| Commit message (Collapse) | Author | Age | Files | Lines |
... | |
|
|
|
| |
llvm-svn: 43778
|
|
|
|
|
|
| |
functions. Patch contributed by Nuno Lopes, thanks!
llvm-svn: 43757
|
|
|
|
|
|
| |
contributed by Oliver Hunt, thanks!
llvm-svn: 43750
|
|
|
|
|
|
| |
instance method. Since all classes are also instances, this is appropriate.
llvm-svn: 43708
|
|
|
|
| |
llvm-svn: 43666
|
|
|
|
| |
llvm-svn: 43665
|
|
|
|
|
|
|
| |
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
|
|
|
|
|
|
|
|
| |
@interface).
A new test case added.
llvm-svn: 43568
|
|
|
|
|
|
|
|
|
|
|
|
| |
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
|
|
|
|
|
|
|
|
| |
objective-c's type qualifiers.
Added initialization of Class/SEMA types.
llvm-svn: 43534
|
|
|
|
|
|
| |
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
|
|
|
|
|
|
| |
- Rewrite categories.
llvm-svn: 43501
|
|
|
|
|
|
| |
rewritten properly).
llvm-svn: 43494
|
|
|
|
| |
llvm-svn: 43493
|
|
|
|
|
|
| |
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
|
|
|
|
|
|
| |
This involved refining how the parser/AST passes/manages SourceLocations for ObjcMethodDecl's.
llvm-svn: 43404
|
|
|
|
|
|
|
|
| |
@implementation
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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
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
|
|
|
|
|
|
| |
Change a dyn_cast_or_null back to cast (which is more efficient).
llvm-svn: 43152
|
|
|
|
| |
llvm-svn: 43151
|
|
|
|
|
|
| |
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
|
|
|
|
|
|
|
|
|
|
| |
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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
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
|
|
|
|
| |
llvm-svn: 43075
|
|
|
|
|
|
| |
report an error if a static initializer is not constant.
llvm-svn: 43058
|
|
|
|
| |
llvm-svn: 43051
|
|
|
|
| |
llvm-svn: 43050
|