SourceManager is passed by reference, allowing the SourceManager to be
associated with a specific translation unit, and not the entire execution
of the driver.

Modified all users of Diagnostics to comply with this new interface.

Integrated SourceManager as a member variable of TargetInfo. TargetInfo will
eventually be associated with a single translation unit (just like
SourceManager).

Made the SourceManager reference in ASTContext private. Provided accessor
getSourceManager() for clients to use instead. Modified clients to comply with
new interface.

llvm-svn: 44878

general use.

llvm-svn: 44876

No functionality change.

llvm-svn: 44875

llvm-svn: 44872

a method declaration.

llvm-svn: 44870

llvm-svn: 44857

llvm-svn: 44845

llvm-svn: 44844

Avoid the first person in a recently added comment. 

llvm-svn: 44843

- Tweak several tests to be compatible with my last commit.
- Add a test to message.m for an unusual case for GCC compat (as suggested by Chris).

llvm-svn: 44842

llvm-svn: 44841

Change err_undef_protocolref to warn_undef_protocolref (this is consistent with GCC).

llvm-svn: 44840

llvm-svn: 44839

the types are right in sema.  Thanks Steve.

llvm-svn: 44834

llvm-svn: 44833

llvm-svn: 44831

For example, struct { char a; short b:2; };

llvm-svn: 44830

Explicitly set the string literal type from "char *" to "constant array of char".

At this point, I am fairly certain the front-end is correct. Unfortunately, the back-end is still unhappy.

That said, I've commented out the two lines in globalinit.c that are causing problems.

Chris, please have a look...thanks!

llvm-svn: 44823

between fetching the size of the expression map (for use as
the next integer id for an Expr*) and the creation of the
entry in the map could be non-deterministic.  This could
cause the size of the map to be incremented prior to the
index being determine.

On Linux the map entry would be created first, causing the
map to the "size" to be incremented prior to it being
queried. On Mac OS X we had the reverse behavior. Now the
size is always queried prior to the new id being inserted
into the map.

This was the real cause of the bit-overrun triggered in
PR 1847:

  http://llvm.org/bugs/show_bug.cgi?id=1847
  
Also reverted the change in patch 44813, which was a bogus
fix to this problem:

  http://llvm.org/viewvc/llvm-project?rev=44813&view=rev

llvm-svn: 44822

compiles again on Linux.

llvm-svn: 44821

Add support for initializing char arrays from string literals.

Adapted from a patch by Anders Carlsson.

llvm-svn: 44816

dataflow analysis over expressions and decls.

This should fix bug 1847:

http://llvm.org/bugs/show_bug.cgi?id=1847

Thanks to Török Edwin for providing a test case that
identified the problem.

llvm-svn: 44813

type.

llvm-svn: 44809

llvm-svn: 44808

llvm-svn: 44807

llvm-svn: 44806

llvm-svn: 44804

llvm-svn: 44801

llvm-svn: 44800

llvm-svn: 44799

llvm-svn: 44798

llvm-svn: 44797

llvm-svn: 44795

llvm-svn: 44790

llvm-svn: 44789

llvm-svn: 44788

llvm-svn: 44787

llvm-svn: 44784

llvm-svn: 44783

llvm-svn: 44782