Rev 5639: It turns out that _observed_sha1 was not setting the size field. in http://bazaar.launchpad.net/~jameinel/bzr/2.3-build-cache-sha-740932

[John Arbash Meinel]

At http://bazaar.launchpad.net/~jameinel/bzr/2.3-build-cache-sha-740932

------------------------------------------------------------
revno: 5639
revision-id: john at arbash-meinel.com-20110404123413-vmd0xo9yrx6f3uza
parent: john at arbash-meinel.com-20110404115739-w4v1i0t9n2us52f1
committer: John Arbash Meinel <john at arbash-meinel.com>
branch nick: 2.3-build-cache-sha-740932
timestamp: Mon 2011-04-04 14:34:13 +0200
message:
  It turns out that _observed_sha1 was not setting the size field.
  
  I don't know why this didn't matter for commit, but maybe the size was getting
  set somewhere else. apply_inventory_delta from TreeTransform wasn't setting it.
  Maybe there is a different bug there. Regardless, we now set the size field
  so I can be sure that we aren't re-computing the sha values for all the
  files which are old enough.
  Now to test on Linux, because the rename is probably going to change the
  ctime there.
-------------- next part --------------
=== modified file 'bzrlib/dirstate.py'
--- a/bzrlib/dirstate.py	2011-04-04 11:24:50 +0000
+++ b/bzrlib/dirstate.py	2011-04-04 12:34:13 +0000
@@ -1745,8 +1745,8 @@
                 self._sha_cutoff_time()
             if (stat_value.st_mtime < self._cutoff_time
                 and stat_value.st_ctime < self._cutoff_time):
-                entry[1][0] = ('f', sha1, entry[1][0][2], entry[1][0][3],
-                    packed_stat)
+                entry[1][0] = ('f', sha1, stat_value.st_size, entry[1][0][3],
+                               packed_stat)
                 self._dirblock_state = DirState.IN_MEMORY_MODIFIED
 
     def _sha_cutoff_time(self):

=== modified file 'bzrlib/tests/test_transform.py'
--- a/bzrlib/tests/test_transform.py	2011-04-04 11:24:50 +0000
+++ b/bzrlib/tests/test_transform.py	2011-04-04 12:34:13 +0000
@@ -2083,17 +2083,20 @@
         # tree
         entry1 = state._get_entry(0, path_utf8='file1')
         self.assertEqual(entry1_sha, entry1[1][0][1])
-        entry1_packed_stat = entry1[1][0][-1]
+        # The 'size' field must also be set.
+        self.assertEqual(25, entry1[1][0][2])
+        entry1_state = entry1[1][0]
         entry2 = state._get_entry(0, path_utf8='dir/file2')
         self.assertEqual(entry2_sha, entry2[1][0][1])
-        entry2_packed_stat = entry2[1][0][-1]
+        self.assertEqual(29, entry2[1][0][2])
+        entry2_state = entry2[1][0]
         # Now, make sure that we don't have to re-read the content. The
         # packed_stat should match exactly.
         self.assertEqual(entry1_sha, target.get_file_sha1('file1-id', 'file1'))
         self.assertEqual(entry2_sha,
                          target.get_file_sha1('file2-id', 'dir/file2'))
-        self.assertEqual(entry1_packed_stat, entry1[1][0][-1])
-        self.assertEqual(entry2_packed_stat, entry2[1][0][-1])
+        self.assertEqual(entry1_state, entry1[1][0])
+        self.assertEqual(entry2_state, entry2[1][0])
 
 
 class TestCommitTransform(tests.TestCaseWithTransport):

=== modified file 'bzrlib/transform.py'
--- a/bzrlib/transform.py	2011-04-04 11:24:50 +0000
+++ b/bzrlib/transform.py	2011-04-04 12:34:13 +0000
@@ -1867,6 +1867,14 @@
         it doesn't know anything about the files we are updating. Also, we want
         to do this as late as possible, so that most entries end up cached.
         """
+        # TODO: this doesn't update the stat information for directories. So
+        #       the first 'bzr status' will still need to rewrite
+        #       .bzr/checkout/dirstate. However, we at least don't need to
+        #       re-read all of the files.
+        # TODO: If the operation took a while, we could do a time.sleep(3) here
+        #       to allow the clock to tick over and ensure we won't have any
+        #       problems. (we could observe start time, and finish time, and if
+        #       it is less than eg 10% overhead, add a sleep call.)
         paths = FinalPaths(self)
         for trans_id, observed in self._observed_sha1s.iteritems():
             path = paths.get_path(trans_id)