llvm-svn: 58077

llvm-svn: 58074

llvm-svn: 58073

conversions.

Added PerformImplicitConversion, which follows an implicit conversion sequence
computed by TryCopyInitialization and actually performs the implicit
conversions, including the extra check for ambiguity mentioned above.

llvm-svn: 58071

llvm-svn: 58070

llvm-svn: 58061

llvm-svn: 58058

llvm-svn: 58056

FileIDs. This seems better conceptually and lets the SourceManager
handle details of mapping the location to a file ID.
 - In practice, fixes an assert because this code wasn't using
   getPhysicalLoc.

llvm-svn: 58055

llvm-svn: 58054

llvm-svn: 58053

created with LHS and RHS whose types didn't match.

llvm-svn: 58049

llvm-svn: 58040

llvm-svn: 58030

llvm-svn: 58029

llvm-svn: 58028

Disable warning about potential leaks of returned values until we test it a little more (lots of noise).

llvm-svn: 58021

pointer-to-base. Also, add overload ranking for pointer conversions
(for both pointer-to-void and derived-to-base pointer conversions).

Note that we do not yet diagnose derived-to-base pointer conversion
errors that stem from ambiguous or inacessible base classes. These
aren't handled during overload resolution; rather, when the conversion
is actually used we go ahead and diagnose the error.

llvm-svn: 58017

Warn about potentially leaked objects that are returned from methods whose names do not follow the Cocoa Memory Management guidelines.

llvm-svn: 58012

Restrict creation of OverloadedFunctionDecl only to C++ (it was getting used for invalid redeclarations on C).

llvm-svn: 58008

Fix <rdar://problem/6311947> clang on xcode (regression): error: use of undeclared identifier 'expandedValue'.

Mea culpa: I introduced this regresson in the following 2 commits: r57529 (10/14), r57841 (10/20).

llvm-svn: 58007

Remove the GraphWriter-based version of the C++ class inheritance visualization, since it isn't being used and can't handle virtual bases properly

llvm-svn: 58002

Factored the QualTypeOrdering predicate into its own header
(TypeOrdering.h), now that it is used in two places.

llvm-svn: 58001

Now that DeclRefExpr accepts a NamedDecl, use a DeclRefExpr for when a CXXFieldDecl is referenced inside a method.

llvm-svn: 58000

Enhance reference-count checker to correctly identify CG "release" functions.  This fixes <rdar://problem/6303488>.

llvm-svn: 57997

Fix <rdar://problem/6257675> error: member reference base type ('NSUserDefaults *') is not a structure or union.

Teach Sema::ActOnMemberReferenceExpr() to look through local category implementations associated with the class.

llvm-svn: 57995

don't have duplicated direct base classes.

Seriliazation of base class specifiers is not yet implemented.

llvm-svn: 57991

aren't trying to compare with address-space qualifiers (for now).

Clean up handing of DeclRefExprs in Expr::isLvalue and refactor part
of the check into a static DeclCanBeLvalue.

llvm-svn: 57980

conversions (e.g., comparing int* -> const int* against 
int* -> const volatile int*); see C++ 13.3.3.2p3 bullet 3.

Add Sema::UnwrapSimilarPointerTypes to simplify the control flow of
IsQualificationConversion and CompareQualificationConversion (and fix
the handling of the int* -> volatile int* conversion in the former).
 

llvm-svn: 57978

llvm-svn: 57977

llvm-svn: 57964

llvm-svn: 57963

llvm-svn: 57951

1. Remove a bogus assertion, clients other than sema can return a
   null pointer from actions that result in ParseTypeName returning null.
2. Remove dead RParenLoc variable.
3. Simplify control flow handling error conditions.
4. On a major failure, we should skip until ')' not until '}'.

llvm-svn: 57949

Fix a thinko in the qualification-conversion check when the qualificaitons are disjoint, and add some overloading-based tests of qualification conversions

llvm-svn: 57942

llvm-svn: 57941

Changes:
  - Sema::IsQualificationConversion determines whether we have a qualification
    conversion.
  - Sema::CheckSingleAssignment constraints now follows the C++ rules in C++,
    performing an implicit conversion from the right-hand side to the type of
    the left-hand side rather than checking based on the C notion of 
    "compatibility". We now rely on the implicit-conversion code to
    determine whether the conversion can happen or
    not. Sema::TryCopyInitialization has an ugly reference-related
    hack to cope with the initialization of references, for now.
  - When building DeclRefExprs, strip away the reference type, since
    there are no expressions whose type is a reference. We'll need to
    do this throughout Sema.
  - Expr::isLvalue now permits functions to be lvalues in C++ (but not
  in C).

llvm-svn: 57935

llvm-svn: 57927

llvm-svn: 57924

When conjuring symbols for compound assignments, use the promoted type to determine if the symbolic value as a "loc::" or "nonloc::" value.

llvm-svn: 57917