| Commit message (Collapse) | Author | Age | Files | Lines |
| ... | |
| |
|
|
|
|
| |
intact.
llvm-svn: 58028
|
| |
|
|
| |
llvm-svn: 58027
|
| |
|
|
| |
llvm-svn: 58024
|
| |
|
|
|
|
| |
little more (lots of noise).
llvm-svn: 58021
|
| |
|
|
| |
llvm-svn: 58020
|
| |
|
|
|
|
|
|
|
|
|
|
| |
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
|
| |
|
|
|
|
| |
LLVM library that isn't being linked in for CodeGen (will fix).
llvm-svn: 58015
|
| |
|
|
|
|
| |
names do not follow the Cocoa Memory Management guidelines.
llvm-svn: 58012
|
| |
|
|
| |
llvm-svn: 58011
|
| |
|
|
|
|
| |
for invalid redeclarations on C).
llvm-svn: 58008
|
| |
|
|
|
|
|
|
| |
undeclared identifier 'expandedValue'.
Mea culpa: I introduced this regresson in the following 2 commits: r57529 (10/14), r57841 (10/20).
llvm-svn: 58007
|
| |
|
|
| |
llvm-svn: 58005
|
| |
|
|
|
|
| |
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
|
| |
|
|
|
|
| |
CXXFieldDecl is referenced inside a method.
llvm-svn: 58000
|
| |
|
|
|
|
| |
functions. This fixes <rdar://problem/6303488>.
llvm-svn: 57997
|
| |
|
|
|
|
|
|
| |
('NSUserDefaults *') is not a structure or union.
Teach Sema::ActOnMemberReferenceExpr() to look through local category implementations associated with the class.
llvm-svn: 57995
|
| |
|
|
| |
llvm-svn: 57993
|
| |
|
|
|
|
|
|
| |
don't have duplicated direct base classes.
Seriliazation of base class specifiers is not yet implemented.
llvm-svn: 57991
|
| |
|
|
| |
llvm-svn: 57990
|
| |
|
|
|
|
| |
Roman Divacky!
llvm-svn: 57988
|
| |
|
|
| |
llvm-svn: 57981
|
| |
|
|
|
|
|
|
|
| |
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
|
| |
|
|
| |
llvm-svn: 57979
|
| |
|
|
|
|
|
|
|
|
|
|
| |
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
|
| |
|
|
|
|
| |
inline
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
|
| |
|
|
|
|
| |
- Stop playing fast and loose with the std stream.
llvm-svn: 57948
|
| |
|
|
|
|
| |
are disjoint, and add some overloading-based tests of qualification conversions
llvm-svn: 57942
|
| |
|
|
| |
llvm-svn: 57941
|
| |
|
|
| |
llvm-svn: 57938
|
| |
|
|
|
|
|
|
|
|
|
| |
- Split backend related consumer out into Backend.cpp, replaces
LLVMCodeGenWriter.
- Structure follows llvm-gcc to some extent.
- Still need to implement all the options which impact code
generation and the optimization passes which llvm-gcc uses at
various levels.
llvm-svn: 57936
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
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: 57931
|
| |
|
|
|
|
| |
previous commit.
llvm-svn: 57930
|
| |
|
|
| |
llvm-svn: 57927
|
| |
|
|
| |
llvm-svn: 57924
|
| |
|
|
|
|
| |
determine if the symbolic value as a "loc::" or "nonloc::" value.
llvm-svn: 57917
|
| |
|
|
|
|
|
|
|
| |
blocks as objects
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
|
| |
|
|
|
|
|
|
| |
blocks as objects
ASTContext::isObjCObjectPointerType() needs to consider blocks as objects.
llvm-svn: 57913
|
| |
|
|
| |
llvm-svn: 57910
|
| |
|
|
| |
llvm-svn: 57909
|
| |
|
|
|
|
|
|
| |
the current autorelease pool).
Added initial code for tracking stack of autorelease pools.
llvm-svn: 57908
|
| |
|
|
| |
llvm-svn: 57907
|
| |
|
|
|
|
| |
Found this while fixing another unrelated radar.
llvm-svn: 57904
|
| |
|
|
| |
llvm-svn: 57903
|
| |
|
|
| |
llvm-svn: 57902
|