copies: also encode p[12]copies destination as index into "files" list

This is mostly for consistency with the filesaddes/filesremoved
fields, but it should also save a bit of space.

Differential Revision: https://phab.mercurial-scm.org/D6431

mercurial/changelog.py

@@ -1,664 +1,668
 # 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,
 )
 
 _defaultextra = {'branch': '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('\\', '\\\\').replace('\n', '\\n').replace('\r', '\\r')
     return text.replace('\0', '\\0')
 
 def _string_unescape(text):
     if '\\0' in text:
         # fix up \0 without getting into trouble with \\0
         text = text.replace('\\\\', '\\\\\n')
         text = text.replace('\\0', '\0')
         text = text.replace('\n', '')
     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('\0'):
         if l:
             k, v = _string_unescape(l).split(':', 1)
             extra[k] = v
     return extra
 
 def encodeextra(d):
     # keys must be sorted to produce a deterministic changelog entry
     items = [
         _string_escape('%s:%s' % (k, pycompat.bytestr(d[k])))
         for k in sorted(d)
     ]
     return "\0".join(items)
 
-def encodecopies(copies):
-    items = [
-        '%s\0%s' % (k, copies[k])
-        for k in sorted(copies)
-    ]
+def encodecopies(files, copies):
+    items = []
+    for i, dst in enumerate(files):
+        if dst in copies:
+            items.append('%d\0%s' % (i, copies[dst]))
+    if len(items) != len(copies):
+        raise error.ProgrammingError('some copy targets missing from file list')
     return "\n".join(items)
 
-def decodecopies(data):
+def decodecopies(files, data):
     try:
         copies = {}
         for l in data.split('\n'):
-            k, v = l.split('\0')
-            copies[k] = v
+            strindex, src = l.split('\0')
+            i = int(strindex)
+            dst = files[i]
+            copies[dst] = src
         return copies
-    except ValueError:
+    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('%d' % i)
     return '\0'.join(indices)
 
 def decodefileindices(files, data):
     try:
         subset = []
         for strindex in data.split('\0'):
             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 '\n'.join([l.rstrip() for l in desc.splitlines()]).strip('\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 = ""
         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, "".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='r', checkambig=False):
         if name != target:
             return opener(name, mode)
         return opener(name + ".a", mode)
     return _divert
 
 def _delayopener(opener, target, buf):
     """build an opener that stores chunks in 'buf' instead of 'target'"""
     def _delay(name, mode='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='')
     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='')
 
 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',
     )
 
     def __new__(cls, text):
         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('\n')
         nl2 = text.index('\n', nl1 + 1)
         nl3 = text.index('\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] == '\n':
             doublenl = nl3
         else:
             doublenl = text.index('\n\n', nl3 + 1)
 
         self._offsets = (nl1, nl2, nl3, doublenl)
         self._text = text
 
         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(' ', 2)[0:2]
 
     @property
     def _rawextra(self):
         off = self._offsets
         dateextra = self._text[off[1] + 1:off[2]]
         fields = dateextra.split(' ', 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('\n')
 
     @property
     def filesadded(self):
         rawindices = self.extra.get('filesadded')
         return rawindices and decodefileindices(self.files, rawindices)
 
     @property
     def filesremoved(self):
         rawindices = self.extra.get('filesremoved')
         return rawindices and decodefileindices(self.files, rawindices)
 
     @property
     def p1copies(self):
         rawcopies = self.extra.get('p1copies')
-        return rawcopies and decodecopies(rawcopies)
+        return rawcopies and decodecopies(self.files, rawcopies)
 
     @property
     def p2copies(self):
         rawcopies = self.extra.get('p2copies')
-        return rawcopies and decodecopies(rawcopies)
+        return rawcopies and 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('00changelog.i.a'):
             indexfile = '00changelog.i.a'
         else:
             indexfile = '00changelog.i'
 
         datafile = '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()
 
     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 reachableroots(self, minroot, heads, roots, includepath=False):
         return self.index.reachableroots2(minroot, heads, roots, includepath)
 
     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,
                                             _('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):
         "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 + '.a'):
                     self._realopener.unlink(self.indexfile + '.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('cl-%i' % id(self), self._writepending)
         tr.addfinalize('cl-%i' % id(self), self._finalize)
 
     def _finalize(self, tr):
         "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 + ".a"
             nfile = self.opener.open(tmpname)
             nfile.close()
             self.opener.rename(tmpname, self.indexfile, checkambig=True)
         elif self._delaybuf:
             fp = self.opener(self.indexfile, 'a', checkambig=True)
             fp.write("".join(self._delaybuf))
             fp.close()
             self._delaybuf = None
         self._divert = False
         # split when we're done
         self._enforceinlinesize(tr)
 
     def _writepending(self, tr):
         "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 + ".a"
             # register as a temp file to ensure cleanup on failure
             tr.registertmp(pendingfilename)
             # write existing data
             fp2 = self._realopener(pendingfilename, "w")
             fp2.write(fp1.read())
             # add pending data
             fp2.write("".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.revision(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."""
         return changelogrevision(self.revision(nodeorrev))
 
     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("\n\n")
         l = text[:last].split('\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(_("empty username"))
         if "\n" in user:
             raise error.StorageError(_("username %r contains a newline")
                                      % pycompat.bytestr(user))
 
         desc = stripdesc(desc)
 
         if date:
             parseddate = "%d %d" % dateutil.parsedate(date)
         else:
             parseddate = "%d %d" % dateutil.makedate()
         if extra:
             branch = extra.get("branch")
             if branch in ("default", ""):
                 del extra["branch"]
             elif branch in (".", "null", "tip"):
                 raise error.StorageError(_('the name \'%s\' is reserved')
                                          % branch)
         extrasentries = p1copies, p2copies, filesadded, filesremoved
         if extra is None and any(x is not None for x in extrasentries):
             extra = {}
+        sortedfiles = sorted(files)
         if p1copies is not None:
-            extra['p1copies'] = encodecopies(p1copies)
+            extra['p1copies'] = encodecopies(sortedfiles, p1copies)
         if p2copies is not None:
-            extra['p2copies'] = encodecopies(p2copies)
-        sortedfiles = sorted(files)
+            extra['p2copies'] = encodecopies(sortedfiles, p2copies)
         if filesadded is not None:
             extra['filesadded'] = encodefileindices(sortedfiles, filesadded)
         if filesremoved is not None:
             extra['filesremoved'] = encodefileindices(sortedfiles, filesremoved)
 
         if extra:
             extra = encodeextra(extra)
             parseddate = "%s %s" % (parseddate, extra)
         l = [hex(manifest), user, parseddate] + sortedfiles + ["", desc]
         text = "\n".join(l)
         return self.addrevision(text, transaction, len(self), p1, p2)
 
     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("branch")), '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('revduplicates', [])
         duplicates.append(self.rev(node))

tests/test-copies-in-changeset.t

@@ -1,183 +1,183
 
   $ cat >> $HGRCPATH << EOF
   > [experimental]
   > copies.write-to=changeset-only
   > copies.read-from=changeset-only
   > [alias]
   > changesetcopies = log -r . -T 'files: {files}
   >   {extras % "{ifcontains("files", key, "{key}: {value}\n")}"}
   >   {extras % "{ifcontains("copies", key, "{key}: {value}\n")}"}'
   > showcopies = log -r . -T '{file_copies % "{source} -> {name}\n"}'
   > [extensions]
   > rebase =
   > EOF
 
 Check that copies are recorded correctly
 
   $ hg init repo
   $ cd repo
   $ echo a > a
   $ hg add a
   $ hg ci -m initial
   $ hg cp a b
   $ hg cp a c
   $ hg cp a d
   $ hg ci -m 'copy a to b, c, and d'
   $ hg changesetcopies
   files: b c d
   filesadded: 0\x001\x002 (esc)
   
-  p1copies: b\x00a (esc)
-  c\x00a (esc)
-  d\x00a (esc)
+  p1copies: 0\x00a (esc)
+  1\x00a (esc)
+  2\x00a (esc)
   $ hg showcopies
   a -> b
   a -> c
   a -> d
   $ hg showcopies --config experimental.copies.read-from=compatibility
   a -> b
   a -> c
   a -> d
   $ hg showcopies --config experimental.copies.read-from=filelog-only
 
 Check that renames are recorded correctly
 
   $ hg mv b b2
   $ hg ci -m 'rename b to b2'
   $ hg changesetcopies
   files: b b2
   filesadded: 1
   filesremoved: 0
   
-  p1copies: b2\x00b (esc)
+  p1copies: 1\x00b (esc)
   $ hg showcopies
   b -> b2
 
 Rename onto existing file. This should get recorded in the changeset files list and in the extras,
 even though there is no filelog entry.
 
   $ hg cp b2 c --force
   $ hg st --copies
   M c
     b2
   $ hg debugindex c
      rev linkrev nodeid       p1           p2
        0       1 b789fdd96dc2 000000000000 000000000000
   $ hg ci -m 'move b onto d'
   $ hg changesetcopies
   files: c
   
-  p1copies: c\x00b2 (esc)
+  p1copies: 0\x00b2 (esc)
   $ hg showcopies
   b2 -> c
   $ hg debugindex c
      rev linkrev nodeid       p1           p2
        0       1 b789fdd96dc2 000000000000 000000000000
 
 Create a merge commit with copying done during merge.
 
   $ hg co 0
   0 files updated, 0 files merged, 3 files removed, 0 files unresolved
   $ hg cp a e
   $ hg cp a f
   $ hg ci -m 'copy a to e and f'
   created new head
   $ hg merge 3
   3 files updated, 0 files merged, 0 files removed, 0 files unresolved
   (branch merge, don't forget to commit)
 File 'a' exists on both sides, so 'g' could be recorded as being from p1 or p2, but we currently
 always record it as being from p1
   $ hg cp a g
 File 'd' exists only in p2, so 'h' should be from p2
   $ hg cp d h
 File 'f' exists only in p1, so 'i' should be from p1
   $ hg cp f i
   $ hg ci -m 'merge'
   $ hg changesetcopies
   files: g h i
   filesadded: 0\x001\x002 (esc)
   
-  p1copies: g\x00a (esc)
-  i\x00f (esc)
-  p2copies: h\x00d (esc)
+  p1copies: 0\x00a (esc)
+  2\x00f (esc)
+  p2copies: 1\x00d (esc)
   $ hg showcopies
   a -> g
   d -> h
   f -> i
 
 Test writing to both changeset and filelog
 
   $ hg cp a j
   $ hg ci -m 'copy a to j' --config experimental.copies.write-to=compatibility
   $ hg changesetcopies
   files: j
   filesadded: 0
   filesremoved: 
   
-  p1copies: j\x00a (esc)
+  p1copies: 0\x00a (esc)
   p2copies: 
   $ hg debugdata j 0
   \x01 (esc)
   copy: a
   copyrev: b789fdd96dc2f3bd229c1dd8eedf0fc60e2b68e3
   \x01 (esc)
   a
   $ hg showcopies
   a -> j
   $ hg showcopies --config experimental.copies.read-from=compatibility
   a -> j
   $ hg showcopies --config experimental.copies.read-from=filelog-only
   a -> j
 The entries should be written to extras even if they're empty (so the client
 won't have to fall back to reading from filelogs)
   $ echo x >> j
   $ hg ci -m 'modify j' --config experimental.copies.write-to=compatibility
   $ hg changesetcopies
   files: j
   filesadded: 
   filesremoved: 
   
   p1copies: 
   p2copies: 
 
 Test writing only to filelog
 
   $ hg cp a k
   $ hg ci -m 'copy a to k' --config experimental.copies.write-to=filelog-only
   $ hg changesetcopies
   files: k
   
   $ hg debugdata k 0
   \x01 (esc)
   copy: a
   copyrev: b789fdd96dc2f3bd229c1dd8eedf0fc60e2b68e3
   \x01 (esc)
   a
   $ hg showcopies
   $ hg showcopies --config experimental.copies.read-from=compatibility
   a -> k
   $ hg showcopies --config experimental.copies.read-from=filelog-only
   a -> k
 
   $ cd ..
 
 Test rebasing a commit with copy information
 
   $ hg init rebase-rename
   $ cd rebase-rename
   $ echo a > a
   $ hg ci -Aqm 'add a'
   $ echo a2 > a
   $ hg ci -m 'modify a'
   $ hg co -q 0
   $ hg mv a b
   $ hg ci -qm 'rename a to b'
   $ hg rebase -d 1 --config rebase.experimental.inmemory=yes
-  rebasing 2:acfc33f3aa6d "rename a to b" (tip)
+  rebasing 2:fc7287ac5b9b "rename a to b" (tip)
   merging a and b to b
-  saved backup bundle to $TESTTMP/rebase-rename/.hg/strip-backup/acfc33f3aa6d-81d0180d-rebase.hg
+  saved backup bundle to $TESTTMP/rebase-rename/.hg/strip-backup/fc7287ac5b9b-8f2a95ec-rebase.hg
   $ hg st --change . --copies
   A b
     a
   R a
   $ cd ..

tests/test-copies.t

@@ -1,647 +1,647
 #testcases filelog compatibility changeset
 
   $ 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
 
   $ 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
 
 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
 
 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'
   $ hg cp x y
   $ hg ci -m '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
   @  3 copy x onto y (again)
   |  y
   o  2 remove y
   |  y
   o  1 copy x to y
   |  y
   o  0 add x
      x
   $ hg debugp1copies -r 3
   x -> y
   $ hg debugpathcopies 0 3
   x -> y
 
 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 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).
   $ newrepo
   $ echo x > x
   $ hg ci -Aqm 'add x'
   $ hg mv x y
   $ hg ci -m 'rename x to y'
   $ hg rm y
   $ hg ci -qm 'remove y'
   $ echo x > y
   $ hg ci -Aqm 'add back y'
   $ hg l
   @  3 add back y
   |  y
   o  2 remove y
   |  y
   o  1 rename x to y
   |  x y
   o  0 add x
      x
   $ hg debugp1copies -r 3
   $ 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
 
 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
 
 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
   |\   x
   | 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 !)
 
 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 !)
   $ hg debugp2copies -r 2
   x -> z (no-changeset !)
   $ hg debugpathcopies 1 2
   x -> z (changeset !)
   $ hg debugpathcopies 0 2
   x -> z (no-changeset !)
 
 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. Pathcopies from the
 first side should not include the y->z rename since y didn't exist in the merge base.
   $ 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
 
 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.
   $ 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
   |\   y z
   +---o  4 merge 1 into 3
   | |/   x 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
   $ hg debugpathcopies 2 4
   $ hg debugpathcopies 0 4
   x -> z (filelog !)
   y -> z (compatibility !)
   $ hg debugpathcopies 1 5
   $ hg debugpathcopies 2 5
   $ 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 df722b7fe2d5 -r ba3ddbbdfd96 b1 (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 5:619047c26bf8 "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 6:9ddc6fb3b691 "added willconflict and d" (tip) (changeset !)