Rev 3486: (jam) Bug #135320, keep symlink lines in ascii, not Unicode in file:///home/pqm/archives/thelove/bzr/%2Btrunk/

[Canonical.com Patch Queue Manager]

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

------------------------------------------------------------
revno: 3486
revision-id:pqm at pqm.ubuntu.com-20080609160347-bbytjk1914u9qast
parent: pqm at pqm.ubuntu.com-20080609074519-afx3xh7bd8wqzjy0
parent: john at arbash-meinel.com-20080605214739-uf050pk6fdgm5xbp
committer: Canonical.com Patch Queue Manager <pqm at pqm.ubuntu.com>
branch nick: +trunk
timestamp: Mon 2008-06-09 17:03:47 +0100
message:
  (jam) Bug #135320, keep symlink lines in ascii, not Unicode
modified:
  NEWS                           NEWS-20050323055033-4e00b5db738777ff
  bzrlib/dirstate.py             dirstate.py-20060728012006-d6mvoihjb3je9peu-1
  bzrlib/tests/test_dirstate.py  test_dirstate.py-20060728012006-d6mvoihjb3je9peu-2
    ------------------------------------------------------------
    revno: 3477.1.1.1.2
    revision-id:john at arbash-meinel.com-20080605214739-uf050pk6fdgm5xbp
    parent: john at arbash-meinel.com-20080605211911-2xtal2ehwcqkcymy
    committer: John Arbash Meinel <john at arbash-meinel.com>
    branch nick: symlink_unicode_135320
    timestamp: Thu 2008-06-05 16:47:39 -0500
    message:
      Change how we handle unicode targets, and add a NEWS entry.
    modified:
      NEWS                           NEWS-20050323055033-4e00b5db738777ff
      bzrlib/dirstate.py             dirstate.py-20060728012006-d6mvoihjb3je9peu-1
      bzrlib/tests/test_dirstate.py  test_dirstate.py-20060728012006-d6mvoihjb3je9peu-2
    ------------------------------------------------------------
    revno: 3477.1.1.1.1
    revision-id:john at arbash-meinel.com-20080605211911-2xtal2ehwcqkcymy
    parent: john at arbash-meinel.com-20080605210642-zoc3nelx84xmsxuf
    committer: John Arbash Meinel <john at arbash-meinel.com>
    branch nick: symlink_unicode_135320
    timestamp: Thu 2008-06-05 16:19:11 -0500
    message:
      Assert that we properly encode inv_entry.symlink_target, (bug #135320)
    modified:
      bzrlib/dirstate.py             dirstate.py-20060728012006-d6mvoihjb3je9peu-1
      bzrlib/tests/test_dirstate.py  test_dirstate.py-20060728012006-d6mvoihjb3je9peu-2
=== modified file 'NEWS'
--- a/NEWS	2008-06-06 19:07:50 +0000
+++ b/NEWS	2008-06-09 16:03:47 +0000
@@ -22,6 +22,11 @@
     * Sanitize branch nick before using it as an attachment filename in
       ``bzr send``. (Lukáš Lalinský, #210218)
 
+    * Squash ``inv_entry.symlink_target`` to a plain string when
+      generating DirState details. This prevents from getting a
+      ``UnicodeError`` when you have symlinks and non-ascii filenames.
+      (John Arbash Meinel, #135320)
+
   IMPROVEMENTS:
 
     * Added the 'alias' command to set/unset and display aliases. (Tim Penhey)

=== modified file 'bzrlib/dirstate.py'
--- a/bzrlib/dirstate.py	2008-05-08 04:12:06 +0000
+++ b/bzrlib/dirstate.py	2008-06-05 21:47:39 +0000
@@ -1825,7 +1825,8 @@
             raise
         return result
 
-    def _inv_entry_to_details(self, inv_entry):
+    @staticmethod
+    def _inv_entry_to_details(inv_entry):
         """Convert an inventory entry (from a revision tree) to state details.
 
         :param inv_entry: An inventory entry whose sha1 and link targets can be
@@ -1841,7 +1842,8 @@
             size = 0
             executable = False
         elif kind == 'symlink':
-            fingerprint = inv_entry.symlink_target or ''
+            # We don't support non-ascii targets for symlinks yet.
+            fingerprint = str(inv_entry.symlink_target or '')
             size = 0
             executable = False
         elif kind == 'file':

=== modified file 'bzrlib/tests/test_dirstate.py'
--- a/bzrlib/tests/test_dirstate.py	2008-04-24 07:22:53 +0000
+++ b/bzrlib/tests/test_dirstate.py	2008-06-05 21:47:39 +0000
@@ -23,6 +23,7 @@
 from bzrlib import (
     dirstate,
     errors,
+    inventory,
     osutils,
     )
 from bzrlib.memorytree import MemoryTree
@@ -2514,3 +2515,26 @@
         state._discard_merge_parents()
         state._validate()
         self.assertEqual(exp_dirblocks, state._dirblocks)
+
+
+class Test_InvEntryToDetails(TestCaseWithDirState):
+
+    def assertDetails(self, expected, inv_entry):
+        details = dirstate.DirState._inv_entry_to_details(inv_entry)
+        self.assertEqual(expected, details)
+        # details should always allow join() and always be a plain str when
+        # finished
+        (minikind, fingerprint, size, executable, tree_data) = details
+        self.assertIsInstance(minikind, str)
+        self.assertIsInstance(fingerprint, str)
+        self.assertIsInstance(tree_data, str)
+
+    def test_unicode_symlink(self):
+        # In general, the code base doesn't support a target that contains
+        # non-ascii characters. So we just assert tha 
+        inv_entry = inventory.InventoryLink('link-file-id', 'name',
+                                            'link-parent-id')
+        inv_entry.revision = 'link-revision-id'
+        inv_entry.symlink_target = u'link-target'
+        details = self.assertDetails(('l', 'link-target', 0, False,
+                                      'link-revision-id'), inv_entry)