This removes several gross hacks to work around the previous "lazy" behavior.
Two notes:
- MinimalActions still needs to be taught about the built-in types (This breaks one of the -noop test cases). I started this, then added a FIXME.
- I didn't convert Sema::GetObjcProtoType() yet.
llvm-svn: 43567
"x == x" and "x != x". We emit a warning for these since they always evaluate
to a constant value and often indicate a logical error.
Added test case for this check.
llvm-svn: 43450
I didn't realize that GCC considers this a hard error (I thought it was built-in).
Since it's not, we should simply emit an error.
[dylan:~/llvm/tools/clang] admin% cc -c trivial.m
trivial.m:6: error: cannot find interface declaration for 'NSConstantString'
[administrators-powerbook59:~/llvm/tools/clang] admin% ../../Debug/bin/clang trivial.m
trivial.m:6:16: error: cannot find interface declaration for 'NSConstantString'
NSString *s = @"123";
^
1 diagnostic generated.
llvm-svn: 43157
This surfaced yesterday, when compiling test/Sema/cocoa.m on Leopard. Since this has nothing to do with ObjC, it's kind of bizarre this hasn't shown up before. I imagine Cocoa.h on Leopard may have changed recently?
Thanks to Ted for localizing the bug and giving me a useful AST dump...
llvm-svn: 43114
when comparing "float" and "const float". This "fixes" the
issue, but may not be the right fix. Steve, please review.
Testcase here: test/Sema/usual-float.c
llvm-svn: 43113
unsigned char asso_values[] = { 34 };
int legal2() {
return asso_values[0];
}
The code that creates the new constant array type was operating on the original type.
As a result, the constant type being generated was "unsigned char [1][]" (which is wrong).
The fix is to operate on the element type - in this case, the correct type is "unsigned char [1]"
I added this case to array-init.c, which clearly didn't catch this bogosity...
llvm-svn: 43112
Rename SourceRange::Begin()/End() to getBegin()/getEnd() for
consistency with other code.
Start building the rewriter towards handling @encode.
llvm-svn: 43047
This makes the typecheck much happier. Without this change, the type checker would have to special case "struct __builtin_CFString *". This change does assume the interface for NSConstantString is declared in the translation unit.
I left ASTContext::getCFConstantStringType() around for now (with a comment that says it is currently unused).
llvm-svn: 43021
This allowed me to fix the following hack from this weekend...
// FIXME: Devise a way to do this without using strcmp.
// Would like to say..."return getAsStructureType() == IdStructType;", but
// we don't have a pointer to ASTContext.
bool Type::isObjcIdType() const {
if (const RecordType *RT = getAsStructureType())
return !strcmp(RT->getDecl()->getName(), "objc_object");
return false;
}
...which is now...
bool isObjcIdType(QualType T) const {
return T->getAsStructureType() == IdStructType;
}
Side notes:
- I had to remove a convenience function from the TypesCompatibleExpr class.
int typesAreCompatible() const {return Type::typesAreCompatible(Type1,Type2);}
Which required a couple clients get a little more verbose...
- Result = TCE->typesAreCompatible();
+ Result = Ctx.typesAreCompatible(TCE->getArgType1(), TCE->getArgType2());
Overall, I think this change also makes sense for a couple reasons...
1) Since ASTContext vends types, it makes sense for the type compatibility API to be there.
2) This allows the type compatibility predeciates to refer to data not strictly present in the AST (which I have found problematic on several occasions).
llvm-svn: 43009