Merge support for --baseline option to 'bzr export'.

4 files changed, 111 insertions, 3 deletions

diff --git a/NEWS b/NEWS
index 32c469a..2e703a9 100644
--- a/NEWS
+++ b/NEWS
@@ -20,6 +20,8 @@ Features
 * New option --dont-squash-empty-commits for 'bzr fast-import-filter'.
   (Alex Usov, #877303)
 
+* Add --baseline option to ``bzr export``. (Andy Grimm, #893382)
+
 0.11 2011-08-22
 
 Bug fixes
diff --git a/cmds.py b/cmds.py
index 7e20a1d..157c9b2 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 at 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 'absolute' 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..2094ff5 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']
@@ -213,6 +215,10 @@ class BzrFastExporter(object):
             self.note("Calculating the revisions to exclude ...")
             self.excluded_revisions = set([rev_id for rev_id, _, _, _ in
                 self.branch.iter_merge_sorted_revisions(start_rev_id)])
+            if self.baseline:
+                # needed so the first relative commit knows its parent
+                self.excluded_revisions.remove(start_rev_id)
+                view_revisions.insert(0, start_rev_id)
         return list(view_revisions)
 
     def run(self):
@@ -225,6 +231,8 @@ class BzrFastExporter(object):
                 self._commit_total)
             if not self.plain_format:
                 self.emit_features()
+            if self.baseline:
+                self.emit_baseline(interesting.pop(0), self.git_branch)
             for revid in interesting:
                 self.emit_commit(revid, self.git_branch)
             if self.branch.supports_tags():
@@ -302,6 +310,16 @@ 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)
+        mark = 1
+        self.revid_to_mark[revid] = mark
+        file_cmds = self._get_filecommands(bzrlib.revision.NULL_REVISION, revid)
+        self.print_cmd(self._get_commit_command(git_ref, mark, revobj,
+            file_cmds))
+
     def emit_commit(self, revid, git_branch):
         if revid in self.revid_to_mark or revid in self.excluded_revisions:
             return
diff --git a/tests/test_commands.py b/tests/test_commands.py
index 5729660..5053416 100644
--- a/tests/test_commands.py
+++ b/tests/test_commands.py
@@ -16,6 +16,7 @@
 """Test the command implementations."""
 
 import os
+import re
 import tempfile
 import gzip
 
@@ -58,6 +59,40 @@ class TestSourceStream(tests.TestCase):
         self.assertIsNot("bla", stream.read())
 
 
+fast_export_baseline_data = """commit refs/heads/master
+mark :1
+committer
+data 15
+add c, remove b
+M 644 inline a
+data 13
+test 1
+test 3
+M 644 inline c
+data 6
+test 4
+commit refs/heads/master
+mark :2
+committer
+data 14
+modify a again
+from :1
+M 644 inline a
+data 20
+test 1
+test 3
+test 5
+commit refs/heads/master
+mark :3
+committer
+data 5
+add d
+from :2
+M 644 inline d
+data 6
+test 6
+"""
+
 class TestFastExport(ExternalBase):
 
     def test_empty(self):
@@ -99,6 +134,45 @@ class TestFastExport(ExternalBase):
         # "bad Tag" should be exported as bad_Tag
         self.assertNotEqual(-1, data.find("reset refs/tags/bad_Tag"))
 
+    def test_baseline_option(self):
+        tree = self.make_branch_and_tree("bl")
+
+        # Revision 1
+        file('bl/a', 'w').write('test 1')
+        tree.add('a')
+        tree.commit(message='add a')
+
+        # Revision 2
+        file('bl/b', 'w').write('test 2')
+        file('bl/a', 'a').write('\ntest 3')
+        tree.add('b')
+        tree.commit(message='add b, modify a')
+
+        # Revision 3
+        file('bl/c', 'w').write('test 4')
+        tree.add('c')
+        tree.remove('b')
+        tree.commit(message='add c, remove b')
+
+        # Revision 4
+        file('bl/a', 'a').write('\ntest 5')
+        tree.commit(message='modify a again')
+
+        # Revision 5
+        file('bl/d', 'w').write('test 6')
+        tree.add('d')
+        tree.commit(message='add d')
+
+        # This exports the baseline state at Revision 3,
+        # followed by the deltas for 4 and 5
+        data = self.run_bzr("fast-export --baseline -r 3.. bl")[0]
+        data = re.sub('committer.*', 'committer', data)
+        self.assertEquals(fast_export_baseline_data, data)
+
+        # Also confirm that --baseline with no args is identical to full export
+        data1 = self.run_bzr("fast-export --baseline bl")[0]
+        data2 = self.run_bzr("fast-export bl")[0]
+        self.assertEquals(data1, data2)
 
 simple_fast_import_stream = """commit refs/heads/master
 mark :1