--- a/hgext/convert/__init__.py	Tue Aug 26 22:03:32 2014 +0200
+++ b/hgext/convert/__init__.py	Tue Aug 26 22:03:32 2014 +0200
@@ -29,6 +29,8 @@
     ('A', 'authormap', '', _('remap usernames using this file'), _('FILE')),
     ('', 'filemap', '', _('remap file names using contents of file'),
      _('FILE')),
+    ('', 'full', None,
+     _('apply filemap changes by converting all files again')),
     ('', 'splicemap', '', _('splice synthesized history into place'),
      _('FILE')),
     ('', 'branchmap', '', _('change branch names while converting'),
@@ -131,6 +133,14 @@
     it is converted. To rename from a subdirectory into the root of
     the repository, use ``.`` as the path to rename to.
 
+    ``--full`` will make sure the converted changesets contain exactly
+    the right files with the right content. It will make a full
+    conversion of all files, not just the ones that have
+    changed. Files that already are correct will not be changed. This
+    can be used to apply filemap changes when converting
+    incrementally. This is currently only supported for Mercurial and
+    Subversion.
+
     The splicemap is a file that allows insertion of synthetic
     history, letting you specify the parents of a revision. This is
     useful if you want to e.g. give a Subversion merge two parents, or

--- a/hgext/convert/bzr.py	Tue Aug 26 22:03:32 2014 +0200
+++ b/hgext/convert/bzr.py	Tue Aug 26 22:03:32 2014 +0200
@@ -134,8 +134,9 @@
             sio = revtree.get_file(fileid)
             return sio.read(), mode
 
-    def getchanges(self, version):
-        # set up caches: modecache and revtree
+    def getchanges(self, version, full):
+        if full:
+            raise util.Abort(_("convert from cvs do not support --full"))
         self._modecache = {}
         self._revtree = self.sourcerepo.revision_tree(version)
         # get the parentids from the cache

--- a/hgext/convert/common.py	Tue Aug 26 22:03:32 2014 +0200
+++ b/hgext/convert/common.py	Tue Aug 26 22:03:32 2014 +0200
@@ -93,12 +93,13 @@
         """
         raise NotImplementedError
 
-    def getchanges(self, version):
+    def getchanges(self, version, full):
         """Returns a tuple of (files, copies).
 
         files is a sorted list of (filename, id) tuples for all files
         changed between version and its first parent returned by
-        getcommit(). id is the source revision id of the file.
+        getcommit(). If full, all files in that revision is returned.
+        id is the source revision id of the file.
 
         copies is a dictionary of dest: source
         """
@@ -204,7 +205,7 @@
         mapping equivalent authors identifiers for each system."""
         return None
 
-    def putcommit(self, files, copies, parents, commit, source, revmap):
+    def putcommit(self, files, copies, parents, commit, source, revmap, full):
         """Create a revision with all changed files listed in 'files'
         and having listed parents. 'commit' is a commit object
         containing at a minimum the author, date, and message for this
@@ -212,7 +213,8 @@
         'copies' is a dictionary mapping destinations to sources,
         'source' is the source repository, and 'revmap' is a mapfile
         of source revisions to converted revisions. Only getfile() and
-        lookuprev() should be called on 'source'.
+        lookuprev() should be called on 'source'. 'full' means that 'files'
+        is complete and all other files should be removed.
 
         Note that the sink repository is not told to update itself to
         a particular revision (or even what that revision would be)

--- a/hgext/convert/convcmd.py	Tue Aug 26 22:03:32 2014 +0200
+++ b/hgext/convert/convcmd.py	Tue Aug 26 22:03:32 2014 +0200
@@ -386,8 +386,8 @@
 
     def copy(self, rev):
         commit = self.commitcache[rev]
-
-        changes = self.source.getchanges(rev)
+        full = self.opts.get('full')
+        changes = self.source.getchanges(rev, full)
         if isinstance(changes, basestring):
             if changes == SKIPREV:
                 dest = SKIPREV
@@ -413,7 +413,7 @@
             parents = [b[0] for b in pbranches]
         source = progresssource(self.ui, self.source, len(files))
         newnode = self.dest.putcommit(files, copies, parents, commit,
-                                      source, self.map)
+                                      source, self.map, full)
         source.close()
         self.source.converted(rev, newnode)
         self.map[rev] = newnode

--- a/hgext/convert/cvs.py	Tue Aug 26 22:03:32 2014 +0200
+++ b/hgext/convert/cvs.py	Tue Aug 26 22:03:32 2014 +0200
@@ -258,7 +258,9 @@
                 else:
                     raise util.Abort(_("unknown CVS response: %s") % line)
 
-    def getchanges(self, rev):
+    def getchanges(self, rev, full):
+        if full:
+            raise util.Abort(_("convert from cvs do not support --full"))
         self._parse()
         return sorted(self.files[rev].iteritems()), {}
 

--- a/hgext/convert/darcs.py	Tue Aug 26 22:03:32 2014 +0200
+++ b/hgext/convert/darcs.py	Tue Aug 26 22:03:32 2014 +0200
@@ -156,7 +156,9 @@
             output, status = self.run('revert', all=True, repodir=self.tmppath)
             self.checkexit(status, output)
 
-    def getchanges(self, rev):
+    def getchanges(self, rev, full):
+        if full:
+            raise util.Abort(_("convert from darcs do not support --full"))
         copies = {}
         changes = []
         man = None

--- a/hgext/convert/filemap.py	Tue Aug 26 22:03:32 2014 +0200
+++ b/hgext/convert/filemap.py	Tue Aug 26 22:03:32 2014 +0200
@@ -304,7 +304,7 @@
         wrev.add(rev)
         self.wantedancestors[rev] = wrev
 
-    def getchanges(self, rev):
+    def getchanges(self, rev, full):
         parents = self.commits[rev].parents
         if len(parents) > 1:
             self.rebuild()
@@ -384,7 +384,7 @@
         # Get the real changes and do the filtering/mapping. To be
         # able to get the files later on in getfile, we hide the
         # original filename in the rev part of the return value.
-        changes, copies = self.base.getchanges(rev)
+        changes, copies = self.base.getchanges(rev, full)
         files = {}
         for f, r in changes:
             newf = self.filemapper(f)

--- a/hgext/convert/git.py	Tue Aug 26 22:03:32 2014 +0200
+++ b/hgext/convert/git.py	Tue Aug 26 22:03:32 2014 +0200
@@ -180,7 +180,9 @@
                 continue
             m.node = node.strip()
 
-    def getchanges(self, version):
+    def getchanges(self, version, full):
+        if full:
+            raise util.Abort(_("convert from git do not support --full"))
         self.modecache = {}
         fh = self.gitopen("git diff-tree -z --root -m -r %s" % version)
         changes = []

--- a/hgext/convert/gnuarch.py	Tue Aug 26 22:03:32 2014 +0200
+++ b/hgext/convert/gnuarch.py	Tue Aug 26 22:03:32 2014 +0200
@@ -142,7 +142,9 @@
 
         return self._getfile(name, rev)
 
-    def getchanges(self, rev):
+    def getchanges(self, rev, full):
+        if full:
+            raise util.Abort(_("convert from arch do not support --full"))
         self._update(rev)
         changes = []
         copies = {}

--- a/hgext/convert/hg.py	Tue Aug 26 22:03:32 2014 +0200
+++ b/hgext/convert/hg.py	Tue Aug 26 22:03:32 2014 +0200
@@ -128,11 +128,13 @@
             fp.write('%s %s\n' % (revid, s[1]))
         return fp.getvalue()
 
-    def putcommit(self, files, copies, parents, commit, source, revmap):
-
+    def putcommit(self, files, copies, parents, commit, source, revmap, full):
         files = dict(files)
         def getfilectx(repo, memctx, f):
-            v = files[f]
+            try:
+                v = files[f]
+            except KeyError:
+                return None
             data, mode = source.getfile(f, v)
             if data is None:
                 return None
@@ -193,7 +195,10 @@
         while parents:
             p1 = p2
             p2 = parents.pop(0)
-            ctx = context.memctx(self.repo, (p1, p2), text, files.keys(),
+            fileset = set(files)
+            if full:
+                fileset.update(self.repo[p1], self.repo[p2])
+            ctx = context.memctx(self.repo, (p1, p2), text, fileset,
                                  getfilectx, commit.author, commit.date, extra)
             self.repo.commitctx(ctx)
             text = "(octopus merge fixup)\n"
@@ -356,17 +361,18 @@
         except error.LookupError:
             return None, None
 
-    def getchanges(self, rev):
+    def getchanges(self, rev, full):
         ctx = self.changectx(rev)
         parents = self.parents(ctx)
-        if not parents:
+        if full or not parents:
             files = copyfiles = ctx.manifest()
-        else:
+        if parents:
             if self._changescache[0] == rev:
                 m, a, r = self._changescache[1]
             else:
                 m, a, r = self.repo.status(parents[0].node(), ctx.node())[:3]
-            files = m + a + r
+            if not full:
+                files = m + a + r
             copyfiles = m + a
         # getcopies() is also run for roots and before filtering so missing
         # revlogs are detected early

--- a/hgext/convert/monotone.py	Tue Aug 26 22:03:32 2014 +0200
+++ b/hgext/convert/monotone.py	Tue Aug 26 22:03:32 2014 +0200
@@ -224,7 +224,9 @@
         else:
             return [self.rev]
 
-    def getchanges(self, rev):
+    def getchanges(self, rev, full):
+        if full:
+            raise util.Abort(_("convert from monotone do not support --full"))
         revision = self.mtnrun("get_revision", rev).split("\n\n")
         files = {}
         ignoremove = {}

--- a/hgext/convert/p4.py	Tue Aug 26 22:03:32 2014 +0200
+++ b/hgext/convert/p4.py	Tue Aug 26 22:03:32 2014 +0200
@@ -192,7 +192,9 @@
 
         return contents, mode
 
-    def getchanges(self, rev):
+    def getchanges(self, rev, full):
+        if full:
+            raise util.Abort(_("convert from p4 do not support --full"))
         return self.files[rev], {}
 
     def getcommit(self, rev):

--- a/hgext/convert/subversion.py	Tue Aug 26 22:03:32 2014 +0200
+++ b/hgext/convert/subversion.py	Tue Aug 26 22:03:32 2014 +0200
@@ -444,37 +444,37 @@
 
         return self.heads
 
-    def _getchanges(self, rev):
+    def _getchanges(self, rev, full):
         (paths, parents) = self.paths[rev]
+        copies = {}
         if parents:
             files, self.removed, copies = self.expandpaths(rev, paths, parents)
-        else:
+        if full or not parents:
             # Perform a full checkout on roots
             uuid, module, revnum = revsplit(rev)
             entries = svn.client.ls(self.baseurl + quote(module),
                                     optrev(revnum), True, self.ctx)
             files = [n for n, e in entries.iteritems()
                      if e.kind == svn.core.svn_node_file]
-            copies = {}
             self.removed = set()
 
         files.sort()
         files = zip(files, [rev] * len(files))
         return (files, copies)
 
-    def getchanges(self, rev):
+    def getchanges(self, rev, full):
         # reuse cache from getchangedfiles
-        if self._changescache[0] == rev:
+        if self._changescache[0] == rev and not full:
             (files, copies) = self._changescache[1]
         else:
-            (files, copies) = self._getchanges(rev)
+            (files, copies) = self._getchanges(rev, full)
             # caller caches the result, so free it here to release memory
             del self.paths[rev]
         return (files, copies)
 
     def getchangedfiles(self, rev, i):
         # called from filemap - cache computed values for reuse in getchanges
-        (files, copies) = self._getchanges(rev)
+        (files, copies) = self._getchanges(rev, False)
         self._changescache = (rev, (files, copies))
         return [f[0] for f in files]
 
@@ -1222,7 +1222,7 @@
     def revid(self, rev):
         return u"svn:%s@%s" % (self.uuid, rev)
 
-    def putcommit(self, files, copies, parents, commit, source, revmap):
+    def putcommit(self, files, copies, parents, commit, source, revmap, full):
         for parent in parents:
             try:
                 return self.revid(self.childmap[parent])
@@ -1238,6 +1238,8 @@
                 self.putfile(f, mode, data)
                 if f in copies:
                     self.copies.append([copies[f], f])
+        if full:
+            self.delete.extend(sorted(self.manifest.difference(files)))
         files = [f[0] for f in files]
 
         entries = set(self.delete)

--- a/tests/test-convert-hg-sink.t	Tue Aug 26 22:03:32 2014 +0200
+++ b/tests/test-convert-hg-sink.t	Tue Aug 26 22:03:32 2014 +0200
@@ -537,3 +537,16 @@
   |
   o  0 0 (a-only f)
   
+Convert with --full adds and removes files that didn't change
+
+  $ echo f >> 0/f
+  $ hg -R 0 ci -m "f"
+  $ hg convert --filemap filemap-b --full 0 a --config convert.hg.revs=1::
+  scanning source...
+  sorting...
+  converting...
+  0 f
+  $ hg -R a status --change tip
+  M f
+  A b-only
+  R a-only

--- a/tests/test-convert-svn-sink.t	Tue Aug 26 22:03:32 2014 +0200
+++ b/tests/test-convert-svn-sink.t	Tue Aug 26 22:03:32 2014 +0200
@@ -247,6 +247,31 @@
 
 #endif
 
+Convert with --full adds and removes files that didn't change
+
+  $ touch a/f
+  $ hg -R a ci -Aqmf
+  $ echo "rename c d" > filemap
+  $ hg convert -d svn a --filemap filemap --full
+  assuming destination a-hg
+  initializing svn working copy 'a-hg-wc'
+  scanning source...
+  sorting...
+  converting...
+  0 f
+  $ svnupanddisplay a-hg-wc 1
+   9 9 test .
+   9 9 test d
+   9 9 test f
+  revision: 9
+  author: test
+  msg: f
+   D /c
+   A /d
+   D /d1
+   A /f
+   D /newlink
+
   $ rm -rf a a-hg a-hg-wc
 
 

--- a/tests/test-convert-svn-source.t	Tue Aug 26 22:03:32 2014 +0200
+++ b/tests/test-convert-svn-source.t	Tue Aug 26 22:03:32 2014 +0200
@@ -168,6 +168,27 @@
   |
   o  0 second letter files: letter2.txt
   
+Convert with --full adds and removes files that didn't change
+
+  $ cd B
+  $ echo >> "letter .txt"
+  $ svn ci -m 'nothing'
+  Sending        letter .txt
+  Transmitting file data .
+  Committed revision 9.
+  $ cd ..
+
+  $ echo 'rename letter2.txt letter3.txt' > filemap
+  $ hg convert --filemap filemap --full "$SVNREPOURL/proj%20B/mytrunk" fmap
+  scanning source...
+  sorting...
+  converting...
+  0 nothing
+  $ hg -R fmap st --change tip
+  A letter .txt
+  A letter3.txt
+  R letter2.txt
+
 test invalid splicemap1
 
   $ cat > splicemap <<EOF

--- a/tests/test-convert.t	Tue Aug 26 22:03:32 2014 +0200
+++ b/tests/test-convert.t	Tue Aug 26 22:03:32 2014 +0200
@@ -91,6 +91,13 @@
       directory if it is converted. To rename from a subdirectory into the root
       of the repository, use "." as the path to rename to.
   
+      "--full" will make sure the converted changesets contain exactly the right
+      files with the right content. It will make a full conversion of all files,
+      not just the ones that have changed. Files that already are correct will
+      not be changed. This can be used to apply filemap changes when converting
+      incrementally. This is currently only supported for Mercurial and
+      Subversion.
+  
       The splicemap is a file that allows insertion of synthetic history,
       letting you specify the parents of a revision. This is useful if you want
       to e.g. give a Subversion merge two parents, or graft two disconnected
@@ -265,6 +272,7 @@
    -r --rev REV          import up to source revision REV
    -A --authormap FILE   remap usernames using this file
       --filemap FILE     remap file names using contents of file
+      --full             apply filemap changes by converting all files again
       --splicemap FILE   splice synthesized history into place
       --branchmap FILE   change branch names while converting
       --branchsort       try to sort changesets by branches