Rev 2215: Repository.tarball fixes for python2.4 in http://sourcefrog.net/bzr/hpss-faster-copy

[Martin Pool]

At http://sourcefrog.net/bzr/hpss-faster-copy

------------------------------------------------------------
revno: 2215
revision-id: mbp at sourcefrog.net-20070426074805-va53nylsxqt7ur7u
parent: mbp at sourcefrog.net-20070423120654-7k0q70jyjrvb5g38
committer: Martin Pool <mbp at sourcefrog.net>
branch nick: hpss-faster-copy
timestamp: Thu 2007-04-26 17:48:05 +1000
message:
  Repository.tarball fixes for python2.4
  
  Use 'r|bz2' to extract since r:bz2 is not supported
  Replace extractall, which is not in python2.4
  RemoteRepository._get_tarball returns a TemporaryFile
  -------------- This line and the following will be ignored --------------
  
  modified:
    bzrlib/remote.py
    bzrlib/tests/test_remote.py
    bzrlib/tests/test_smart.py
modified:
  bzrlib/remote.py               remote.py-20060720103555-yeeg2x51vn0rbtdp-1
  bzrlib/tests/test_remote.py    test_remote.py-20060720103555-yeeg2x51vn0rbtdp-2
  bzrlib/tests/test_smart.py     test_smart.py-20061122024551-ol0l0o0oofsu9b3t-2
=== modified file 'bzrlib/remote.py'
--- a/bzrlib/remote.py	2007-04-23 12:06:54 +0000
+++ b/bzrlib/remote.py	2007-04-26 07:48:05 +0000
@@ -429,7 +429,8 @@
         return self._real_repository.break_lock()
 
     def _get_tarball(self, compression):
-        """See Repository.tarball()."""
+        """Return a TemporaryFile containing a repository tarball"""
+        import tempfile
         path = self.bzrdir._path_for_remote_call(self._client)
         response, protocol = self._client.call_expecting_body(
             'Repository.tarball', path, compression)
@@ -437,8 +438,11 @@
             'unexpected response code %s' % (response,)
         if response[0] == 'ok':
             # Extract the tarball and return it
-            body = protocol.read_body_bytes()
-            return body
+            t = tempfile.NamedTemporaryFile()
+            # TODO: rpc layer should read directly into it...
+            t.write(protocol.read_body_bytes())
+            t.seek(0)
+            return t
         else:
             raise errors.SmartServerError(error_code=response)
 
@@ -597,17 +601,20 @@
         from StringIO import StringIO
         # TODO: Maybe a progress bar while streaming the tarball?
         note("Copying repository content as tarball...")
-        tar_file = StringIO(self._get_tarball('bz2'))
-        tar = tarfile.open('repository', fileobj=tar_file,
-            mode='r:bz2')
-        tmpdir = tempfile.mkdtemp()
+        tar_file = self._get_tarball('bz2')
         try:
-            tar.extractall(tmpdir)
-            tmp_bzrdir = BzrDir.open(tmpdir)
-            tmp_repo = tmp_bzrdir.open_repository()
-            tmp_repo.copy_content_into(destination, revision_id)
+            tar = tarfile.open('repository', fileobj=tar_file,
+                mode='r|bz2')
+            tmpdir = tempfile.mkdtemp()
+            try:
+                _extract_tar(tar, tmpdir)
+                tmp_bzrdir = BzrDir.open(tmpdir)
+                tmp_repo = tmp_bzrdir.open_repository()
+                tmp_repo.copy_content_into(destination, revision_id)
+            finally:
+                osutils.rmtree(tmpdir)
         finally:
-            osutils.rmtree(tmpdir)
+            tar_file.close()
         # TODO: if the server doesn't support this operation, maybe do it the
         # slow way using the _real_repository?
         #
@@ -1032,3 +1039,11 @@
             self._branch_data_config = TreeConfig(self.branch._real_branch)
         return self._branch_data_config
 
+
+def _extract_tar(tar, to_dir):
+    """Extract all the contents of a tarfile object.
+
+    A replacement for extractall, which is not present in python2.4
+    """
+    for tarinfo in tar:
+        tar.extract(tarinfo, to_dir)

=== modified file 'bzrlib/tests/test_remote.py'
--- a/bzrlib/tests/test_remote.py	2007-04-23 12:06:54 +0000
+++ b/bzrlib/tests/test_remote.py	2007-04-26 07:48:05 +0000
@@ -657,9 +657,12 @@
         remote_repo, client = self.setup_fake_client_and_repository(
             expected_responses, transport_path)
         # Now actually ask for the tarball
-        tarball_data = remote_repo._get_tarball('bz2')
-        self.assertEqual(expected_calls, client._calls)
-        self.assertEqual(self.tarball_content, tarball_data)
+        tarball_file = remote_repo._get_tarball('bz2')
+        try:
+            self.assertEqual(expected_calls, client._calls)
+            self.assertEqual(self.tarball_content, tarball_file.read())
+        finally:
+            tarball_file.close()
 
     def test_sprout_uses_tarball(self):
         # RemoteRepository.sprout should try to use the

=== modified file 'bzrlib/tests/test_smart.py'
--- a/bzrlib/tests/test_smart.py	2007-04-23 05:03:44 +0000
+++ b/bzrlib/tests/test_smart.py	2007-04-26 07:48:05 +0000
@@ -756,7 +756,7 @@
         # body should be a tbz2
         body_file = StringIO(response.body)
         body_tar = tarfile.open('body_tar.tbz2', fileobj=body_file,
-            mode='r:bz2')
+            mode='r|bz2')
         # let's make sure there are some key repository components inside it.
         # the tarfile returns directories with trailing slashes...
         names = set([n.rstrip('/') for n in body_tar.getnames()])