Hi Vedant, Thanks for the reply! Yes, I have a small test case- I actually attached it to the original bug report (https://llvm.org/bugs/show_bug.cgi?id=30413), but I will go ahead and try adding it to clang/test/CodeGenObjC, or extend a case if possible.
Is it OK to make changes to CodeGenObjC directly, or should I submit a diff of those changes to this list, along with my original patch? Thanks! --David > On Feb 9, 2017, at 8:22 PM, Vedant Kumar <v...@apple.com> wrote: > > Hi David, > > Thanks for tracking this down. > > Do you have a small reproducer to use as a test case? Ideally, you'd add a > regression test to clang/test/CodeGenObjC, or extend an existing one. > > vedant > >> On Feb 7, 2017, at 6:42 PM, Lobron, David via cfe-commits >> <cfe-commits@lists.llvm.org> wrote: >> >> Hello clang developers, >> >> I discovered a bug that affects Objective-C programs compiled with clang on >> Linux. The current code was not emitting Objective-C class name metadata, >> which made it impossible for programs to do runtime type introspection. I >> opened a bug report that describes the problem and provides a test program >> that reproduces it: >> >> https://llvm.org/bugs/show_bug.cgi?id=30413 >> >> I've attached an svn-generated patch file: the patch changes one argument to >> the getObjCEncodingForTypeImpl function from false to true, so that >> Objective-C class names are encoded. If this looks OK, it would be great if >> it could be added to the trunk. Once that is done, the bug can of course be >> closed. >> >> Thank you. >> >> Sincerely, >> >> David Lobron >> >> <PatchForBug30413.patch>_______________________________________________ >> cfe-commits mailing list >> cfe-commits@lists.llvm.org >> http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits > _______________________________________________ cfe-commits mailing list cfe-commits@lists.llvm.org http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
