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
visits its decls, rather than just creating an "end()" iterator.
Fixed child_end() for statements and expressions to use
child_iterator() to create the end() iterator, rather than just
returning NULL.
Fixed bug in StmtIterator where we did not correctly detect if we had
marched off the end of the ScopedDecls.
llvm-svn: 43156
and StmtIteratorImpl (templated), which StmtIterator and
ConstStmtIterator now succintly subclass.
Implemented iteration over the initializers in DeclStmts. This is not
thoroughly tested, so there may be bugs.
llvm-svn: 43138
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
that will (soon) allow iteration over the initializers in
declarations. This new iterator mechanism is implemented by the
classes StmtIterator and ConstStmtIterator.
Patched a few files to use "operator++" instead of "operator+" on
child_iterators.
Friendship added in VarDecl to StmtIterator to allow returning a
reference to the initializer within the VarDecl. We may not wish this
as a permanent solution.
llvm-svn: 43105
we currently turn:
c = @encode(char *)[2] + 4;
into:
c = "foo"[2] + 4;
Right now the foo string is hard coded, but you can imagine a world
where it wouldn't be :)
llvm-svn: 43093
Silenced some VC++ warnings.
Had to rephrase a partial specialization of the IntrospectionTrait struct in SerializationTest.cpp, please review.
Added a compiler specific workaround in IdentifierTable.h. Is that the way to fix this kind of issues?
llvm-svn: 43074
serialization logic as well as driver code is now in
Driver/SerializationTest.cpp. The status of this code is that it
should be used by no clients.
Added --test-pickling option to driver to run the serialization code.
Modified IdentifierInfo and IdentifierTable to have friend classes
that permit object serialization. Such friendship may not be needed
in the final design.
llvm-svn: 43052
Rename SourceRange::Begin()/End() to getBegin()/getEnd() for
consistency with other code.
Start building the rewriter towards handling @encode.
llvm-svn: 43047