Add --baseline option

2 files changed, 35 insertions, 3 deletions

diff --git a/cmds.py b/cmds.py
index 7e20a1d..a92e326 100644
--- a/cmds.py
+++ b/cmds.py
@@ -606,6 +606,16 @@ class cmd_fast_export(Command):
      unsupported in git with an underscore instead, specify
      --rewrite-tag-names.
 
+    :History truncation:
+
+    When code has been significantly refactored over time (e.g., to separate 
+    proprietary code from open source code), it is sometimes convenient to
+    simply truncate the revision history at a certain point.  The --baseline 
+    option, to be used in conjunction with -r, emits a baseline commit
+    containing the state of the entire source tree immediately prior to the
+    first requested revision.  This allows a user to produce a tree identical
+    to the original without munging multiple exports.
+
     :Examples:
 
      To produce data destined for import into Bazaar::
@@ -656,12 +666,16 @@ class cmd_fast_export(Command):
                         help="Replace characters invalid in git with '_'"
                              " (plain mode only).",
                         ),
+                    Option('baseline',
+                        help="Export an 'abolute' baseline commit prior to"
+                             "the first relative commit",
+                        ),
                      ]
     encoding_type = 'exact'
     def run(self, source, destination=None, verbose=False,
         git_branch="master", checkpoint=10000, marks=None,
         import_marks=None, export_marks=None, revision=None,
-        plain=True, rewrite_tag_names=False):
+        plain=True, rewrite_tag_names=False, baseline=False):
         load_fastimport()
         from bzrlib.branch import Branch
         from bzrlib.plugins.fastimport import exporter
@@ -676,7 +690,7 @@ class cmd_fast_export(Command):
             outf=outf, git_branch=git_branch, checkpoint=checkpoint,
             import_marks_file=import_marks, export_marks_file=export_marks,
             revision=revision, verbose=verbose, plain_format=plain,
-            rewrite_tags=rewrite_tag_names)
+            rewrite_tags=rewrite_tag_names, baseline=baseline)
         return exporter.run()
 
 
diff --git a/exporter.py b/exporter.py
index e4b5132..b5c6651 100644
--- a/exporter.py
+++ b/exporter.py
@@ -148,7 +148,8 @@ class BzrFastExporter(object):
 
     def __init__(self, source, outf, git_branch=None, checkpoint=-1,
         import_marks_file=None, export_marks_file=None, revision=None,
-        verbose=False, plain_format=False, rewrite_tags=False):
+        verbose=False, plain_format=False, rewrite_tags=False,
+        baseline=False):
         """Export branch data in fast import format.
 
         :param plain_format: if True, 'classic' fast-import format is
@@ -170,6 +171,7 @@ class BzrFastExporter(object):
         self.excluded_revisions = set()
         self.plain_format = plain_format
         self.rewrite_tags = rewrite_tags
+        self.baseline = baseline
         self._multi_author_api_available = hasattr(bzrlib.revision.Revision,
             'get_apparent_authors')
         self.properties_to_exclude = ['authors', 'author']
@@ -225,6 +227,9 @@ class BzrFastExporter(object):
                 self._commit_total)
             if not self.plain_format:
                 self.emit_features()
+            if self.baseline:
+                self._commit_total += 1
+                self.emit_baseline(interesting[0], self.git_branch)
             for revid in interesting:
                 self.emit_commit(revid, self.git_branch)
             if self.branch.supports_tags():
@@ -302,6 +307,19 @@ class BzrFastExporter(object):
         for feature in sorted(commands.FEATURE_NAMES):
             self.print_cmd(commands.FeatureCommand(feature))
 
+    def emit_baseline(self, revid, git_branch):
+        # Emit a full source tree of the first commit's parent
+        git_ref = 'refs/heads/%s' % (git_branch,)
+        revobj = self.branch.repository.get_revision(revid)
+        assert(len(revobj.parent_ids))
+        previd = revobj.parent_ids[0]
+        prevobj = self.branch.repository.get_revision(previd)
+        mark = 1
+        self.revid_to_mark[previd] = mark
+        file_cmds = self._get_filecommands(bzrlib.revision.NULL_REVISION, previd)
+        self.print_cmd(self._get_commit_command(git_ref, mark, prevobj,
+            file_cmds))
+
     def emit_commit(self, revid, git_branch):
         if revid in self.revid_to_mark or revid in self.excluded_revisions:
             return