homepage

> 
>> entirely deterministic: I couldn't see any other reason why the flag 
> would have different values
>> on different machines.
> Sorry, what flag?
By "flag" I mean _cache_generated_egg ("flag" as in Boolean value)
> Patches for upstream cpython would be most helpful. I also think that fixing 
> bugs in the pythonv branch makes it harder to review.
Ordinarily I'd submit a cpython patch, but in this case it's a one liner as Paul has
suggested, so there's not much to review / comment on.IMO BitBucket makes it
reasonably easy to review short patches like this. Here's the change to
packaging.manifest:
--- a/Lib/packaging/manifest.py  Sun Nov 06 22:27:53 2011 +0000
+++ b/Lib/packaging/manifest.py  Mon Nov 07 14:58:23 2011 +0000
@@ -366,7 +366,8 @@
     # ditch end of pattern character
     empty_pattern = _glob_to_re('')
     prefix_re = _glob_to_re(prefix)[:-len(empty_pattern)]
-    pattern_re = "^" + os.path.join(prefix_re, ".*" + pattern_re)
+    # See issue 13193: Don't use os.path.join
+    pattern_re = "^%s/.*%s" % (prefix_re, pattern_re)
   else:                # no prefix -- respect anchor flag
     if anchor:
       pattern_re = "^" + pattern_re
and the change to distutils.filelist:
--- a/Lib/distutils/filelist.py  Mon Nov 07 14:58:23 2011 +0000
+++ b/Lib/distutils/filelist.py  Mon Nov 07 15:06:18 2011 +0000
@@ -313,7 +313,8 @@
     # ditch end of pattern character
     empty_pattern = glob_to_re('')
     prefix_re = (glob_to_re(prefix))[:-len(empty_pattern)]
-    pattern_re = "^" + os.path.join(prefix_re, ".*" + pattern_re)
+    # See issue 13193: Don't use os.path.join
+    pattern_re = "^%s/.*%s" % (prefix_re, pattern_re)
   else:                # no prefix -- respect anchor flag
     if anchor:
       pattern_re = "^" + pattern_re
You'll see I used a different idiom to Paul in my fix :-)
Can the distutils/packaging duplication not be avoided? IMO the correct
cpython fix would address this.