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

ASTContext::isObjCObjectPointerType() needs to consider blocks as objects.

Note: My previous commit was done in the test directory...as a result, this commit was necessary.
llvm-svn: 57914

llvm-svn: 57910

llvm-svn: 57909

Handle [NSAutoreleasePool addObject:] (an alternative way to add objects to the current autorelease pool).

Added initial code for tracking stack of autorelease pools.

llvm-svn: 57908

Found this while fixing another unrelated radar.

llvm-svn: 57904

llvm-svn: 57899

Fix <rdar://problem/6265257> warnings for ambiguous message send swamp other warnings.

Reworked Sema::MatchTwoMethodDeclarations() to optionally match based on method size and alignment (the default in GCC). Changed Sema::LookupInstanceMethodInGlobalPool() to use this feature.

Added -Wno-struct-selector-match to driver, however didn't hook it up yet. Added a FIXME that says this.

llvm-svn: 57898

GRExprEngine::VisitCast() so that other parts of the analyzer can be ignorant.
When we cast "array of type T" to "pointer to T", we get the loc::MemRegionVal
corresponding to the array variable. This is sufficient for BasicStore, but not
for RegionStore. RegionStore should get the element region for the first array
element in the cast. So next comes to the revamping of transfer functions for
different store model.

llvm-svn: 57897