Submitted by:
Reviewed by:
- ParseForStatement(): Put back a test/assignment. My removal of
ParseExprStmt() was a bit over zealous:-(thanks to Chris for pointing it out)
- Add assert to VisitDeclStmt().
- Removed an out-of-date FIXME
- Added some curlies for a couple multi-line calls to Diag().

llvm-svn: 39528

Comment format changes.

llvm-svn: 39527

Submitted by:
Reviewed by:
- Many tweaks to various diagnostics.
- Fixed some location/range issues.
- Bug fix to Sema::ParseDeclStmt() - error return code is "true", not 0.

llvm-svn: 39526

- Conjugate "diagnostic" correctly for 1 diagnostic.

llvm-svn: 39525

void test1() {
  foo:
    goto foo;
    goto foo;
    goto foo;
}

void test() {
  goto l;

l:
  ;
}
into:

define void @test1() {
entry:
        br label %foo

foo:            ; preds = %0, %foo, %entry
        br label %foo
                ; No predecessors!
        br label %foo
                ; No predecessors!
}

define void @test() {
entry:
        br label %l

l:              ; preds = %entry
}

llvm-svn: 39524

Submitted by:
Reviewed by:
Unified the diagnostics for function calls. Since we have range support,
there is no need for including the argument number. Instead, I've made
the diags more expressive by including more type info.

Also improved the indentation of many calls to Diag (which can be 2-3
lines now).

llvm-svn: 39523

llvm-svn: 39522

llvm-svn: 39521

llvm-svn: 39520

cases.

llvm-svn: 39519

Submitted by:
Reviewed by:
Implement some FIXME's that stand in the way of fully typechecking "for"
statements. This involved:

- Adding a DeclStmt AST node (with statement visitor). The DeclStmt
printer is preliminary.
- Added a ParseDeclStmt action, called from Parser::ParseForStatement()
and Parser::ParseStatementOrDeclaration(). DID NOT add to
Parser::ParseIdentifierStatement()...probably could have, however didn't
really understand the context of this rule (will speak with Chris).
- Removed ParseExprStmt (and it's clients)...it was vestigial.

llvm-svn: 39518

Submitted by:
Reviewed by:
- Finished Sema::ParseReturnStmt(). Still need to tweak ranges.
- Tweaked location for function arguments (they now point at the expression directly, no parens or commas).
- Added InvalidOperands helper...was sick of looking at the same 3 lines in ~9 Check functions.
- Added a few diags and moved a group of statement diags to the proper comment/category.

llvm-svn: 39517

extern int pintFunc(int *, int *);

int test() {
  pintFunc(0,
           3);
}

We now print:

t3.c:4:13: warning: passing argument 2 makes pointer from integer without a cast
  pintFunc(0,
  ~~~~~~~~  ^

instead of:

t3.c:4:13: warning: passing argument 2 makes pointer from integer without a cast
  pintFunc(0,
  ~~~~~~~~

llvm-svn: 39516

Submitted by:
Reviewed by:
Implement type checking for ParseDoStmt, ParseWhileStmt, ParseIfStmt, and
ParseForStmt. ParseForStmt still under construction (contains a FIXME).

llvm-svn: 39515

Submitted by:
Reviewed by:
Add range support to Sema::CheckConditionalOperands().

llvm-svn: 39514

Submitted by:
Reviewed by:
Refine Sema::ParseCallExpr() diags (range support, add types).

Before:

func-assign.c:27:11: warning: passing argument 1 from incompatible pointer type
  pintFunc(&FOO);
          ^
func-assign.c:28:12: error: incompatible type for argument 1
  floatFunc(&FOO);
           ^
func-assign.c:29:12: error: too many arguments to function
  floatFunc(1,2,3);
           ^
After:

func-assign.c:27:11: warning: passing incompatible pointer 'struct foo *' to function expecting 'int *'
  pintFunc(&FOO);
  ~~~~~~~~^~~~~
func-assign.c:28:12: error: passing incompatible type 'struct foo *' to function expecting 'float'
  floatFunc(&FOO);
  ~~~~~~~~~^~~~~
func-assign.c:29:12: error: too many arguments to function
  floatFunc(1,2,3);
  ~~~~~~~~~^  ~

llvm-svn: 39513

Submitted by:
Reviewed by:
- Implement FIXME in Sema::CheckIndirectionOperand().
- Added "const" to FunctionDecl::getResultType().

llvm-svn: 39512

llvm-svn: 39511

llvm-svn: 39510

the label identifier.  Handle fwd references etc.  This allows us to detect
uses of undefined labels and label redefinitions, such as:

t.c:2:12: error: redefinition of label 'abc'
  abc: ;   abc:
           ^
t.c:2:3: error: previous definition is here
  abc: ;   abc:
  ^
t.c:12:12: error: use of undeclared label 'hijl'
      goto hijl;
           ^

llvm-svn: 39509

void foo() {
  if (0) break;
  abc:
  def:
  hij:
    break;

into:

void foo() {
  if ((0)')
    ;
abc:
def:
hij:
  ;

instead of dropping the if and labels (due to break not being in a loop).

llvm-svn: 39508

llvm-svn: 39507

llvm-svn: 39506

llvm-svn: 39505

llvm-svn: 39504

llvm-svn: 39503

llvm-svn: 39502

Submitted by:
Reviewed by:
- Added type checking to Sema::ParseReturnStmt (still under construction).
- Improved Expr::isLvalue() and Expr::isModifiableLvalue() to return more
info. Used the info in Sema::CheckAssignmentOperands() to produce more
descriptive diagnostics. Added FIXME to other clients of isLvalue()/etc.
- Added a SourceLocation slot to MemberExpr...changed the implementation
of getSourceRange().
- Added getResultType() helper to FunctionDecl.
- Changed many Diag calls to use the SourceRange support (now that it's
a big hit...we better milk it:-).

llvm-svn: 39501

Submitted by: Bill Wendling
Reviewed by:

- Can do just a 'cast<>()' because we're checking that it's Tagged.

llvm-svn: 39500

Submitted by: Bill Wendling
Reviewed by: Steve Naroff

- Steve suggested avoiding the dyn_cast by using the "Tagged" type class
  and having the "default" just return false.

llvm-svn: 39499

Submitted by: Bill Wendling
Reviewed by: Chris Lattner

- Rework the isDerivedType method so that if a language doesn't support
  references, it won't have to pay the price for them. This inlines the
  checks for derived types and turns it into a switch statement instead.

llvm-svn: 39498

Submitted by: Bill Wendling
Reviewed by:

C++ references testcase.

llvm-svn: 39497

Submitted by: Bill Wendling
Reviewed by: Chris Lattner

- Initial support for C++ references. Adding to the AST and Parser.
  Skeletal support added in the semantic analysis portion. Full semantic
  analysis is to be done soon.

llvm-svn: 39496

library to be built for the driver to link.

llvm-svn: 39495

llvm-svn: 39494

constants.

llvm-svn: 39493

llvm-svn: 39492

llvm-svn: 39491

llvm-svn: 39490

llvm-svn: 39489