convert: fix bad conversion of copies when hg.startrev is specified

The 'copynode' was looked up in self.keep as if it was a changeset node. It is
however a filelog node, and self.keep would thus fail if it actually looked at
its parameter ... which it only did if a startrev was specified.

Instead we now don't check the copy node - we don't have to. It must have been
copied from one of the parents, and we already check whether one of the parents
have the copy source.

We could perhaps use linkrev to see if the corresponding changeset was
converted ... but that would sometimes be wrong.

The existing test of this was wrong - now it is better, but it seems like it
exposes a 'log' issue.

hgext/convert/hg.py

@@ -1,403 +1,403 b''
 # hg.py - hg backend for convert extension
 #
 #  Copyright 2005-2009 Matt Mackall <[e-mail]> and others
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 # Notes for hg->hg conversion:
 #
 # * Old versions of Mercurial didn't trim the whitespace from the ends
 #   of commit messages, but new versions do.  Changesets created by
 #   those older versions, then converted, may thus have different
 #   hashes for changesets that are otherwise identical.
 #
 # * Using "--config convert.hg.saverev=true" will make the source
 #   identifier to be stored in the converted revision. This will cause
 #   the converted revision to have a different identity than the
 #   source.
 
 
 import os, time, cStringIO
 from mercurial.i18n import _
 from mercurial.node import bin, hex, nullid
 from mercurial import hg, util, context, bookmarks, error
 
 from common import NoRepo, commit, converter_source, converter_sink
 
 class mercurial_sink(converter_sink):
     def __init__(self, ui, path):
         converter_sink.__init__(self, ui, path)
         self.branchnames = ui.configbool('convert', 'hg.usebranchnames', True)
         self.clonebranches = ui.configbool('convert', 'hg.clonebranches', False)
         self.tagsbranch = ui.config('convert', 'hg.tagsbranch', 'default')
         self.lastbranch = None
         if os.path.isdir(path) and len(os.listdir(path)) > 0:
             try:
                 self.repo = hg.repository(self.ui, path)
                 if not self.repo.local():
                     raise NoRepo(_('%s is not a local Mercurial repository')
                                  % path)
             except error.RepoError, err:
                 ui.traceback()
                 raise NoRepo(err.args[0])
         else:
             try:
                 ui.status(_('initializing destination %s repository\n') % path)
                 self.repo = hg.repository(self.ui, path, create=True)
                 if not self.repo.local():
                     raise NoRepo(_('%s is not a local Mercurial repository')
                                  % path)
                 self.created.append(path)
             except error.RepoError:
                 ui.traceback()
                 raise NoRepo(_("could not create hg repository %s as sink")
                              % path)
         self.lock = None
         self.wlock = None
         self.filemapmode = False
 
     def before(self):
         self.ui.debug('run hg sink pre-conversion action\n')
         self.wlock = self.repo.wlock()
         self.lock = self.repo.lock()
 
     def after(self):
         self.ui.debug('run hg sink post-conversion action\n')
         if self.lock:
             self.lock.release()
         if self.wlock:
             self.wlock.release()
 
     def revmapfile(self):
         return self.repo.join("shamap")
 
     def authorfile(self):
         return self.repo.join("authormap")
 
     def getheads(self):
         h = self.repo.changelog.heads()
         return [hex(x) for x in h]
 
     def setbranch(self, branch, pbranches):
         if not self.clonebranches:
             return
 
         setbranch = (branch != self.lastbranch)
         self.lastbranch = branch
         if not branch:
             branch = 'default'
         pbranches = [(b[0], b[1] and b[1] or 'default') for b in pbranches]
         pbranch = pbranches and pbranches[0][1] or 'default'
 
         branchpath = os.path.join(self.path, branch)
         if setbranch:
             self.after()
             try:
                 self.repo = hg.repository(self.ui, branchpath)
             except Exception:
                 self.repo = hg.repository(self.ui, branchpath, create=True)
             self.before()
 
         # pbranches may bring revisions from other branches (merge parents)
         # Make sure we have them, or pull them.
         missings = {}
         for b in pbranches:
             try:
                 self.repo.lookup(b[0])
             except Exception:
                 missings.setdefault(b[1], []).append(b[0])
 
         if missings:
             self.after()
             for pbranch, heads in sorted(missings.iteritems()):
                 pbranchpath = os.path.join(self.path, pbranch)
                 prepo = hg.peer(self.ui, {}, pbranchpath)
                 self.ui.note(_('pulling from %s into %s\n') % (pbranch, branch))
                 self.repo.pull(prepo, [prepo.lookup(h) for h in heads])
             self.before()
 
     def _rewritetags(self, source, revmap, data):
         fp = cStringIO.StringIO()
         for line in data.splitlines():
             s = line.split(' ', 1)
             if len(s) != 2:
                 continue
             revid = revmap.get(source.lookuprev(s[0]))
             if not revid:
                 continue
             fp.write('%s %s\n' % (revid, s[1]))
         return fp.getvalue()
 
     def putcommit(self, files, copies, parents, commit, source, revmap):
 
         files = dict(files)
         def getfilectx(repo, memctx, f):
             v = files[f]
             data, mode = source.getfile(f, v)
             if f == '.hgtags':
                 data = self._rewritetags(source, revmap, data)
             return context.memfilectx(f, data, 'l' in mode, 'x' in mode,
                                       copies.get(f))
 
         pl = []
         for p in parents:
             if p not in pl:
                 pl.append(p)
         parents = pl
         nparents = len(parents)
         if self.filemapmode and nparents == 1:
             m1node = self.repo.changelog.read(bin(parents[0]))[0]
             parent = parents[0]
 
         if len(parents) < 2:
             parents.append(nullid)
         if len(parents) < 2:
             parents.append(nullid)
         p2 = parents.pop(0)
 
         text = commit.desc
         extra = commit.extra.copy()
         if self.branchnames and commit.branch:
             extra['branch'] = commit.branch
         if commit.rev:
             extra['convert_revision'] = commit.rev
 
         while parents:
             p1 = p2
             p2 = parents.pop(0)
             ctx = context.memctx(self.repo, (p1, p2), text, files.keys(),
                                  getfilectx, commit.author, commit.date, extra)
             self.repo.commitctx(ctx)
             text = "(octopus merge fixup)\n"
             p2 = hex(self.repo.changelog.tip())
 
         if self.filemapmode and nparents == 1:
             man = self.repo.manifest
             mnode = self.repo.changelog.read(bin(p2))[0]
             closed = 'close' in commit.extra
             if not closed and not man.cmp(m1node, man.revision(mnode)):
                 self.ui.status(_("filtering out empty revision\n"))
                 self.repo.rollback(force=True)
                 return parent
         return p2
 
     def puttags(self, tags):
         try:
             parentctx = self.repo[self.tagsbranch]
             tagparent = parentctx.node()
         except error.RepoError:
             parentctx = None
             tagparent = nullid
 
         try:
             oldlines = sorted(parentctx['.hgtags'].data().splitlines(True))
         except Exception:
             oldlines = []
 
         newlines = sorted([("%s %s\n" % (tags[tag], tag)) for tag in tags])
         if newlines == oldlines:
             return None, None
         data = "".join(newlines)
         def getfilectx(repo, memctx, f):
             return context.memfilectx(f, data, False, False, None)
 
         self.ui.status(_("updating tags\n"))
         date = "%s 0" % int(time.mktime(time.gmtime()))
         extra = {'branch': self.tagsbranch}
         ctx = context.memctx(self.repo, (tagparent, None), "update tags",
                              [".hgtags"], getfilectx, "convert-repo", date,
                              extra)
         self.repo.commitctx(ctx)
         return hex(self.repo.changelog.tip()), hex(tagparent)
 
     def setfilemapmode(self, active):
         self.filemapmode = active
 
     def putbookmarks(self, updatedbookmark):
         if not len(updatedbookmark):
             return
 
         self.ui.status(_("updating bookmarks\n"))
         destmarks = self.repo._bookmarks
         for bookmark in updatedbookmark:
             destmarks[bookmark] = bin(updatedbookmark[bookmark])
         destmarks.write()
 
     def hascommit(self, rev):
         if rev not in self.repo and self.clonebranches:
             raise util.Abort(_('revision %s not found in destination '
                                'repository (lookups with clonebranches=true '
                                'are not implemented)') % rev)
         return rev in self.repo
 
 class mercurial_source(converter_source):
     def __init__(self, ui, path, rev=None):
         converter_source.__init__(self, ui, path, rev)
         self.ignoreerrors = ui.configbool('convert', 'hg.ignoreerrors', False)
         self.ignored = set()
         self.saverev = ui.configbool('convert', 'hg.saverev', False)
         try:
             self.repo = hg.repository(self.ui, path)
             # try to provoke an exception if this isn't really a hg
             # repo, but some other bogus compatible-looking url
             if not self.repo.local():
                 raise error.RepoError
         except error.RepoError:
             ui.traceback()
             raise NoRepo(_("%s is not a local Mercurial repository") % path)
         self.lastrev = None
         self.lastctx = None
         self._changescache = None
         self.convertfp = None
         # Restrict converted revisions to startrev descendants
         startnode = ui.config('convert', 'hg.startrev')
         if startnode is not None:
             try:
                 startnode = self.repo.lookup(startnode)
             except error.RepoError:
                 raise util.Abort(_('%s is not a valid start revision')
                                  % startnode)
             startrev = self.repo.changelog.rev(startnode)
             children = {startnode: 1}
             for rev in self.repo.changelog.descendants([startrev]):
                 children[self.repo.changelog.node(rev)] = 1
             self.keep = children.__contains__
         else:
             self.keep = util.always
 
     def changectx(self, rev):
         if self.lastrev != rev:
             self.lastctx = self.repo[rev]
             self.lastrev = rev
         return self.lastctx
 
     def parents(self, ctx):
         return [p for p in ctx.parents() if p and self.keep(p.node())]
 
     def getheads(self):
         if self.rev:
             heads = [self.repo[self.rev].node()]
         else:
             heads = self.repo.heads()
         return [hex(h) for h in heads if self.keep(h)]
 
     def getfile(self, name, rev):
         try:
             fctx = self.changectx(rev)[name]
             return fctx.data(), fctx.flags()
         except error.LookupError, err:
             raise IOError(err)
 
     def getchanges(self, rev):
         ctx = self.changectx(rev)
         parents = self.parents(ctx)
         if not parents:
             files = sorted(ctx.manifest())
             # getcopies() is not needed for roots, but it is a simple way to
             # detect missing revlogs and abort on errors or populate
             # self.ignored
             self.getcopies(ctx, parents, files)
             return [(f, rev) for f in files if f not in self.ignored], {}
         if self._changescache and self._changescache[0] == rev:
             m, a, r = self._changescache[1]
         else:
             m, a, r = self.repo.status(parents[0].node(), ctx.node())[:3]
         # getcopies() detects missing revlogs early, run it before
         # filtering the changes.
         copies = self.getcopies(ctx, parents, m + a)
         changes = [(name, rev) for name in m + a + r
                    if name not in self.ignored]
         return sorted(changes), copies
 
     def getcopies(self, ctx, parents, files):
         copies = {}
         for name in files:
             if name in self.ignored:
                 continue
             try:
-                copysource, copynode = ctx.filectx(name).renamed()
-                if copysource in self.ignored or not self.keep(copynode):
+                copysource, _copynode = ctx.filectx(name).renamed()
+                if copysource in self.ignored:
                     continue
                 # Ignore copy sources not in parent revisions
                 found = False
                 for p in parents:
                     if copysource in p:
                         found = True
                         break
                 if not found:
                     continue
                 copies[name] = copysource
             except TypeError:
                 pass
             except error.LookupError, e:
                 if not self.ignoreerrors:
                     raise
                 self.ignored.add(name)
                 self.ui.warn(_('ignoring: %s\n') % e)
         return copies
 
     def getcommit(self, rev):
         ctx = self.changectx(rev)
         parents = [p.hex() for p in self.parents(ctx)]
         if self.saverev:
             crev = rev
         else:
             crev = None
         return commit(author=ctx.user(),
                       date=util.datestr(ctx.date(), '%Y-%m-%d %H:%M:%S %1%2'),
                       desc=ctx.description(), rev=crev, parents=parents,
                       branch=ctx.branch(), extra=ctx.extra(),
                       sortkey=ctx.rev())
 
     def gettags(self):
         tags = [t for t in self.repo.tagslist() if t[0] != 'tip']
         return dict([(name, hex(node)) for name, node in tags
                      if self.keep(node)])
 
     def getchangedfiles(self, rev, i):
         ctx = self.changectx(rev)
         parents = self.parents(ctx)
         if not parents and i is None:
             i = 0
             changes = [], ctx.manifest().keys(), []
         else:
             i = i or 0
             changes = self.repo.status(parents[i].node(), ctx.node())[:3]
         changes = [[f for f in l if f not in self.ignored] for l in changes]
 
         if i == 0:
             self._changescache = (rev, changes)
 
         return changes[0] + changes[1] + changes[2]
 
     def converted(self, rev, destrev):
         if self.convertfp is None:
             self.convertfp = open(self.repo.join('shamap'), 'a')
         self.convertfp.write('%s %s\n' % (destrev, rev))
         self.convertfp.flush()
 
     def before(self):
         self.ui.debug('run hg source pre-conversion action\n')
 
     def after(self):
         self.ui.debug('run hg source post-conversion action\n')
 
     def hasnativeorder(self):
         return True
 
     def hasnativeclose(self):
         return True
 
     def lookuprev(self, rev):
         try:
             return hex(self.repo.lookup(rev))
         except error.RepoError:
             return None
 
     def getbookmarks(self):
         return bookmarks.listbookmarks(self.repo)
 
     def checkrevformat(self, revstr):
         """ Mercurial, revision string is a 40 byte hex """
         self.checkhexformat(revstr)

tests/test-convert-hg-startrev.t

@@ -1,175 +1,185 b''
 
   $ cat >> $HGRCPATH <<EOF
   > [extensions]
   > graphlog =
   > convert =
   > [convert]
   > hg.saverev = yes
   > EOF
 
   $ glog()
   > {
   >     hg -R "$1" glog --template '{rev} "{desc}" files: {files}\n'
   > }
 
   $ hg init source
   $ cd source
 
   $ echo a > a
   $ echo b > b
   $ echo f > f
   $ hg ci -d '0 0' -qAm '0: add a b f'
   $ echo c > c
   $ hg move f d
   $ hg ci -d '1 0' -qAm '1: add c, move f to d'
   $ hg copy a e
   $ echo b >> b
   $ hg ci -d '2 0' -qAm '2: copy e from a, change b'
   $ hg up -C 0
   2 files updated, 0 files merged, 3 files removed, 0 files unresolved
   $ echo a >> a
   $ hg ci -d '3 0' -qAm '3: change a'
   $ hg merge
   merging a and e to e
   3 files updated, 1 files merged, 1 files removed, 0 files unresolved
   (branch merge, don't forget to commit)
   $ hg ci -d '4 0' -qAm '4: merge 2 and 3'
   $ echo a >> a
   $ hg ci -d '5 0' -qAm '5: change a'
   $ cd ..
 
 Convert from null revision
 
   $ hg convert --config convert.hg.startrev=null source full
   initializing destination full repository
   scanning source...
   sorting...
   converting...
   5 0: add a b f
   4 1: add c, move f to d
   3 2: copy e from a, change b
   2 3: change a
   1 4: merge 2 and 3
   0 5: change a
 
   $ glog full
   o  5 "5: change a" files: a
   |
   o    4 "4: merge 2 and 3" files: e f
   |\
   | o  3 "3: change a" files: a
   | |
   o |  2 "2: copy e from a, change b" files: b e
   | |
   o |  1 "1: add c, move f to d" files: c d f
   |/
   o  0 "0: add a b f" files: a b f
   
   $ rm -Rf full
 
 Convert from zero revision
 
   $ hg convert --config convert.hg.startrev=0 source full
   initializing destination full repository
   scanning source...
   sorting...
   converting...
   5 0: add a b f
   4 1: add c, move f to d
   3 2: copy e from a, change b
   2 3: change a
   1 4: merge 2 and 3
   0 5: change a
 
   $ glog full
   o  5 "5: change a" files: a
   |
   o    4 "4: merge 2 and 3" files: e f
   |\
   | o  3 "3: change a" files: a
   | |
   o |  2 "2: copy e from a, change b" files: b e
   | |
   o |  1 "1: add c, move f to d" files: c d f
   |/
   o  0 "0: add a b f" files: a b f
   
 Convert from merge parent
 
   $ hg convert --config convert.hg.startrev=1 source conv1
   initializing destination conv1 repository
   scanning source...
   sorting...
   converting...
   3 1: add c, move f to d
   2 2: copy e from a, change b
   1 4: merge 2 and 3
   0 5: change a
 
   $ glog conv1
   o  3 "5: change a" files: a
   |
   o  2 "4: merge 2 and 3" files: a e
   |
   o  1 "2: copy e from a, change b" files: b e
   |
   o  0 "1: add c, move f to d" files: a b c d
   
   $ cd conv1
   $ hg up -q
 
 Check copy preservation
 
+  $ hg st -C --change 2 e
+  M e
+  $ hg st -C --change 1 e
+  A e
+    a
+  $ hg st -C --change 0 a
+  A a
+
+(It seems like a bug in log that the following doesn't show rev 1.)
+
   $ hg log --follow --copies e
-  changeset:   2:60633ee11cfa
+  changeset:   2:82bbac3d2cf4
   user:        test
   date:        Thu Jan 01 00:00:04 1970 +0000
   summary:     4: merge 2 and 3
   
-  changeset:   1:d56e8baefff8
+  changeset:   0:23c3be426dce
   user:        test
-  date:        Thu Jan 01 00:00:02 1970 +0000
-  summary:     2: copy e from a, change b
+  date:        Thu Jan 01 00:00:01 1970 +0000
+  summary:     1: add c, move f to d
   
 Check copy removal on missing parent
 
   $ hg log --follow --copies d
   changeset:   0:23c3be426dce
   user:        test
   date:        Thu Jan 01 00:00:01 1970 +0000
   summary:     1: add c, move f to d
   
   $ hg cat -r tip a b
   a
   a
   a
   b
   b
   $ hg -q verify
   $ cd ..
 
 Convert from merge
 
   $ hg convert --config convert.hg.startrev=4 source conv4
   initializing destination conv4 repository
   scanning source...
   sorting...
   converting...
   1 4: merge 2 and 3
   0 5: change a
   $ glog conv4
   o  1 "5: change a" files: a
   |
   o  0 "4: merge 2 and 3" files: a b c d e
   
   $ cd conv4
   $ hg up -C
   5 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ hg cat -r tip a b
   a
   a
   a
   b
   b
   $ hg -q verify
   $ cd ..