forked from OSchip/llvm-project
5192783bb2
Similarly to other patches of mine, I'm trying to uniformize the checker interface so that dependency checkers don't emit diagnostics. The checker that made me most anxious so far was definitely RetainCount, because it is definitely impacted by backward compatibility concerns, and implements a checker hierarchy that is a lot different to other examples of similar size. Also, I don't have authority, nor expertise regarding ObjC related code, so I welcome any objection/discussion! Differential Revision: https://reviews.llvm.org/D78099 |
||
|---|---|---|
| .. | ||
| Inputs/expected-plists | ||
| DynDispatchBifurcate.m | ||
| InlineObjCClassMethod.m | ||
| InlineObjCInstanceMethod.h | ||
| InlineObjCInstanceMethod.m | ||
| ObjCDynTypePopagation.m | ||
| ObjCImproperDynamictallyDetectableCast.m | ||
| RetainCountExamples.m | ||
| analysis-order.c | ||
| assume-super-init-does-not-return-nil.m | ||
| containers.cpp | ||
| dyn-dispatch-bifurcate.cpp | ||
| eager-reclamation-path-notes.c | ||
| eager-reclamation-path-notes.cpp | ||
| false-positive-suppression.c | ||
| false-positive-suppression.cpp | ||
| false-positive-suppression.m | ||
| inline-defensive-checks.c | ||
| inline-defensive-checks.cpp | ||
| inline-defensive-checks.m | ||
| path-notes.c | ||
| path-notes.cpp | ||
| path-notes.m | ||
| placement-new-fp-suppression.cpp | ||
| retain-count-self-init.m | ||
| stl.cpp | ||
| temp-dtors-path-notes.cpp | ||
| test-always-inline-size-option.c | ||
| test_objc_inlining_option.m | ||