convert: abstract map files into a class

hgext/convert/__init__.py

@@ -5,7 +5,7 @@
 # This software may be used and distributed according to the terms
 # of the GNU General Public License, incorporated herein by reference.
 
-from common import NoRepo, SKIPREV, converter_source, converter_sink
+from common import NoRepo, SKIPREV, converter_source, converter_sink, mapfile
 from cvs import convert_cvs
 from darcs import darcs_source
 from git import convert_git
@@ -57,23 +57,10 @@ class converter(object):
         self.ui = ui
         self.opts = opts
         self.commitcache = {}
-        self.revmapfile = revmapfile
-        self.revmapfilefd = None
         self.authors = {}
         self.authorfile = None
 
-        self.maporder = []
-        self.map = {}
-        try:
-            origrevmapfile = open(self.revmapfile, 'r')
-            for l in origrevmapfile:
-                sv, dv = l[:-1].split()
-                if sv not in self.map:
-                    self.maporder.append(sv)
-                self.map[sv] = dv
-            origrevmapfile.close()
-        except IOError:
-            pass
+        self.map = mapfile(ui, revmapfile)
 
         # Read first the dst author map if any
         authorfile = self.dest.authorfile()
@@ -161,16 +148,6 @@ class converter(object):
 
         return s
 
-    def mapentry(self, src, dst):
-        if self.revmapfilefd is None:
-            try:
-                self.revmapfilefd = open(self.revmapfile, "a")
-            except IOError, (errno, strerror):
-                raise util.Abort("Could not open map file %s: %s, %s\n" % (self.revmapfile, errno, strerror))
-        self.map[src] = dst
-        self.revmapfilefd.write("%s %s\n" % (src, dst))
-        self.revmapfilefd.flush()
-
     def writeauthormap(self):
         authorfile = self.authorfile
         if authorfile:
@@ -217,7 +194,7 @@ class converter(object):
                 dest = SKIPREV
             else:
                 dest = self.map[changes]
-            self.mapentry(rev, dest)
+            self.map[rev] = dest
             return
         files, copies = changes
         parents = [self.map[r] for r in commit.parents]
@@ -245,13 +222,13 @@ class converter(object):
                         self.dest.copyfile(copyf, f)
 
         newnode = self.dest.putcommit(filenames, parents, commit)
-        self.mapentry(rev, newnode)
+        self.map[rev] = newnode
 
     def convert(self):
         try:
             self.source.before()
             self.dest.before()
-            self.source.setrevmap(self.map, self.maporder)
+            self.source.setrevmap(self.map)
             self.ui.status("scanning source...\n")
             heads = self.source.getheads()
             parents = self.walktree(heads)
@@ -281,7 +258,7 @@ class converter(object):
                 # write another hash correspondence to override the previous
                 # one so we don't end up with extra tag heads
                 if nrev:
-                    self.mapentry(c, nrev)
+                    self.map[c] = nrev
 
             self.writeauthormap()
         finally:
@@ -292,8 +269,7 @@ class converter(object):
             self.dest.after()
         finally:
             self.source.after()
-        if self.revmapfilefd:
-            self.revmapfilefd.close()
+        self.map.close()
 
 def convert(ui, src, dest=None, revmapfile=None, **opts):
     """Convert a foreign SCM repository to a Mercurial one.

hgext/convert/common.py

@@ -1,5 +1,5 @@
 # common code for the convert extension
-import base64
+import base64, errno
 import cPickle as pickle
 from mercurial import util
 
@@ -54,11 +54,8 @@ class converter_source(object):
     def after(self):
         pass
 
-    def setrevmap(self, revmap, order):
-        """set the map of already-converted revisions
-        
-        order is a list with the keys from revmap in the order they
-        appear in the revision map file."""
+    def setrevmap(self, revmap):
+        """set the map of already-converted revisions"""
         pass
 
     def getheads(self):
@@ -190,3 +187,41 @@ class converter_sink(object):
         filter empty revisions.
         """
         pass
+
+
+class mapfile(dict):
+    def __init__(self, ui, path):
+        super(mapfile, self).__init__()
+        self.ui = ui
+        self.path = path
+        self.fp = None
+        self.order = []
+        self._read()
+
+    def _read(self):
+        try:
+            fp = open(self.path, 'r')
+        except IOError, err:
+            if err.errno != errno.ENOENT:
+                raise
+            return
+        for line in fp:
+            key, value = line[:-1].split(' ', 1)
+            if key not in self:
+                self.order.append(key)
+            super(mapfile, self).__setitem__(key, value)
+        fp.close()
+            
+    def __setitem__(self, key, value):
+        if self.fp is None:
+            try:
+                self.fp = open(self.path, 'a')
+            except IOError, err:
+                raise util.Abort(_('could not open map file %r: %s') %
+                                 (self.path, err.strerror))
+        self.fp.write('%s %s\n' % (key, value))
+        self.fp.flush()
+        super(mapfile, self).__setitem__(key, value)
+
+    def close(self):
+        self.fp.close()

hgext/convert/filemap.py

@@ -128,7 +128,7 @@ class filemap_source(object):
         self.children = {}
         self.seenchildren = {}
 
-    def setrevmap(self, revmap, order):
+    def setrevmap(self, revmap):
         # rebuild our state to make things restartable
         #
         # To avoid calling getcommit for every revision that has already
@@ -143,7 +143,7 @@ class filemap_source(object):
         seen = {SKIPREV: SKIPREV}
         dummyset = util.set()
         converted = []
-        for rev in order:
+        for rev in revmap.order:
             mapped = revmap[rev]
             wanted = mapped not in seen
             if wanted:
@@ -157,7 +157,7 @@ class filemap_source(object):
                 arg = None
             converted.append((rev, wanted, arg))
         self.convertedorder = converted
-        return self.base.setrevmap(revmap, order)
+        return self.base.setrevmap(revmap)
 
     def rebuild(self):
         if self._rebuilt:

hgext/convert/subversion.py

@@ -149,7 +149,7 @@ class svn_source(converter_source):
         self.head = self.revid(self.last_changed)
         self._changescache = None
 
-    def setrevmap(self, revmap, order):
+    def setrevmap(self, revmap):
         lastrevs = {}
         for revid in revmap.keys():
             uuid, module, revnum = self.revsplit(revid)