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

[Davide Italiano via lldb-commits]

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