessage(self._text)
 
     def manifestnode(self):
         return self._manifestnode
 
     @property
     def _manifestctx(self):
         return self._repo.manifestlog[self._manifestnode]
 
     def filectx(self, path, filelog=None):
         return self._originalctx.filectx(path, filelog=filelog)
 
     def commit(self):
         """commit context to the repo"""
         return self._repo.commitctx(self)
 
     @property
     def _manifest(self):
         return self._originalctx.manifest()
 
     @propertycache
     def _status(self):
         """Calculate exact status from ``files`` specified in the ``origctx``
         and parents manifests.
         """
         man1 = self.p1().manifest()
         p2 = self._parents[1]
         # "1 < len(self._parents)" can't be used for checking
         # existence of the 2nd parent, because "metadataonlyctx._parents" is
         # explicitly initialized by the list, of which length is 2.
         if p2.node() != nullid:
             man2 = p2.manifest()
             managing = lambda f: f in man1 or f in man2
         else:
             managing = lambda f: f in man1
 
         modified, added, removed = [], [], []
         for f in self._files:
             if not managing(f):
                 added.append(f)
             elif f in self:
                 modified.append(f)
             else:
                 removed.append(f)
 
         return scmutil.status(modified, added, removed, [], [], [], [])
 
 
 class arbitraryfilectx(object):
     """Allows you to use filectx-like functions on a file in an arbitrary
     location on disk, possibly not in the working directory.
     """
 
     def __init__(self, path, repo=None):
         # Repo is optional because contrib/simplemerge uses this class.
         self._repo = repo
         self._path = path
 
     def cmp(self, fctx):
         # filecmp follows symlinks whereas `cmp` should not, so skip the fast
         # path if either side is a symlink.
         symlinks = b'l' in self.flags() or b'l' in fctx.flags()
         if not symlinks and isinstance(fctx, workingfilectx) and self._repo:
             # Add a fast-path for merge if both sides are disk-backed.
             # Note that filecmp uses the opposite return values (True if same)
             # from our cmp functions (True if different).
             return not filecmp.cmp(self.path(), self._repo.wjoin(fctx.path()))
         return self.data() != fctx.data()
 
     def path(self):
         return self._path
 
     def flags(self):
         return b''
 
     def data(self):
         return util.readfile(self._path)
 
     def decodeddata(self):
         with open(self._path, b"rb") as f:
             return f.read()
 
     def remove(self):
         util.unlink(self._path)
 
     def write(self, data, flags, **kwargs):
         assert not flags
         with open(self._path, b"wb") as f:
             f.write(data)

mercurial/copies.py

@@ -1,879 +1,881 b''
 # copies.py - copy detection for Mercurial
 #
 # Copyright 2008 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import collections
 import heapq
 import os
 
 from .i18n import _
 
 from . import (
     match as matchmod,
     node,
     pathutil,
     pycompat,
     util,
 )
 from .utils import stringutil
 
 
 def _findlimit(repo, ctxa, ctxb):
     """
     Find the last revision that needs to be checked to ensure that a full
     transitive closure for file copies can be properly calculated.
     Generally, this means finding the earliest revision number that's an
     ancestor of a or b but not both, except when a or b is a direct descendent
     of the other, in which case we can return the minimum revnum of a and b.
     """
 
     # basic idea:
     # - mark a and b with different sides
     # - if a parent's children are all on the same side, the parent is
     #   on that side, otherwise it is on no side
     # - walk the graph in topological order with the help of a heap;
     #   - add unseen parents to side map
     #   - clear side of any parent that has children on different sides
     #   - track number of interesting revs that might still be on a side
     #   - track the lowest interesting rev seen
     #   - quit when interesting revs is zero
 
     cl = repo.changelog
     wdirparents = None
     a = ctxa.rev()
     b = ctxb.rev()
     if a is None:
         wdirparents = (ctxa.p1(), ctxa.p2())
         a = node.wdirrev
     if b is None:
         assert not wdirparents
         wdirparents = (ctxb.p1(), ctxb.p2())
         b = node.wdirrev
 
     side = {a: -1, b: 1}
     visit = [-a, -b]
     heapq.heapify(visit)
     interesting = len(visit)
     limit = node.wdirrev
 
     while interesting:
         r = -(heapq.heappop(visit))
         if r == node.wdirrev:
             parents = [pctx.rev() for pctx in wdirparents]
         else:
             parents = cl.parentrevs(r)
         if parents[1] == node.nullrev:
             parents = parents[:1]
         for p in parents:
             if p not in side:
                 # first time we see p; add it to visit
                 side[p] = side[r]
                 if side[p]:
                     interesting += 1
                 heapq.heappush(visit, -p)
             elif side[p] and side[p] != side[r]:
                 # p was interesting but now we know better
                 side[p] = 0
                 interesting -= 1
         if side[r]:
             limit = r  # lowest rev visited
             interesting -= 1
 
     # Consider the following flow (see test-commit-amend.t under issue4405):
     # 1/ File 'a0' committed
     # 2/ File renamed from 'a0' to 'a1' in a new commit (call it 'a1')
     # 3/ Move back to first commit
     # 4/ Create a new commit via revert to contents of 'a1' (call it 'a1-amend')
     # 5/ Rename file from 'a1' to 'a2' and commit --amend 'a1-msg'
     #
     # During the amend in step five, we will be in this state:
     #
     # @  3 temporary amend commit for a1-amend
     # |
     # o  2 a1-amend
     # |
     # | o  1 a1
     # |/
     # o  0 a0
     #
     # When _findlimit is called, a and b are revs 3 and 0, so limit will be 2,
     # yet the filelog has the copy information in rev 1 and we will not look
     # back far enough unless we also look at the a and b as candidates.
     # This only occurs when a is a descendent of b or visa-versa.
     return min(limit, a, b)
 
 
 def _filter(src, dst, t):
     """filters out invalid copies after chaining"""
 
     # When _chain()'ing copies in 'a' (from 'src' via some other commit 'mid')
     # with copies in 'b' (from 'mid' to 'dst'), we can get the different cases
     # in the following table (not including trivial cases). For example, case 2
     # is where a file existed in 'src' and remained under that name in 'mid' and
     # then was renamed between 'mid' and 'dst'.
     #
     # case src mid dst result
     #   1   x   y   -    -
     #   2   x   y   y   x->y
     #   3   x   y   x    -
     #   4   x   y   z   x->z
     #   5   -   x   y    -
     #   6   x   x   y   x->y
     #
     # _chain() takes care of chaining the copies in 'a' and 'b', but it
     # cannot tell the difference between cases 1 and 2, between 3 and 4, or
     # between 5 and 6, so it includes all cases in its result.
     # Cases 1, 3, and 5 are then removed by _filter().
 
     for k, v in list(t.items()):
         # remove copies from files that didn't exist
         if v not in src:
             del t[k]
         # remove criss-crossed copies
         elif k in src and v in dst:
             del t[k]
         # remove copies to files that were then removed
         elif k not in dst:
             del t[k]
 
 
 def _chain(a, b):
     """chain two sets of copies 'a' and 'b'"""
     t = a.copy()
     for k, v in pycompat.iteritems(b):
         if v in t:
             t[k] = t[v]
         else:
             t[k] = v
     return t
 
 
 def _tracefile(fctx, am, basemf, limit):
     """return file context that is the ancestor of fctx present in ancestor
     manifest am, stopping after the first ancestor lower than limit"""
 
     for f in fctx.ancestors():
         path = f.path()
         if am.get(path, None) == f.filenode():
             return path
         if basemf and basemf.get(path, None) == f.filenode():
             return path
         if not f.isintroducedafter(limit):
             return None
 
 
 def _dirstatecopies(repo, match=None):
     ds = repo.dirstate
     c = ds.copies().copy()
     for k in list(c):
         if ds[k] not in b'anm' or (match and not match(k)):
             del c[k]
     return c
 
 
 def _computeforwardmissing(a, b, match=None):
     """Computes which files are in b but not a.
     This is its own function so extensions can easily wrap this call to see what
     files _forwardcopies is about to process.
     """
     ma = a.manifest()
     mb = b.manifest()
     return mb.filesnotin(ma, match=match)
 
 
 def usechangesetcentricalgo(repo):
     """Checks if we should use changeset-centric copy algorithms"""
+    if repo.filecopiesmode == b'changeset-sidedata':
+        return True
     readfrom = repo.ui.config(b'experimental', b'copies.read-from')
     changesetsource = (b'changeset-only', b'compatibility')
     return readfrom in changesetsource
 
 
 def _committedforwardcopies(a, b, base, match):
     """Like _forwardcopies(), but b.rev() cannot be None (working copy)"""
     # files might have to be traced back to the fctx parent of the last
     # one-side-only changeset, but not further back than that
     repo = a._repo
 
     if usechangesetcentricalgo(repo):
         return _changesetforwardcopies(a, b, match)
 
     debug = repo.ui.debugflag and repo.ui.configbool(b'devel', b'debug.copies')
     dbg = repo.ui.debug
     if debug:
         dbg(b'debug.copies:    looking into rename from %s to %s\n' % (a, b))
     limit = _findlimit(repo, a, b)
     if debug:
         dbg(b'debug.copies:      search limit: %d\n' % limit)
     am = a.manifest()
     basemf = None if base is None else base.manifest()
 
     # find where new files came from
     # we currently don't try to find where old files went, too expensive
     # this means we can miss a case like 'hg rm b; hg cp a b'
     cm = {}
 
     # Computing the forward missing is quite expensive on large manifests, since
     # it compares the entire manifests. We can optimize it in the common use
     # case of computing what copies are in a commit versus its parent (like
     # during a rebase or histedit). Note, we exclude merge commits from this
     # optimization, since the ctx.files() for a merge commit is not correct for
     # this comparison.
     forwardmissingmatch = match
     if b.p1() == a and b.p2().node() == node.nullid:
         filesmatcher = matchmod.exact(b.files())
         forwardmissingmatch = matchmod.intersectmatchers(match, filesmatcher)
     missing = _computeforwardmissing(a, b, match=forwardmissingmatch)
 
     ancestrycontext = a._repo.changelog.ancestors([b.rev()], inclusive=True)
 
     if debug:
         dbg(b'debug.copies:      missing files to search: %d\n' % len(missing))
 
     for f in sorted(missing):
         if debug:
             dbg(b'debug.copies:        tracing file: %s\n' % f)
         fctx = b[f]
         fctx._ancestrycontext = ancestrycontext
 
         if debug:
             start = util.timer()
         opath = _tracefile(fctx, am, basemf, limit)
         if opath:
             if debug:
                 dbg(b'debug.copies:          rename of: %s\n' % opath)
             cm[f] = opath
         if debug:
             dbg(
                 b'debug.copies:          time: %f seconds\n'
                 % (util.timer() - start)
             )
     return cm
 
 
 def _changesetforwardcopies(a, b, match):
     if a.rev() in (node.nullrev, b.rev()):
         return {}
 
     repo = a.repo()
     children = {}
     cl = repo.changelog
     missingrevs = cl.findmissingrevs(common=[a.rev()], heads=[b.rev()])
     for r in missingrevs:
         for p in cl.parentrevs(r):
             if p == node.nullrev:
                 continue
             if p not in children:
                 children[p] = [r]
             else:
                 children[p].append(r)
 
     roots = set(children) - set(missingrevs)
     # 'work' contains 3-tuples of a (revision number, parent number, copies).
     # The parent number is only used for knowing which parent the copies dict
     # came from.
     # NOTE: To reduce costly copying the 'copies' dicts, we reuse the same
     # instance for *one* of the child nodes (the last one). Once an instance
     # has been put on the queue, it is thus no longer safe to modify it.
     # Conversely, it *is* safe to modify an instance popped off the queue.
     work = [(r, 1, {}) for r in roots]
     heapq.heapify(work)
     alwaysmatch = match.always()
     while work:
         r, i1, copies = heapq.heappop(work)
         if work and work[0][0] == r:
             # We are tracing copies from both parents
             r, i2, copies2 = heapq.heappop(work)
             for dst, src in copies2.items():
                 # Unlike when copies are stored in the filelog, we consider
                 # it a copy even if the destination already existed on the
                 # other branch. It's simply too expensive to check if the
                 # file existed in the manifest.
                 if dst not in copies:
                     # If it was copied on the p1 side, leave it as copied from
                     # that side, even if it was also copied on the p2 side.
                     copies[dst] = copies2[dst]
         if r == b.rev():
             return copies
         for i, c in enumerate(children[r]):
             childctx = repo[c]
             if r == childctx.p1().rev():
                 parent = 1
                 childcopies = childctx.p1copies()
             else:
                 assert r == childctx.p2().rev()
                 parent = 2
                 childcopies = childctx.p2copies()
             if not alwaysmatch:
                 childcopies = {
                     dst: src for dst, src in childcopies.items() if match(dst)
                 }
             # Copy the dict only if later iterations will also need it
             if i != len(children[r]) - 1:
                 newcopies = copies.copy()
             else:
                 newcopies = copies
             if childcopies:
                 newcopies = _chain(newcopies, childcopies)
             for f in childctx.filesremoved():
                 if f in newcopies:
                     del newcopies[f]
             heapq.heappush(work, (c, parent, newcopies))
     assert False
 
 
 def _forwardcopies(a, b, base=None, match=None):
     """find {dst@b: src@a} copy mapping where a is an ancestor of b"""
 
     if base is None:
         base = a
     match = a.repo().narrowmatch(match)
     # check for working copy
     if b.rev() is None:
         cm = _committedforwardcopies(a, b.p1(), base, match)
         # combine copies from dirstate if necessary
         copies = _chain(cm, _dirstatecopies(b._repo, match))
     else:
         copies = _committedforwardcopies(a, b, base, match)
     return copies
 
 
 def _backwardrenames(a, b, match):
     if a._repo.ui.config(b'experimental', b'copytrace') == b'off':
         return {}
 
     # Even though we're not taking copies into account, 1:n rename situations
     # can still exist (e.g. hg cp a b; hg mv a c). In those cases we
     # arbitrarily pick one of the renames.
     # We don't want to pass in "match" here, since that would filter
     # the destination by it. Since we're reversing the copies, we want
     # to filter the source instead.
     f = _forwardcopies(b, a)
     r = {}
     for k, v in sorted(pycompat.iteritems(f)):
         if match and not match(v):
             continue
         # remove copies
         if v in a:
             continue
         r[v] = k
     return r
 
 
 def pathcopies(x, y, match=None):
     """find {dst@y: src@x} copy mapping for directed compare"""
     repo = x._repo
     debug = repo.ui.debugflag and repo.ui.configbool(b'devel', b'debug.copies')
     if debug:
         repo.ui.debug(
             b'debug.copies: searching copies from %s to %s\n' % (x, y)
         )
     if x == y or not x or not y:
         return {}
     a = y.ancestor(x)
     if a == x:
         if debug:
             repo.ui.debug(b'debug.copies: search mode: forward\n')
         if y.rev() is None and x == y.p1():
             # short-circuit to avoid issues with merge states
             return _dirstatecopies(repo, match)
         copies = _forwardcopies(x, y, match=match)
     elif a == y:
         if debug:
             repo.ui.debug(b'debug.copies: search mode: backward\n')
         copies = _backwardrenames(x, y, match=match)
     else:
         if debug:
             repo.ui.debug(b'debug.copies: search mode: combined\n')
         base = None
         if a.rev() != node.nullrev:
             base = x
         copies = _chain(
             _backwardrenames(x, a, match=match),
             _forwardcopies(a, y, base, match=match),
         )
     _filter(x, y, copies)
     return copies
 
 
 def mergecopies(repo, c1, c2, base):
     """
     Finds moves and copies between context c1 and c2 that are relevant for
     merging. 'base' will be used as the merge base.
 
     Copytracing is used in commands like rebase, merge, unshelve, etc to merge
     files that were moved/ copied in one merge parent and modified in another.
     For example:
 
     o          ---> 4 another commit
     |
     |   o      ---> 3 commit that modifies a.txt
     |  /
     o /        ---> 2 commit that moves a.txt to b.txt
     |/
     o          ---> 1 merge base
 
     If we try to rebase revision 3 on revision 4, since there is no a.txt in
     revision 4, and if user have copytrace disabled, we prints the following
     message:
 
     ```other changed <file> which local deleted```
 
     Returns five dicts: "copy", "movewithdir", "diverge", "renamedelete" and
     "dirmove".
 
     "copy" is a mapping from destination name -> source name,
     where source is in c1 and destination is in c2 or vice-versa.
 
     "movewithdir" is a mapping from source name -> destination name,
     where the file at source present in one context but not the other
     needs to be moved to destination by the merge process, because the
     other context moved the directory it is in.
 
     "diverge" is a mapping of source name -> list of destination names
     for divergent renames.
 
     "renamedelete" is a mapping of source name -> list of destination
     names for files deleted in c1 that were renamed in c2 or vice-versa.
 
     "dirmove" is a mapping of detected source dir -> destination dir renames.
     This is needed for handling changes to new files previously grafted into
     renamed directories.
 
     This function calls different copytracing algorithms based on config.
     """
     # avoid silly behavior for update from empty dir
     if not c1 or not c2 or c1 == c2:
         return {}, {}, {}, {}, {}
 
     narrowmatch = c1.repo().narrowmatch()
 
     # avoid silly behavior for parent -> working dir
     if c2.node() is None and c1.node() == repo.dirstate.p1():
         return _dirstatecopies(repo, narrowmatch), {}, {}, {}, {}
 
     copytracing = repo.ui.config(b'experimental', b'copytrace')
     if stringutil.parsebool(copytracing) is False:
         # stringutil.parsebool() returns None when it is unable to parse the
         # value, so we should rely on making sure copytracing is on such cases
         return {}, {}, {}, {}, {}
 
     if usechangesetcentricalgo(repo):
         # The heuristics don't make sense when we need changeset-centric algos
         return _fullcopytracing(repo, c1, c2, base)
 
     # Copy trace disabling is explicitly below the node == p1 logic above
     # because the logic above is required for a simple copy to be kept across a
     # rebase.
     if copytracing == b'heuristics':
         # Do full copytracing if only non-public revisions are involved as
         # that will be fast enough and will also cover the copies which could
         # be missed by heuristics
         if _isfullcopytraceable(repo, c1, base):
             return _fullcopytracing(repo, c1, c2, base)
         return _heuristicscopytracing(repo, c1, c2, base)
     else:
         return _fullcopytracing(repo, c1, c2, base)
 
 
 def _isfullcopytraceable(repo, c1, base):
     """ Checks that if base, source and destination are all no-public branches,
     if yes let's use the full copytrace algorithm for increased capabilities
     since it will be fast enough.
 
     `experimental.copytrace.sourcecommitlimit` can be used to set a limit for
     number of changesets from c1 to base such that if number of changesets are
     more than the limit, full copytracing algorithm won't be used.
     """
     if c1.rev() is None:
         c1 = c1.p1()
     if c1.mutable() and base.mutable():
         sourcecommitlimit = repo.ui.configint(
             b'experimental', b'copytrace.sourcecommitlimit'
         )
         commits = len(repo.revs(b'%d::%d', base.rev(), c1.rev()))
         return commits < sourcecommitlimit
     return False
 
 
 def _checksinglesidecopies(
     src, dsts1, m1, m2, mb, c2, base, copy, renamedelete
 ):
     if src not in m2:
         # deleted on side 2
         if src not in m1:
             # renamed on side 1, deleted on side 2
             renamedelete[src] = dsts1
     elif m2[src] != mb[src]:
         if not _related(c2[src], base[src]):
             return
         # modified on side 2
         for dst in dsts1:
             if dst not in m2:
                 # dst not added on side 2 (handle as regular
                 # "both created" case in manifestmerge otherwise)
                 copy[dst] = src
 
 
 def _fullcopytracing(repo, c1, c2, base):
     """ The full copytracing algorithm which finds all the new files that were
     added from merge base up to the top commit and for each file it checks if
     this file was copied from another file.
 
     This is pretty slow when a lot of changesets are involved but will track all
     the copies.
     """
     m1 = c1.manifest()
     m2 = c2.manifest()
     mb = base.manifest()
 
     copies1 = pathcopies(base, c1)
     copies2 = pathcopies(base, c2)
 
     inversecopies1 = {}
     inversecopies2 = {}
     for dst, src in copies1.items():
         inversecopies1.setdefault(src, []).append(dst)
     for dst, src in copies2.items():
         inversecopies2.setdefault(src, []).append(dst)
 
     copy = {}
     diverge = {}
     renamedelete = {}
     allsources = set(inversecopies1) | set(inversecopies2)
     for src in allsources:
         dsts1 = inversecopies1.get(src)
         dsts2 = inversecopies2.get(src)
         if dsts1 and dsts2:
             # copied/renamed on both sides
             if src not in m1 and src not in m2:
                 # renamed on both sides
                 dsts1 = set(dsts1)
                 dsts2 = set(dsts2)
                 # If there's some overlap in the rename destinations, we
                 # consider it not divergent. For example, if side 1 copies 'a'
                 # to 'b' and 'c' and deletes 'a', and side 2 copies 'a' to 'c'
                 # and 'd' and deletes 'a'.
                 if dsts1 & dsts2:
                     for dst in dsts1 & dsts2:
                         copy[dst] = src
                 else:
                     diverge[src] = sorted(dsts1 | dsts2)
             elif src in m1 and src in m2:
                 # copied on both sides
                 dsts1 = set(dsts1)
                 dsts2 = set(dsts2)
                 for dst in dsts1 & dsts2:
                     copy[dst] = src
             # TODO: Handle cases where it was renamed on one side and copied
             # on the other side
         elif dsts1:
             # copied/renamed only on side 1
             _checksinglesidecopies(
                 src, dsts1, m1, m2, mb, c2, base, copy, renamedelete
             )
         elif dsts2:
             # copied/renamed only on side 2
             _checksinglesidecopies(
                 src, dsts2, m2, m1, mb, c1, base, copy, renamedelete
             )
 
     renamedeleteset = set()
     divergeset = set()
     for dsts in diverge.values():
         divergeset.update(dsts)
     for dsts in renamedelete.values():
         renamedeleteset.update(dsts)
 
     # find interesting file sets from manifests
     addedinm1 = m1.filesnotin(mb, repo.narrowmatch())
     addedinm2 = m2.filesnotin(mb, repo.narrowmatch())
     u1 = sorted(addedinm1 - addedinm2)
     u2 = sorted(addedinm2 - addedinm1)
 
     header = b"  unmatched files in %s"
     if u1:
         repo.ui.debug(b"%s:\n   %s\n" % (header % b'local', b"\n   ".join(u1)))
     if u2:
         repo.ui.debug(b"%s:\n   %s\n" % (header % b'other', b"\n   ".join(u2)))
 
     fullcopy = copies1.copy()
     fullcopy.update(copies2)
     if not fullcopy:
         return copy, {}, diverge, renamedelete, {}
 
     if repo.ui.debugflag:
         repo.ui.debug(
             b"  all copies found (* = to merge, ! = divergent, "
             b"% = renamed and deleted):\n"
         )
         for f in sorted(fullcopy):
             note = b""
             if f in copy:
                 note += b"*"
             if f in divergeset:
                 note += b"!"
             if f in renamedeleteset:
                 note += b"%"
             repo.ui.debug(
                 b"   src: '%s' -> dst: '%s' %s\n" % (fullcopy[f], f, note)
             )
     del divergeset
 
     repo.ui.debug(b"  checking for directory renames\n")
 
     # generate a directory move map
     d1, d2 = c1.dirs(), c2.dirs()
     invalid = set()
     dirmove = {}
 
     # examine each file copy for a potential directory move, which is
     # when all the files in a directory are moved to a new directory
     for dst, src in pycompat.iteritems(fullcopy):
         dsrc, ddst = pathutil.dirname(src), pathutil.dirname(dst)
         if dsrc in invalid:
             # already seen to be uninteresting
             continue
         elif dsrc in d1 and ddst in d1:
             # directory wasn't entirely moved locally
             invalid.add(dsrc)
         elif dsrc in d2 and ddst in d2:
             # directory wasn't entirely moved remotely
             invalid.add(dsrc)
         elif dsrc in dirmove and dirmove[dsrc] != ddst:
             # files from the same directory moved to two different places
             invalid.add(dsrc)
         else:
             # looks good so far
             dirmove[dsrc] = ddst
 
     for i in invalid:
         if i in dirmove:
             del dirmove[i]
     del d1, d2, invalid
 
     if not dirmove:
         return copy, {}, diverge, renamedelete, {}
 
     dirmove = {k + b"/": v + b"/" for k, v in pycompat.iteritems(dirmove)}
 
     for d in dirmove:
         repo.ui.debug(
             b"   discovered dir src: '%s' -> dst: '%s'\n" % (d, dirmove[d])
         )
 
     movewithdir = {}
     # check unaccounted nonoverlapping files against directory moves
     for f in u1 + u2:
         if f not in fullcopy:
             for d in dirmove:
                 if f.startswith(d):
                     # new file added in a directory that was moved, move it
                     df = dirmove[d] + f[len(d) :]
                     if df not in copy:
                         movewithdir[f] = df
                         repo.ui.debug(
                             b"   pending file src: '%s' -> dst: '%s'\n"
                             % (f, df)
                         )
                     break
 
     return copy, movewithdir, diverge, renamedelete, dirmove
 
 
 def _heuristicscopytracing(repo, c1, c2, base):
     """ Fast copytracing using filename heuristics
 
     Assumes that moves or renames are of following two types:
 
     1) Inside a directory only (same directory name but different filenames)
     2) Move from one directory to another
                     (same filenames but different directory names)
 
     Works only when there are no merge commits in the "source branch".
     Source branch is commits from base up to c2 not including base.
 
     If merge is involved it fallbacks to _fullcopytracing().
 
     Can be used by setting the following config:
 
         [experimental]
         copytrace = heuristics
 
     In some cases the copy/move candidates found by heuristics can be very large
     in number and that will make the algorithm slow. The number of possible
     candidates to check can be limited by using the config
     `experimental.copytrace.movecandidateslimit` which defaults to 100.
     """
 
     if c1.rev() is None:
         c1 = c1.p1()
     if c2.rev() is None:
         c2 = c2.p1()
 
     copies = {}
 
     changedfiles = set()
     m1 = c1.manifest()
     if not repo.revs(b'%d::%d', base.rev(), c2.rev()):
         # If base is not in c2 branch, we switch to fullcopytracing
         repo.ui.debug(
             b"switching to full copytracing as base is not "
             b"an ancestor of c2\n"
         )
         return _fullcopytracing(repo, c1, c2, base)
 
     ctx = c2
     while ctx != base:
         if len(ctx.parents()) == 2:
             # To keep things simple let's not handle merges
             repo.ui.debug(b"switching to full copytracing because of merges\n")
             return _fullcopytracing(repo, c1, c2, base)
         changedfiles.update(ctx.files())
         ctx = ctx.p1()
 
     cp = _forwardcopies(base, c2)
     for dst, src in pycompat.iteritems(cp):
         if src in m1:
             copies[dst] = src
 
     # file is missing if it isn't present in the destination, but is present in
     # the base and present in the source.
     # Presence in the base is important to exclude added files, presence in the
     # source is important to exclude removed files.
     filt = lambda f: f not in m1 and f in base and f in c2
     missingfiles = [f for f in changedfiles if filt(f)]
 
     if missingfiles:
         basenametofilename = collections.defaultdict(list)
         dirnametofilename = collections.defaultdict(list)
 
         for f in m1.filesnotin(base.manifest()):
             basename = os.path.basename(f)
             dirname = os.path.dirname(f)
             basenametofilename[basename].append(f)
             dirnametofilename[dirname].append(f)
 
         for f in missingfiles:
             basename = os.path.basename(f)
             dirname = os.path.dirname(f)
             samebasename = basenametofilename[basename]
             samedirname = dirnametofilename[dirname]
             movecandidates = samebasename + samedirname
             # f is guaranteed to be present in c2, that's why
             # c2.filectx(f) won't fail
             f2 = c2.filectx(f)
             # we can have a lot of candidates which can slow down the heuristics
             # config value to limit the number of candidates moves to check
             maxcandidates = repo.ui.configint(
                 b'experimental', b'copytrace.movecandidateslimit'
             )
 
             if len(movecandidates) > maxcandidates:
                 repo.ui.status(
                     _(
                         b"skipping copytracing for '%s', more "
                         b"candidates than the limit: %d\n"
                     )
                     % (f, len(movecandidates))
                 )
                 continue
 
             for candidate in movecandidates:
                 f1 = c1.filectx(candidate)
                 if _related(f1, f2):
                     # if there are a few related copies then we'll merge
                     # changes into all of them. This matches the behaviour
                     # of upstream copytracing
                     copies[candidate] = f
 
     return copies, {}, {}, {}, {}
 
 
 def _related(f1, f2):
     """return True if f1 and f2 filectx have a common ancestor
 
     Walk back to common ancestor to see if the two files originate
     from the same file. Since workingfilectx's rev() is None it messes
     up the integer comparison logic, hence the pre-step check for
     None (f1 and f2 can only be workingfilectx's initially).
     """
 
     if f1 == f2:
         return True  # a match
 
     g1, g2 = f1.ancestors(), f2.ancestors()
     try:
         f1r, f2r = f1.linkrev(), f2.linkrev()
 
         if f1r is None:
             f1 = next(g1)
         if f2r is None:
             f2 = next(g2)
 
         while True:
             f1r, f2r = f1.linkrev(), f2.linkrev()
             if f1r > f2r:
                 f1 = next(g1)
             elif f2r > f1r:
                 f2 = next(g2)
             else:  # f1 and f2 point to files in the same linkrev
                 return f1 == f2  # true if they point to the same file
     except StopIteration:
         return False
 
 
 def duplicatecopies(repo, wctx, rev, fromrev, skiprev=None):
     """reproduce copies from fromrev to rev in the dirstate
 
     If skiprev is specified, it's a revision that should be used to
     filter copy records. Any copies that occur between fromrev and
     skiprev will not be duplicated, even if they appear in the set of
     copies between fromrev and rev.
     """
     exclude = {}
     ctraceconfig = repo.ui.config(b'experimental', b'copytrace')
     bctrace = stringutil.parsebool(ctraceconfig)
     if skiprev is not None and (
         ctraceconfig == b'heuristics' or bctrace or bctrace is None
     ):
         # copytrace='off' skips this line, but not the entire function because
         # the line below is O(size of the repo) during a rebase, while the rest
         # of the function is much faster (and is required for carrying copy
         # metadata across the rebase anyway).
         exclude = pathcopies(repo[fromrev], repo[skiprev])
     for dst, src in pycompat.iteritems(pathcopies(repo[fromrev], repo[rev])):
         if dst in exclude:
             continue
         if dst in wctx:
             wctx[dst].markcopied(src)
 
 
 def computechangesetcopies(ctx):
     """return the copies data for a changeset
 
     The copies data are returned as a pair of dictionnary (p1copies, p2copies).
 
     Each dictionnary are in the form: `{newname: oldname}`
     """
     p1copies = {}
     p2copies = {}
     p1 = ctx.p1()
     p2 = ctx.p2()
     narrowmatch = ctx._repo.narrowmatch()
     for dst in ctx.files():
         if not narrowmatch(dst) or dst not in ctx:
             continue
         copied = ctx[dst].renamed()
         if not copied:
             continue
         src, srcnode = copied
         if src in p1 and p1[src].filenode() == srcnode:
             p1copies[dst] = src
         elif src in p2 and p2[src].filenode() == srcnode:
             p2copies[dst] = src
     return p1copies, p2copies

tests/test-copies-unrelated.t

@@ -1,396 +1,396 b''
 #testcases filelog compatibility changeset sidedata
 
   $ cat >> $HGRCPATH << EOF
   > [extensions]
   > rebase=
   > [alias]
   > l = log -G -T '{rev} {desc}\n{files}\n'
   > EOF
 
 #if compatibility
   $ cat >> $HGRCPATH << EOF
   > [experimental]
   > copies.read-from = compatibility
   > EOF
 #endif
 
 #if changeset
   $ cat >> $HGRCPATH << EOF
   > [experimental]
   > copies.read-from = changeset-only
   > copies.write-to = changeset-only
   > EOF
 #endif
 
 #if sidedata
   $ cat >> $HGRCPATH << EOF
   > [format]
   > exp-use-copies-side-data-changeset = yes
   > EOF
 #endif
 
   $ REPONUM=0
   $ newrepo() {
   >     cd $TESTTMP
   >     REPONUM=`expr $REPONUM + 1`
   >     hg init repo-$REPONUM
   >     cd repo-$REPONUM
   > }
 
 Copy a file, then delete destination, then copy again. This does not create a new filelog entry.
   $ newrepo
   $ echo x > x
   $ hg ci -Aqm 'add x'
   $ echo x2 > x
   $ hg ci -m 'modify x'
   $ hg co -q 0
   $ hg cp x y
   $ hg ci -qm 'copy x to y'
   $ hg rm y
   $ hg ci -m 'remove y'
   $ hg cp -f x y
   $ hg ci -m 'copy x onto y (again)'
   $ hg l
   @  4 copy x onto y (again)
   |  y
   o  3 remove y
   |  y
   o  2 copy x to y
   |  y
   | o  1 modify x
   |/   x
   o  0 add x
      x
   $ hg debugp1copies -r 4
   x -> y
   $ hg debugpathcopies 0 4
   x -> y
   $ hg graft -r 1
   grafting 1:* "modify x" (glob)
   merging y and x to y
   $ hg co -qC 1
   $ hg graft -r 4
   grafting 4:* "copy x onto y (again)" (glob)
   merging x and y to y
 
 Copy x to y, then remove y, then add back y. With copy metadata in the
 changeset, this could easily end up reporting y as copied from x (if we don't
 unmark it as a copy when it's removed). Despite x and y not being related, we
 want grafts to propagate across the rename.
   $ newrepo
   $ echo x > x
   $ hg ci -Aqm 'add x'
   $ echo x2 > x
   $ hg ci -m 'modify x'
   $ hg co -q 0
   $ hg mv x y
   $ hg ci -qm 'rename x to y'
   $ hg rm y
   $ hg ci -qm 'remove y'
   $ echo x > y
   $ hg ci -Aqm 'add back y'
   $ hg l
   @  4 add back y
   |  y
   o  3 remove y
   |  y
   o  2 rename x to y
   |  x y
   | o  1 modify x
   |/   x
   o  0 add x
      x
   $ hg debugpathcopies 0 4
 BROKEN: This should succeed and merge the changes from x into y
   $ hg graft -r 1
   grafting 1:* "modify x" (glob)
   file 'x' was deleted in local [local] but was modified in other [graft].
   You can use (c)hanged version, leave (d)eleted, or leave (u)nresolved.
   What do you want to do? u
   abort: unresolved conflicts, can't continue
   (use 'hg resolve' and 'hg graft --continue')
   [255]
 
 Add x, remove it, then add it back, then rename x to y. Similar to the case
 above, but here the break in history is before the rename.
   $ newrepo
   $ echo x > x
   $ hg ci -Aqm 'add x'
   $ echo x2 > x
   $ hg ci -m 'modify x'
   $ hg co -q 0
   $ hg rm x
   $ hg ci -qm 'remove x'
   $ echo x > x
   $ hg ci -Aqm 'add x again'
   $ hg mv x y
   $ hg ci -m 'rename x to y'
   $ hg l
   @  4 rename x to y
   |  x y
   o  3 add x again
   |  x
   o  2 remove x
   |  x
   | o  1 modify x
   |/   x
   o  0 add x
      x
   $ hg debugpathcopies 0 4
   x -> y
   $ hg graft -r 1
   grafting 1:* "modify x" (glob)
   merging y and x to y
   $ hg co -qC 1
   $ hg graft -r 4
   grafting 4:* "rename x to y" (glob)
   merging x and y to y
 
 Add x, modify it, remove it, then add it back, then rename x to y. Similar to
 the case above, but here the re-added file's nodeid is different from before
 the break.
 
   $ newrepo
   $ echo x > x
   $ hg ci -Aqm 'add x'
   $ echo x2 > x
   $ hg ci -m 'modify x'
   $ echo x3 > x
   $ hg ci -qm 'modify x again'
   $ hg co -q 1
   $ hg rm x
   $ hg ci -qm 'remove x'
 # Same content to avoid conflicts
   $ hg revert -r 1 x
   $ hg ci -Aqm 'add x again'
   $ hg mv x y
   $ hg ci -m 'rename x to y'
   $ hg l
   @  5 rename x to y
   |  x y
   o  4 add x again
   |  x
   o  3 remove x
   |  x
   | o  2 modify x again
   |/   x
   o  1 modify x
   |  x
   o  0 add x
      x
   $ hg debugpathcopies 0 5
-  x -> y (no-filelog no-sidedata !)
-#if no-filelog no-sidedata
+  x -> y (no-filelog !)
+#if no-filelog
   $ hg graft -r 2
   grafting 2:* "modify x again" (glob)
   merging y and x to y
 #else
 BROKEN: This should succeed and merge the changes from x into y
   $ hg graft -r 2
   grafting 2:* "modify x again" (glob)
   file 'x' was deleted in local [local] but was modified in other [graft].
   You can use (c)hanged version, leave (d)eleted, or leave (u)nresolved.
   What do you want to do? u
   abort: unresolved conflicts, can't continue
   (use 'hg resolve' and 'hg graft --continue')
   [255]
 #endif
   $ hg co -qC 2
 BROKEN: This should succeed and merge the changes from x into y
   $ hg graft -r 5
   grafting 5:* "rename x to y"* (glob)
   file 'x' was deleted in other [graft] but was modified in local [local].
   You can use (c)hanged version, (d)elete, or leave (u)nresolved.
   What do you want to do? u
   abort: unresolved conflicts, can't continue
   (use 'hg resolve' and 'hg graft --continue')
   [255]
 
 Add x, remove it, then add it back, rename x to y from the first commit.
 Similar to the case above, but here the break in history is parallel to the
 rename.
   $ newrepo
   $ echo x > x
   $ hg ci -Aqm 'add x'
   $ hg rm x
   $ hg ci -qm 'remove x'
   $ echo x > x
   $ hg ci -Aqm 'add x again'
   $ echo x2 > x
   $ hg ci -m 'modify x'
   $ hg co -q 0
   $ hg mv x y
   $ hg ci -qm 'rename x to y'
   $ hg l
   @  4 rename x to y
   |  x y
   | o  3 modify x
   | |  x
   | o  2 add x again
   | |  x
   | o  1 remove x
   |/   x
   o  0 add x
      x
   $ hg debugpathcopies 2 4
   x -> y
   $ hg graft -r 3
   grafting 3:* "modify x" (glob)
   merging y and x to y
   $ hg co -qC 3
   $ hg graft -r 4
   grafting 4:* "rename x to y" (glob)
   merging x and y to y
 
 Add x, remove it, then add it back, rename x to y from the first commit.
 Similar to the case above, but here the re-added file's nodeid is different
 from the base.
   $ newrepo
   $ echo x > x
   $ hg ci -Aqm 'add x'
   $ hg rm x
   $ hg ci -qm 'remove x'
   $ echo x2 > x
   $ hg ci -Aqm 'add x again with different content'
   $ hg co -q 0
   $ hg mv x y
   $ hg ci -qm 'rename x to y'
   $ hg l
   @  3 rename x to y
   |  x y
   | o  2 add x again with different content
   | |  x
   | o  1 remove x
   |/   x
   o  0 add x
      x
   $ hg debugpathcopies 2 3
   x -> y
 BROKEN: This should merge the changes from x into y
   $ hg graft -r 2
   grafting 2:* "add x again with different content" (glob)
   $ hg co -qC 2
 BROKEN: This should succeed and merge the changes from x into y
   $ hg graft -r 3
   grafting 3:* "rename x to y" (glob)
   file 'x' was deleted in other [graft] but was modified in local [local].
   You can use (c)hanged version, (d)elete, or leave (u)nresolved.
   What do you want to do? u
   abort: unresolved conflicts, can't continue
   (use 'hg resolve' and 'hg graft --continue')
   [255]
 
 Add x on two branches, then rename x to y on one side. Similar to the case
 above, but here the break in history is via the base commit.
   $ newrepo
   $ echo a > a
   $ hg ci -Aqm 'base'
   $ echo x > x
   $ hg ci -Aqm 'add x'
   $ echo x2 > x
   $ hg ci -m 'modify x'
   $ hg co -q 0
   $ echo x > x
   $ hg ci -Aqm 'add x again'
   $ hg mv x y
   $ hg ci -qm 'rename x to y'
   $ hg l
   @  4 rename x to y
   |  x y
   o  3 add x again
   |  x
   | o  2 modify x
   | |  x
   | o  1 add x
   |/   x
   o  0 base
      a
   $ hg debugpathcopies 1 4
   x -> y
   $ hg graft -r 2
   grafting 2:* "modify x" (glob)
   merging y and x to y
   $ hg co -qC 2
   $ hg graft -r 4
   grafting 4:* "rename x to y"* (glob)
   merging x and y to y
 
 Add x on two branches, with same content but different history, then rename x
 to y on one side. Similar to the case above, here the file's nodeid is
 different between the branches.
   $ newrepo
   $ echo a > a
   $ hg ci -Aqm 'base'
   $ echo x > x
   $ hg ci -Aqm 'add x'
   $ echo x2 > x
   $ hg ci -m 'modify x'
   $ hg co -q 0
   $ touch x
   $ hg ci -Aqm 'add empty x'
 # Same content to avoid conflicts
   $ hg revert -r 1 x
   $ hg ci -m 'modify x to match commit 1'
   $ hg mv x y
   $ hg ci -qm 'rename x to y'
   $ hg l
   @  5 rename x to y
   |  x y
   o  4 modify x to match commit 1
   |  x
   o  3 add empty x
   |  x
   | o  2 modify x
   | |  x
   | o  1 add x
   |/   x
   o  0 base
      a
   $ hg debugpathcopies 1 5
-  x -> y (no-filelog no-sidedata !)
-#if no-filelog no-sidedata
+  x -> y (no-filelog !)
+#if no-filelog
   $ hg graft -r 2
   grafting 2:* "modify x" (glob)
   merging y and x to y
 #else
 BROKEN: This should succeed and merge the changes from x into y
   $ hg graft -r 2
   grafting 2:* "modify x" (glob)
   file 'x' was deleted in local [local] but was modified in other [graft].
   You can use (c)hanged version, leave (d)eleted, or leave (u)nresolved.
   What do you want to do? u
   abort: unresolved conflicts, can't continue
   (use 'hg resolve' and 'hg graft --continue')
   [255]
 #endif
   $ hg co -qC 2
 BROKEN: This should succeed and merge the changes from x into y
   $ hg graft -r 5
   grafting 5:* "rename x to y"* (glob)
   file 'x' was deleted in other [graft] but was modified in local [local].
   You can use (c)hanged version, (d)elete, or leave (u)nresolved.
   What do you want to do? u
   abort: unresolved conflicts, can't continue
   (use 'hg resolve' and 'hg graft --continue')
   [255]
 
 Copies via null revision (there shouldn't be any)
   $ newrepo
   $ echo x > x
   $ hg ci -Aqm 'add x'
   $ hg cp x y
   $ hg ci -m 'copy x to y'
   $ hg co -q null
   $ echo x > x
   $ hg ci -Aqm 'add x (again)'
   $ hg l
   @  2 add x (again)
      x
   o  1 copy x to y
   |  y
   o  0 add x
      x
   $ hg debugpathcopies 1 2
   $ hg debugpathcopies 2 1
   $ hg graft -r 1
   grafting 1:* "copy x to y" (glob)

tests/test-copies.t

@@ -1,607 +1,606 b''
 #testcases filelog compatibility changeset sidedata
 
   $ cat >> $HGRCPATH << EOF
   > [extensions]
   > rebase=
   > [alias]
   > l = log -G -T '{rev} {desc}\n{files}\n'
   > EOF
 
 #if compatibility
   $ cat >> $HGRCPATH << EOF
   > [experimental]
   > copies.read-from = compatibility
   > EOF
 #endif
 
 #if changeset
   $ cat >> $HGRCPATH << EOF
   > [experimental]
   > copies.read-from = changeset-only
   > copies.write-to = changeset-only
   > EOF
 #endif
 
 #if sidedata
   $ cat >> $HGRCPATH << EOF
   > [format]
   > exp-use-copies-side-data-changeset = yes
   > EOF
 #endif
 
   $ REPONUM=0
   $ newrepo() {
   >     cd $TESTTMP
   >     REPONUM=`expr $REPONUM + 1`
   >     hg init repo-$REPONUM
   >     cd repo-$REPONUM
   > }
 
 Simple rename case
   $ newrepo
   $ echo x > x
   $ hg ci -Aqm 'add x'
   $ hg mv x y
   $ hg debugp1copies
   x -> y
   $ hg debugp2copies
   $ hg ci -m 'rename x to y'
   $ hg l
   @  1 rename x to y
   |  x y
   o  0 add x
      x
   $ hg debugp1copies -r 1
   x -> y
   $ hg debugpathcopies 0 1
   x -> y
   $ hg debugpathcopies 1 0
   y -> x
 Test filtering copies by path. We do filtering by destination.
   $ hg debugpathcopies 0 1 x
   $ hg debugpathcopies 1 0 x
   y -> x
   $ hg debugpathcopies 0 1 y
   x -> y
   $ hg debugpathcopies 1 0 y
 
 Copies not including commit changes
   $ newrepo
   $ echo x > x
   $ hg ci -Aqm 'add x'
   $ hg mv x y
   $ hg debugpathcopies . .
   $ hg debugpathcopies . 'wdir()'
   x -> y
   $ hg debugpathcopies 'wdir()' .
   y -> x
 
 Copy a file onto another file
   $ newrepo
   $ echo x > x
   $ echo y > y
   $ hg ci -Aqm 'add x and y'
   $ hg cp -f x y
   $ hg debugp1copies
   x -> y
   $ hg debugp2copies
   $ hg ci -m 'copy x onto y'
   $ hg l
   @  1 copy x onto y
   |  y
   o  0 add x and y
      x y
   $ hg debugp1copies -r 1
   x -> y
 Incorrectly doesn't show the rename
   $ hg debugpathcopies 0 1
 
 Copy a file onto another file with same content. If metadata is stored in changeset, this does not
 produce a new filelog entry. The changeset's "files" entry should still list the file.
   $ newrepo
   $ echo x > x
   $ echo x > x2
   $ hg ci -Aqm 'add x and x2 with same content'
   $ hg cp -f x x2
   $ hg ci -m 'copy x onto x2'
   $ hg l
   @  1 copy x onto x2
   |  x2
   o  0 add x and x2 with same content
      x x2
   $ hg debugp1copies -r 1
   x -> x2
 Incorrectly doesn't show the rename
   $ hg debugpathcopies 0 1
 
 Rename file in a loop: x->y->z->x
   $ newrepo
   $ echo x > x
   $ hg ci -Aqm 'add x'
   $ hg mv x y
   $ hg debugp1copies
   x -> y
   $ hg debugp2copies
   $ hg ci -m 'rename x to y'
   $ hg mv y z
   $ hg ci -m 'rename y to z'
   $ hg mv z x
   $ hg ci -m 'rename z to x'
   $ hg l
   @  3 rename z to x
   |  x z
   o  2 rename y to z
   |  y z
   o  1 rename x to y
   |  x y
   o  0 add x
      x
   $ hg debugpathcopies 0 3
 
 Copy x to z, then remove z, then copy x2 (same content as x) to z. With copy metadata in the
 changeset, the two copies here will have the same filelog entry, so ctx['z'].introrev() might point
 to the first commit that added the file. We should still report the copy as being from x2.
   $ newrepo
   $ echo x > x
   $ echo x > x2
   $ hg ci -Aqm 'add x and x2 with same content'
   $ hg cp x z
   $ hg ci -qm 'copy x to z'
   $ hg rm z
   $ hg ci -m 'remove z'
   $ hg cp x2 z
   $ hg ci -m 'copy x2 to z'
   $ hg l
   @  3 copy x2 to z
   |  z
   o  2 remove z
   |  z
   o  1 copy x to z
   |  z
   o  0 add x and x2 with same content
      x x2
   $ hg debugp1copies -r 3
   x2 -> z
   $ hg debugpathcopies 0 3
   x2 -> z
 
 Create x and y, then rename them both to the same name, but on different sides of a fork
   $ newrepo
   $ echo x > x
   $ echo y > y
   $ hg ci -Aqm 'add x and y'
   $ hg mv x z
   $ hg ci -qm 'rename x to z'
   $ hg co -q 0
   $ hg mv y z
   $ hg ci -qm 'rename y to z'
   $ hg l
   @  2 rename y to z
   |  y z
   | o  1 rename x to z
   |/   x z
   o  0 add x and y
      x y
   $ hg debugpathcopies 1 2
   z -> x
   y -> z
 
 Fork renames x to y on one side and removes x on the other
   $ newrepo
   $ echo x > x
   $ hg ci -Aqm 'add x'
   $ hg mv x y
   $ hg ci -m 'rename x to y'
   $ hg co -q 0
   $ hg rm x
   $ hg ci -m 'remove x'
   created new head
   $ hg l
   @  2 remove x
   |  x
   | o  1 rename x to y
   |/   x y
   o  0 add x
      x
   $ hg debugpathcopies 1 2
 
 Merge rename from other branch
   $ newrepo
   $ echo x > x
   $ hg ci -Aqm 'add x'
   $ hg mv x y
   $ hg ci -m 'rename x to y'
   $ hg co -q 0
   $ echo z > z
   $ hg ci -Aqm 'add z'
   $ hg merge -q 1
   $ hg debugp1copies
   $ hg debugp2copies
   $ hg ci -m 'merge rename from p2'
   $ hg l
   @    3 merge rename from p2
   |\
   | o  2 add z
   | |  z
   o |  1 rename x to y
   |/   x y
   o  0 add x
      x
 Perhaps we should indicate the rename here, but `hg status` is documented to be weird during
 merges, so...
   $ hg debugp1copies -r 3
   $ hg debugp2copies -r 3
   $ hg debugpathcopies 0 3
   x -> y
   $ hg debugpathcopies 1 2
   y -> x
   $ hg debugpathcopies 1 3
   $ hg debugpathcopies 2 3
   x -> y
 
 Copy file from either side in a merge
   $ newrepo
   $ echo x > x
   $ hg ci -Aqm 'add x'
   $ hg co -q null
   $ echo y > y
   $ hg ci -Aqm 'add y'
   $ hg merge -q 0
   $ hg cp y z
   $ hg debugp1copies
   y -> z
   $ hg debugp2copies
   $ hg ci -m 'copy file from p1 in merge'
   $ hg co -q 1
   $ hg merge -q 0
   $ hg cp x z
   $ hg debugp1copies
   $ hg debugp2copies
   x -> z
   $ hg ci -qm 'copy file from p2 in merge'
   $ hg l
   @    3 copy file from p2 in merge
   |\   z
   +---o  2 copy file from p1 in merge
   | |/   z
   | o  1 add y
   |    y
   o  0 add x
      x
   $ hg debugp1copies -r 2
   y -> z
   $ hg debugp2copies -r 2
   $ hg debugpathcopies 1 2
   y -> z
   $ hg debugpathcopies 0 2
   $ hg debugp1copies -r 3
   $ hg debugp2copies -r 3
   x -> z
   $ hg debugpathcopies 1 3
   $ hg debugpathcopies 0 3
   x -> z
 
 Copy file that exists on both sides of the merge, same content on both sides
   $ newrepo
   $ echo x > x
   $ hg ci -Aqm 'add x on branch 1'
   $ hg co -q null
   $ echo x > x
   $ hg ci -Aqm 'add x on branch 2'
   $ hg merge -q 0
   $ hg cp x z
   $ hg debugp1copies
   x -> z
   $ hg debugp2copies
   $ hg ci -qm 'merge'
   $ hg l
   @    2 merge
   |\   z
   | o  1 add x on branch 2
   |    x
   o  0 add x on branch 1
      x
   $ hg debugp1copies -r 2
   x -> z
   $ hg debugp2copies -r 2
 It's a little weird that it shows up on both sides
   $ hg debugpathcopies 1 2
   x -> z
   $ hg debugpathcopies 0 2
   x -> z (filelog !)
-  x -> z (sidedata !)
 
 Copy file that exists on both sides of the merge, different content
   $ newrepo
   $ echo branch1 > x
   $ hg ci -Aqm 'add x on branch 1'
   $ hg co -q null
   $ echo branch2 > x
   $ hg ci -Aqm 'add x on branch 2'
   $ hg merge -q 0
   warning: conflicts while merging x! (edit, then use 'hg resolve --mark')
   [1]
   $ echo resolved > x
   $ hg resolve -m x
   (no more unresolved files)
   $ hg cp x z
   $ hg debugp1copies
   x -> z
   $ hg debugp2copies
   $ hg ci -qm 'merge'
   $ hg l
   @    2 merge
   |\   x z
   | o  1 add x on branch 2
   |    x
   o  0 add x on branch 1
      x
   $ hg debugp1copies -r 2
   x -> z (changeset !)
+  x -> z (sidedata !)
   $ hg debugp2copies -r 2
-  x -> z (no-changeset !)
+  x -> z (no-changeset no-sidedata !)
   $ hg debugpathcopies 1 2
   x -> z (changeset !)
+  x -> z (sidedata !)
   $ hg debugpathcopies 0 2
-  x -> z (no-changeset !)
+  x -> z (no-changeset no-sidedata !)
 
 Copy x->y on one side of merge and copy x->z on the other side. Pathcopies from one parent
 of the merge to the merge should include the copy from the other side.
   $ newrepo
   $ echo x > x
   $ hg ci -Aqm 'add x'
   $ hg cp x y
   $ hg ci -qm 'copy x to y'
   $ hg co -q 0
   $ hg cp x z
   $ hg ci -qm 'copy x to z'
   $ hg merge -q 1
   $ hg ci -m 'merge copy x->y and copy x->z'
   $ hg l
   @    3 merge copy x->y and copy x->z
   |\
   | o  2 copy x to z
   | |  z
   o |  1 copy x to y
   |/   y
   o  0 add x
      x
   $ hg debugp1copies -r 3
   $ hg debugp2copies -r 3
   $ hg debugpathcopies 2 3
   x -> y
   $ hg debugpathcopies 1 3
   x -> z
 
 Copy x to y on one side of merge, create y and rename to z on the other side.
   $ newrepo
   $ echo x > x
   $ hg ci -Aqm 'add x'
   $ hg cp x y
   $ hg ci -qm 'copy x to y'
   $ hg co -q 0
   $ echo y > y
   $ hg ci -Aqm 'add y'
   $ hg mv y z
   $ hg ci -m 'rename y to z'
   $ hg merge -q 1
   $ hg ci -m 'merge'
   $ hg l
   @    4 merge
   |\
   | o  3 rename y to z
   | |  y z
   | o  2 add y
   | |  y
   o |  1 copy x to y
   |/   y
   o  0 add x
      x
   $ hg debugp1copies -r 3
   y -> z
   $ hg debugp2copies -r 3
   $ hg debugpathcopies 2 3
   y -> z
   $ hg debugpathcopies 1 3
-  y -> z (no-filelog no-sidedata !)
+  y -> z (no-filelog !)
 
 Create x and y, then rename x to z on one side of merge, and rename y to z and
 modify z on the other side. When storing copies in the changeset, we don't
 filter out copies whose target was created on the other side of the merge.
   $ newrepo
   $ echo x > x
   $ echo y > y
   $ hg ci -Aqm 'add x and y'
   $ hg mv x z
   $ hg ci -qm 'rename x to z'
   $ hg co -q 0
   $ hg mv y z
   $ hg ci -qm 'rename y to z'
   $ echo z >> z
   $ hg ci -m 'modify z'
   $ hg merge -q 1
   warning: conflicts while merging z! (edit, then use 'hg resolve --mark')
   [1]
   $ echo z > z
   $ hg resolve -qm z
   $ hg ci -m 'merge 1 into 3'
 Try merging the other direction too
   $ hg co -q 1
   $ hg merge -q 3
   warning: conflicts while merging z! (edit, then use 'hg resolve --mark')
   [1]
   $ echo z > z
   $ hg resolve -qm z
   $ hg ci -m 'merge 3 into 1'
   created new head
   $ hg l
   @    5 merge 3 into 1
   |\   z
   +---o  4 merge 1 into 3
   | |/   z
   | o  3 modify z
   | |  z
   | o  2 rename y to z
   | |  y z
   o |  1 rename x to z
   |/   x z
   o  0 add x and y
      x y
   $ hg debugpathcopies 1 4
-  y -> z (no-filelog no-sidedata !)
+  y -> z (no-filelog !)
   $ hg debugpathcopies 2 4
-  x -> z (no-filelog no-sidedata !)
+  x -> z (no-filelog !)
   $ hg debugpathcopies 0 4
   x -> z (filelog !)
-  x -> z (sidedata !)
-  y -> z (compatibility !)
-  y -> z (changeset !)
+  y -> z (no-filelog !)
   $ hg debugpathcopies 1 5
-  y -> z (no-filelog no-sidedata !)
+  y -> z (no-filelog !)
   $ hg debugpathcopies 2 5
-  x -> z (no-filelog no-sidedata !)
+  x -> z (no-filelog !)
   $ hg debugpathcopies 0 5
   x -> z
 
 
 Test for a case in fullcopytracing algorithm where neither of the merging csets
 is a descendant of the merge base. This test reflects that the algorithm
 correctly finds the copies:
 
   $ cat >> $HGRCPATH << EOF
   > [experimental]
   > evolution.createmarkers=True
   > evolution.allowunstable=True
   > EOF
 
   $ newrepo
   $ echo a > a
   $ hg add a
   $ hg ci -m "added a"
   $ echo b > b
   $ hg add b
   $ hg ci -m "added b"
 
   $ hg mv b b1
   $ hg ci -m "rename b to b1"
 
   $ hg up ".^"
   1 files updated, 0 files merged, 1 files removed, 0 files unresolved
   $ echo d > d
   $ hg add d
   $ hg ci -m "added d"
   created new head
 
   $ echo baba >> b
   $ hg ci --amend -m "added d, modified b"
 
   $ hg l --hidden
   @  4 added d, modified b
   |  b d
   | x  3 added d
   |/   d
   | o  2 rename b to b1
   |/   b b1
   o  1 added b
   |  b
   o  0 added a
      a
 
 Grafting revision 4 on top of revision 2, showing that it respect the rename:
 
   $ hg up 2 -q
   $ hg graft -r 4 --base 3 --hidden
   grafting 4:af28412ec03c "added d, modified b" (tip) (no-changeset !)
   grafting 4:6325ca0b7a1c "added d, modified b" (tip) (changeset !)
   merging b1 and b to b1
 
   $ hg l -l1 -p
   @  5 added d, modified b
   |  b1
   ~  diff -r 5a4825cc2926 -r 94a2f1a0e8e2 b1 (no-changeset !)
   ~  diff -r 0a0ed3b3251c -r d544fb655520 b1 (changeset !)
      --- a/b1	Thu Jan 01 00:00:00 1970 +0000
      +++ b/b1	Thu Jan 01 00:00:00 1970 +0000
      @@ -1,1 +1,2 @@
       b
      +baba
   
 Test to make sure that fullcopytracing algorithm doesn't fail when neither of the
 merging csets is a descendant of the base.
 -------------------------------------------------------------------------------------------------
 
   $ newrepo
   $ echo a > a
   $ hg add a
   $ hg ci -m "added a"
   $ echo b > b
   $ hg add b
   $ hg ci -m "added b"
 
   $ echo foobar > willconflict
   $ hg add willconflict
   $ hg ci -m "added willconflict"
   $ echo c > c
   $ hg add c
   $ hg ci -m "added c"
 
   $ hg l
   @  3 added c
   |  c
   o  2 added willconflict
   |  willconflict
   o  1 added b
   |  b
   o  0 added a
      a
 
   $ hg up ".^^"
   0 files updated, 0 files merged, 2 files removed, 0 files unresolved
   $ echo d > d
   $ hg add d
   $ hg ci -m "added d"
   created new head
 
   $ echo barfoo > willconflict
   $ hg add willconflict
   $ hg ci --amend -m "added willconflict and d"
 
   $ hg l
   @  5 added willconflict and d
   |  d willconflict
   | o  3 added c
   | |  c
   | o  2 added willconflict
   |/   willconflict
   o  1 added b
   |  b
   o  0 added a
      a
 
   $ hg rebase -r . -d 2 -t :other
   rebasing 5:5018b1509e94 "added willconflict and d" (tip) (no-changeset !)
   rebasing 5:af8d273bf580 "added willconflict and d" (tip) (changeset !)
 
   $ hg up 3 -q
   $ hg l --hidden
   o  6 added willconflict and d
   |  d willconflict
   | x  5 added willconflict and d
   | |  d willconflict
   | | x  4 added d
   | |/   d
   +---@  3 added c
   | |    c
   o |  2 added willconflict
   |/   willconflict
   o  1 added b
   |  b
   o  0 added a
      a
 
 Now if we trigger a merge between revision 3 and 6 using base revision 4,
 neither of the merging csets will be a descendant of the base revision:
 
   $ hg graft -r 6 --base 4 --hidden -t :other
   grafting 6:99802e4f1e46 "added willconflict and d" (tip) (no-changeset !)
   grafting 6:b19f0df72728 "added willconflict and d" (tip) (changeset !)