[Lldb-commits] [lldb] r328083 - Fix TestOperatorOverload for 32-bit builds

[Pavel Labath via lldb-commits]

Affirmative.

I've checked the compiler invocations before and after the patch. -g goes
only to b.cpp. (also, this is the same pattern we use for other tests which
want to build stuff with no debug info).


On Wed, 21 Mar 2018 at 15:47, Davide Italiano <dccitaliano at gmail.com> wrote:

> On Wed, Mar 21, 2018 at 2:43 AM, Pavel Labath via lldb-commits
> <lldb-commits at lists.llvm.org> wrote:
> > Author: labath
> > Date: Wed Mar 21 02:43:50 2018
> > New Revision: 328083
> >
> > URL: http://llvm.org/viewvc/llvm-project?rev=328083&view=rev
> > Log:
> > Fix TestOperatorOverload for 32-bit builds
> >
> > - use more goodies from Makefile.rules to correctly build a 32-bit
> > binary.
> > - avoid hardcoding typeof(nil) in the test.
> >
> > This should partially fix the linux bot. There is still one assertion
> > failure remaining, which I'll have to investigate separately, as I am
> > not experiencing it locally.
> >
> > Modified:
> >
>  lldb/trunk/packages/Python/lldbsuite/test/lang/cpp/operator-overload/Makefile
> >
>  lldb/trunk/packages/Python/lldbsuite/test/lang/cpp/operator-overload/TestOperatorOverload.py
> >
> > Modified:
> lldb/trunk/packages/Python/lldbsuite/test/lang/cpp/operator-overload/Makefile
> > URL:
> http://llvm.org/viewvc/llvm-project/lldb/trunk/packages/Python/lldbsuite/test/lang/cpp/operator-overload/Makefile?rev=328083&r1=328082&r2=328083&view=diff
> >
> ==============================================================================
> > ---
> lldb/trunk/packages/Python/lldbsuite/test/lang/cpp/operator-overload/Makefile
> (original)
> > +++
> lldb/trunk/packages/Python/lldbsuite/test/lang/cpp/operator-overload/Makefile
> Wed Mar 21 02:43:50 2018
> > @@ -1,18 +1,8 @@
> >  LEVEL = ../../../make
> >
> >  CXX_SOURCES = a.cpp b.cpp
> > -CXXFLAGS_NO_DEBUGINFO = -c
> > -CXXFLAGS_DEBUGINFO = -c -g
> >
> > -all: main
> > -
> > -main: a.o b.o
> > -       $(CXX) $^ -o $@ $(LDFLAGS)
> > +include $(LEVEL)/Makefile.rules
> >
> >  a.o: a.cpp
> > -       $(CXX) $< $(CXXFLAGS_NO_DEBUGINFO) -o $@
> > -
> > -b.o: b.cpp
> > -       $(CXX) $< $(CXXFLAGS_DEBUGINFO) -o $@
> > -
> > -include $(LEVEL)/Makefile.rules
> > +       $(CC) $(CFLAGS_NO_DEBUG) -c $< -o $@
> >
>
> Thanks for fixing this! Only one comment.
> I originally wrote this in a way that `-g` is passed only to b.cpp
> (and not to a).
> I needed that flag just to set a breakpoint (and I'm not sure if it's
> still hit, or just happens to work).
> Did this preserve the exact same meaning for the test?
>
> Best,
>
> --
> Davide
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/lldb-commits/attachments/20180321/b65e4f44/attachment-0001.html>