zero tokens. This fixes PR2045, thanks to Neil for finding another
incredibly subtle corner case :)
git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@47203 91177308-0d34-0410-b5e6-96231b3b80d8
message when handling the GNU ", ## __VA_ARGS__" extension. While
I'm at it, flag uses of this as extensions.
git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@46503 91177308-0d34-0410-b5e6-96231b3b80d8
incorrectly apply the multiple include optimization to files with
guards like:
#if !defined(x) MACRO
where MACRO could expand to different things in different contexts.
Thanks Neil!
git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@45716 91177308-0d34-0410-b5e6-96231b3b80d8
both Preprocessor and ASTContext, we no longer need to explicitly pass
MainFileID around in function calls that also pass either Preprocessor or
ASTContext. This resulted in some nice cleanups in the ASTConsumers and the
driver.
git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@45228 91177308-0d34-0410-b5e6-96231b3b80d8
contents of the header map. Look ma, no assumptions about input data
here (aka, corrupt header maps can't crash the compiler - crazy thought).
git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@45122 91177308-0d34-0410-b5e6-96231b3b80d8
cross-endianness case, where we checked the version in the wrong endianness.
Amusingly, the GCC logic that detects mixed endianness hmaps and rejects
them is dead for this very reason.
git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@45113 91177308-0d34-0410-b5e6-96231b3b80d8
HeaderSearch into DirectoryLookup, as a particular framework lookup is
specific to the directory we are currently querying.
git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@45093 91177308-0d34-0410-b5e6-96231b3b80d8
the internal representation. This also fixes a bug where -I foo -F foo would
not search foo as both a normal and framework include dir.
git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@45092 91177308-0d34-0410-b5e6-96231b3b80d8
Moved all clients of Diagnostics to use FullSourceLoc instead of SourceLocation.
Added many utility methods to FullSourceLoc to provide shorthand for:
FullLoc.getManager().someMethod(FullLoc.getLocation());
instead we have:
FullLoc.someMethod();
Modified TextDiagnostics (and related classes) to use this short-hand.
git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@44957 91177308-0d34-0410-b5e6-96231b3b80d8
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.
git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@44878 91177308-0d34-0410-b5e6-96231b3b80d8
that are builtin and those that are aren't. This is a bunch
of API refactoring that will make this possible, but there is
no functionality change yet.
git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@44473 91177308-0d34-0410-b5e6-96231b3b80d8
converts a parsed literal into an APFloat. We are still performing a copy of the
string, which hopefully will be removed eventually for performance reasons. This
version now is at least safe.
Changed rounding in APFloat construction in NumericLiteralParser from rmTowardsZero
to rmNearestTiesToEven.
git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@44422 91177308-0d34-0410-b5e6-96231b3b80d8
NumericLiteralParser::GetFloatValue(). Upon method return, this flag has the value
true if the returned APFloat can exactly represent the number in the parsed text,
and false otherwise.
Modified the implementation of GetFloatValue() to parse literals using APFloat's
convertFromString method (which allows us to set the value of isExact).
git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@44339 91177308-0d34-0410-b5e6-96231b3b80d8
This removes several gross hacks to work around the previous "lazy" behavior.
Two notes:
- MinimalActions still needs to be taught about the built-in types (This breaks one of the -noop test cases). I started this, then added a FIXME.
- I didn't convert Sema::GetObjcProtoType() yet.
git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@43567 91177308-0d34-0410-b5e6-96231b3b80d8
I need to (finally) change the way Class/id/SEL/IMP are built-in...the current approach of doing it in the preprocessor is "broken". The other problem is Sema::GetObjcIdType/GetObjcSelType/GetObjcClassType, the hooks that initialize ASTContext lazily. These built-in types need to be done up front...
git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@43557 91177308-0d34-0410-b5e6-96231b3b80d8
Chris Lattner
Dan Gohman
Steve Naroff
Ted Kremenek
Nate Begeman
Christopher Lamb