Rev 5374: (jameinel) Use a custom object for build details to save a decent amount of in file:///home/pqm/archives/thelove/bzr/%2Btrunk/

[Canonical.com Patch Queue Manager]

At file:///home/pqm/archives/thelove/bzr/%2Btrunk/

------------------------------------------------------------
revno: 5374 [merge]
revision-id: pqm at pqm.ubuntu.com-20100807214836-umokeeg6d1dytzvm
parent: pqm at pqm.ubuntu.com-20100807203122-emne66ssgwyu26o6
parent: john at arbash-meinel.com-20100806181422-puv63wplscz2mc0w
committer: Canonical.com Patch Queue Manager <pqm at pqm.ubuntu.com>
branch nick: +trunk
timestamp: Sat 2010-08-07 22:48:36 +0100
message:
  (jameinel) Use a custom object for build details to save a decent amount of
   memory (John A Meinel)
modified:
  bzrlib/groupcompress.py        groupcompress.py-20080705181503-ccbxd6xuy1bdnrpu-8
  bzrlib/tests/test_groupcompress.py test_groupcompress.p-20080705181503-ccbxd6xuy1bdnrpu-13
=== modified file 'bzrlib/groupcompress.py'
--- a/bzrlib/groupcompress.py	2010-05-20 02:57:52 +0000
+++ b/bzrlib/groupcompress.py	2010-08-06 18:14:22 +0000
@@ -1809,6 +1809,54 @@
         return result
 
 
+class _GCBuildDetails(object):
+    """A blob of data about the build details.
+
+    This stores the minimal data, which then allows compatibility with the old
+    api, without taking as much memory.
+    """
+
+    __slots__ = ('_index', '_group_start', '_group_end', '_basis_end',
+                 '_delta_end', '_parents')
+
+    method = 'group'
+    compression_parent = None
+
+    def __init__(self, parents, position_info):
+        self._parents = parents
+        (self._index, self._group_start, self._group_end, self._basis_end,
+         self._delta_end) = position_info
+
+    def __repr__(self):
+        return '%s(%s, %s)' % (self.__class__.__name__,
+            self.index_memo, self._parents)
+
+    @property
+    def index_memo(self):
+        return (self._index, self._group_start, self._group_end,
+                self._basis_end, self._delta_end)
+
+    @property
+    def record_details(self):
+        return static_tuple.StaticTuple(self.method, None)
+
+    def __getitem__(self, offset):
+        """Compatibility thunk to act like a tuple."""
+        if offset == 0:
+            return self.index_memo
+        elif offset == 1:
+            return self.compression_parent # Always None
+        elif offset == 2:
+            return self._parents
+        elif offset == 3:
+            return self.record_details
+        else:
+            raise IndexError('offset out of range')
+            
+    def __len__(self):
+        return 4
+
+
 class _GCGraphIndex(object):
     """Mapper from GroupCompressVersionedFiles needs into GraphIndex storage."""
 
@@ -2009,9 +2057,8 @@
                 parents = None
             else:
                 parents = entry[3][0]
-            method = 'group'
-            result[key] = (self._node_to_position(entry),
-                                  None, parents, (method, None))
+            details = _GCBuildDetails(parents, self._node_to_position(entry))
+            result[key] = details
         return result
 
     def keys(self):
@@ -2033,7 +2080,7 @@
         # each, or about 7MB. Note that it might be even more when you consider
         # how PyInt is allocated in separate slabs. And you can't return a slab
         # to the OS if even 1 int on it is in use. Note though that Python uses
-        # a LIFO when re-using PyInt slots, which probably causes more
+        # a LIFO when re-using PyInt slots, which might cause more
         # fragmentation.
         start = int(bits[0])
         start = self._int_cache.setdefault(start, start)

=== modified file 'bzrlib/tests/test_groupcompress.py'
--- a/bzrlib/tests/test_groupcompress.py	2010-02-17 17:11:16 +0000
+++ b/bzrlib/tests/test_groupcompress.py	2010-08-05 16:27:35 +0000
@@ -1066,3 +1066,25 @@
         # consumption
         self.add_key_to_manager(('key4',), locations, block, manager)
         self.assertTrue(manager.check_is_well_utilized())
+
+
+class Test_GCBuildDetails(tests.TestCase):
+
+    def test_acts_like_tuple(self):
+        # _GCBuildDetails inlines some of the data that used to be spread out
+        # across a bunch of tuples
+        bd = groupcompress._GCBuildDetails((('parent1',), ('parent2',)),
+            ('INDEX', 10, 20, 0, 5))
+        self.assertEqual(4, len(bd))
+        self.assertEqual(('INDEX', 10, 20, 0, 5), bd[0])
+        self.assertEqual(None, bd[1]) # Compression Parent is always None
+        self.assertEqual((('parent1',), ('parent2',)), bd[2])
+        self.assertEqual(('group', None), bd[3]) # Record details
+
+    def test__repr__(self):
+        bd = groupcompress._GCBuildDetails((('parent1',), ('parent2',)),
+            ('INDEX', 10, 20, 0, 5))
+        self.assertEqual("_GCBuildDetails(('INDEX', 10, 20, 0, 5),"
+                         " (('parent1',), ('parent2',)))",
+                         repr(bd))
+