llvm-project

Commit Graph

Author	SHA1	Message	Date
Pavel Labath	e1463ef4d3	Make TestDynamicValueSameBase gcc-compatible gcc will say that the type of "this" is "T * const", clang "T *". Compare the unqualified type names to erase the difference between the two, as the constness is not a part of this test. FWIW, I think that the gcc behavior makes more sense here. llvm-svn: 326449	2018-03-01 16:56:28 +00:00
Jim Ingham	06292869cd	We were getting the wrong dynamic type if there were two classes with the same basename. There's a bug in FindTypes, it ignores the exact flag if you pass a name that doesn't begin with :: and pass eTypeClassAny for the type. In this case we always know that the name we get from the vtable name is absolute so we can work around the bug by prepending the "::". This doesn't fix the FindTypes bug. <rdar://problem/38010986> llvm-svn: 326412	2018-03-01 02:44:34 +00:00

Author

SHA1

Message

Date

Pavel Labath

e1463ef4d3

Make TestDynamicValueSameBase gcc-compatible

gcc will say that the type of "this" is "T * const", clang "T *".
Compare the unqualified type names to erase the difference between the
two, as the constness is not a part of this test.

FWIW, I think that the gcc behavior makes more sense here.

llvm-svn: 326449

2018-03-01 16:56:28 +00:00

Jim Ingham

06292869cd

We were getting the wrong dynamic type if there were two classes with the same basename.

There's a bug in FindTypes, it ignores the exact flag if you pass a name that doesn't begin with
:: and pass eTypeClassAny for the type.

In this case we always know that the name we get from the vtable name is absolute so we can
work around the bug by prepending the "::".  This doesn't fix the FindTypes bug.

<rdar://problem/38010986>

llvm-svn: 326412

2018-03-01 02:44:34 +00:00

2 Commits