convert: reintegrate file retrieval code in sinks

It simplifies the sink interface and all the sinks to handle files data as they
want.

hgext/convert/common.py

@@ -153,26 +153,18 b' class converter_sink(object):'
         mapping equivalent authors identifiers for each system."""
         return None
 
-    def putfile(self, f, e, data):
-        """Put file for next putcommit().
-        f: path to file
-        e: '', 'x', or 'l' (regular file, executable, or symlink)
-        data: file contents"""
-        raise NotImplementedError()
-
-    def delfile(self, f):
-        """Delete file for next putcommit().
-        f: path to file"""
-        raise NotImplementedError()
-
-    def putcommit(self, files, parents, commit):
+    def putcommit(self, files, copies, parents, commit, source):
         """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 changeset.
-        Called after putfile() and delfile() calls. Note that the sink
-        repository is not told to update itself to a particular revision
-        (or even what that revision would be) before it receives the
-        file data."""
+        'files' is a list of (path, version) tuples, 'copies'is a dictionary
+        mapping destinations to sources, and 'source' is the source repository.
+        Only getfile() and getmode() should be called on 'source'.
+
+        Note that the sink repository is not told to update itself to
+        a particular revision (or even what that revision would be)
+        before it receives the file data.
+        """
         raise NotImplementedError()
 
     def puttags(self, tags):
@@ -181,7 +173,7 b' class converter_sink(object):'
         raise NotImplementedError()
 
     def setbranch(self, branch, pbranches):
-        """Set the current branch name. Called before the first putfile
+        """Set the current branch name. Called before the first putcommit
         on the branch.
         branch: branch name for subsequent commits
         pbranches: (converted parent revision, parent branch) tuples"""

hgext/convert/convcmd.py

@@ -221,8 +221,6 b' class converter(object):'
 
     def copy(self, rev):
         commit = self.commitcache[rev]
-        do_copies = hasattr(self.dest, 'copyfile')
-        filenames = []
 
         changes = self.source.getchanges(rev)
         if isinstance(changes, basestring):
@@ -241,21 +239,6 b' class converter(object):'
                 pbranches.append((self.map[prev],
                                   self.commitcache[prev].branch))
         self.dest.setbranch(commit.branch, pbranches)
-        for f, v in files:
-            filenames.append(f)
-            try:
-                data = self.source.getfile(f, v)
-            except IOError, inst:
-                self.dest.delfile(f)
-            else:
-                e = self.source.getmode(f, v)
-                self.dest.putfile(f, e, data)
-                if do_copies:
-                    if f in copies:
-                        copyf = copies[f]
-                        # Merely marks that a copy happened.
-                        self.dest.copyfile(copyf, f)
-
         try:
             parents = self.splicemap[rev].replace(',', ' ').split()
             self.ui.status('spliced in %s as parents of %s\n' %
@@ -263,7 +246,7 b' class converter(object):'
             parents = [self.map.get(p, p) for p in parents]
         except KeyError:
             parents = [b[0] for b in pbranches]
-        newnode = self.dest.putcommit(filenames, parents, commit)
+        newnode = self.dest.putcommit(files, copies, parents, commit, self.source)
         self.source.converted(rev, newnode)
         self.map[rev] = newnode
 

hgext/convert/hg.py

@@ -72,21 +72,6 b' class mercurial_sink(converter_sink):'
         h = self.repo.changelog.heads()
         return [ hex(x) for x in h ]
 
-    def putfile(self, f, e, data):
-        self.repo.wwrite(f, data, e)
-        if f not in self.repo.dirstate:
-            self.repo.dirstate.normallookup(f)
-
-    def copyfile(self, source, dest):
-        self.repo.copy(source, dest)
-
-    def delfile(self, f):
-        try:
-            util.unlink(self.repo.wjoin(f))
-            #self.repo.remove([f])
-        except OSError:
-            pass
-
     def setbranch(self, branch, pbranches):
         if not self.clonebranches:
             return
@@ -125,7 +110,25 b' class mercurial_sink(converter_sink):'
                 self.repo.pull(prepo, [prepo.lookup(h) for h in heads])
             self.before()
 
-    def putcommit(self, files, parents, commit):
+    def putcommit(self, files, copies, parents, commit, source):
+        # Apply changes to working copy
+        for f, v in files:
+            try:
+                data = source.getfile(f, v)
+            except IOError, inst:
+                try:
+                    util.unlink(self.repo.wjoin(f))
+                except OSError:
+                    pass
+            else:
+                e = source.getmode(f, v)
+                self.repo.wwrite(f, data, e)
+                if f not in self.repo.dirstate:
+                    self.repo.dirstate.normallookup(f)
+                if f in copies:
+                    self.repo.copy(copies[f], f)
+        files = [f[0] for f in files]
+
         seen = {}
         pl = []
         for p in parents:

hgext/convert/subversion.py

@@ -1013,12 +1013,6 b' class svn_sink(converter_sink, commandli'
                 if 'x' in flags:
                     self.setexec.append(filename)
 
-    def delfile(self, name):
-        self.delete.append(name)
-
-    def copyfile(self, source, dest):
-        self.copies.append([source, dest])
-
     def _copyfile(self, source, dest):
         # SVN's copy command pukes if the destination file exists, but
         # our copyfile method expects to record a copy that has
@@ -1081,7 +1075,20 b' class svn_sink(converter_sink, commandli'
     def revid(self, rev):
         return u"svn:%s@%s" % (self.uuid, rev)
 
-    def putcommit(self, files, parents, commit):
+    def putcommit(self, files, copies, parents, commit, source):
+        # Apply changes to working copy
+        for f, v in files:
+            try:
+                data = source.getfile(f, v)
+            except IOError, inst:
+                self.delete.append(f)
+            else:
+                e = source.getmode(f, v)
+                self.putfile(f, e, data)
+                if f in copies:
+                    self.copies.append([copies[f], f])
+        files = [f[0] for f in files]
+
         for parent in parents:
             try:
                 return self.revid(self.childmap[parent])