Robert Collins wrote:
> IIRC this test is to allow non-VPATH-aware makes to work correctly. In
> theory if you are building in the src tree it will output
> ufs/store_dir_ufs.c, otherwise /path/to/src/src/fs/ufs/store_dir_ufs.c.
>
> The test is broken though - it test should be test -f ufs/store_dir_ufs
> || ech `/home/users...
>
> What precise version of automake did you create the .in's with ? (I'll
> track this down as an automake bug).
This was a current HEAD snapshot tarball.
It very much looks like an Sun make incompability/bug, not an automake
bug.
> > Trying to make heads or tail of that make line, but I can't. There
> seems
> > to be more than one thing failing here.
>
> Nope, just the one - file location test.
Not entirely.
a) There is both an explicit rule and a extension rule in the Makefile.
b) Both rules looks correct, and the explicit is using the expected path
Which makes me think that the extension based rule is being called and
that $< within backquotes gets expanded wrongly.
> can you confirm that that is what is in your Makefile.in && Makefile on
> the compile farm?
As far as I can see it is. It is the HEAD snapshot tarball.
> Otherwise, if you have that test, then either that rule is not getting
> fired - try adding an echo or something to it before the $(CC) line - or
> the sun make is fiddling with the rule contents as part of it's VPATH
> support (urrggh).
My guess exactly. Don't have time to test now (need to sleep).
You are welcome to try fiddling around as much as you want. You have as
much access to these Solaris 8 boxes as I have. Just ssh to
compile.sourceforge.net and select the box you want.
To get sources into the compilefarm, start by uploading the tarball(s)
to your SourceForge shell account, then login to the compile farm and
copy them over with "scp shell1:filename ."
Regards
Henrik
Received on Mon Oct 08 2001 - 18:16:02 MDT
This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 16:14:26 MST