ASTConsumer to process the AST before it is destroyed.
This allows elimination of HandleObjcMetaDataEmission.

llvm-svn: 43659

llvm-svn: 43640

llvm-svn: 43629

llvm-svn: 43628

method types.

llvm-svn: 43617

llvm-svn: 43613

2) Fixed a test failure (which should have failed all along!).

llvm-svn: 43589

A new test case added.

llvm-svn: 43568

Implement a more sensible strategy for ObjC built-in types (addressing a long standing FIXME in Sema::GetObjcIdType()).

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

llvm-svn: 43556

llvm-svn: 43540

Added new type and bitfield fields in some decl types in preparation for objective-c's type qualifiers.
Added initialization of Class/SEMA types.

llvm-svn: 43534

Stop pre-defining objc_msgSend/objc_getClass in the preprocessor. Instead, I generate these declaration on the fly when rewriting a message expression.

llvm-svn: 43529

llvm-svn: 43517

llvm-svn: 43515

llvm-svn: 43507

llvm-svn: 43504

- Add location info to category/protocol AST's
- Rewrite categories.

llvm-svn: 43501

Remove a couple FIXME's for rewriting ObjC interfaces (which are now being rewritten properly).

llvm-svn: 43494

More support for rewriting ObjC intefaces. Still some edge cases to handle...

llvm-svn: 43493

This commit contains lot's of small tweaks to how we pass around and store SourceLocation's for interfaces/protocols/categories/implementations.

llvm-svn: 43475

Moved a dependent predicate in an if statement to be an assertion
within the if statement body.

llvm-svn: 43453

"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

(x) == x  is the treated the same as x == x.

llvm-svn: 43448

errors for cases such as "x == x".

Added test case to test this feature.

llvm-svn: 43447

llvm-svn: 43441

one bogus error on PR1750.

llvm-svn: 43436

resolving a crash on a .i file in PR1750.  We now generate 49 errors on the
.i file in that bug.

llvm-svn: 43433

Start rewriting ObjC interfaces. As a start, we comment out all the methods. This involved refining how the parser/AST passes/manages SourceLocations for ObjcMethodDecl's. 

llvm-svn: 43404

decl without an @interface decl.

llvm-svn: 43403

Thanks to Steve N. to point out using of offsetof for this.

llvm-svn: 43391

llvm-svn: 43188

Fix the previous (short lived:-) FIXME.

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

llvm-svn: 43155

Add a FIXME to an assert.
Change a dyn_cast_or_null back to cast (which is more efficient).

llvm-svn: 43152

llvm-svn: 43151

Tweak a recent fix to UsualArithmeticConversions (made by Chris - r43113). The benefit of this tweak is it guarantees the entire routine operates on unqualified types (which I believe is a bit clearer).  

llvm-svn: 43142

Fix a bug in Sema::CheckConditionalOperands(). When mixing pointers and null pointer constants, we need to promote the null pointer constant (which is an integer) to the pointer type. Test case is self explanatory.

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

Fix the following bug...

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