caio/clang-p2996
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
38,425 Commits 1 Branch 0 Tags
38ef3a8ec7e5b4d1f5e951136094de9a6f9ae22e
Commit Graph

286 Commits

Author SHA1 Message Date
Anders Carlsson
5dd106b212 Handle initializing vector elements correctly. Emit just one warning if there are excess initializers, instead of one per initializer. 
llvm-svn: 44525
 2007-12-03 01:01:28 +00:00
Chris Lattner
310369fb84 restore these lines, which fixes some regtest failures. 
llvm-svn: 44516
 2007-12-02 07:50:03 +00:00
Chris Lattner
9724ce12f9 improve VC++ compatibility, patch by Cédric Venet. 
llvm-svn: 44496
 2007-12-02 00:47:03 +00:00
Steve Naroff
205ec3d07a Yesterday, I simplified how we stream top-level decls. 
After a discussion with Ted, we both came to the conclusion that adding a "HandleTopLevelDeclaration" hook to ASConsumer is far more elegant. The default implementation of HandleTopLevelDeclaration will be responsible for iterating over the ScopedDecl (which has a chain of the decls:-).

TODO: Once Ted adds HandleTopLevelDeclaration, make sure TagDecls are chainged appropriately...
llvm-svn: 44445
 2007-11-29 23:05:20 +00:00
Christopher Lamb
2ed9afd777 Update the initializer's type, in addition to the decl, if we've changed the type of the decl based on it. 
llvm-svn: 44440
 2007-11-29 19:09:19 +00:00
Steve Naroff
197616c3a8 Several fixes/simplifications surrounding how we stream top-level decl AST's. 
The following code...

typedef struct cssm_data {} CSSM_DATA, *CSSM_DATA_PTR;

struct Y { int A; };

struct X { int A; } D; 

struct X E, F;

...now produces the following output...

> ../../Debug/bin/clang xx.c -ast-print
Read top-level tag decl: 'cssm_data'
typedef struct cssm_data CSSM_DATA;
typedef struct cssm_data *CSSM_DATA_PTR;
Read top-level tag decl: 'Y'
Read top-level tag decl: 'X'
Read top-level variable decl: 'D'
Read top-level variable decl: 'E'
Read top-level variable decl: 'F'

...which is much more accurate than the previous -ast-print output...

typedef struct cssm_data CSSM_DATA;
typedef struct cssm_data CSSM_DATA;
Read top-level variable decl: 'D'
Read top-level variable decl: 'E'
Read top-level variable decl: 'E'

llvm-svn: 44421
 2007-11-28 22:54:11 +00:00
Chris Lattner
db2a6ef881 Fix a bug checking for 'int foo(void)' that didn't look through typedefs of void. 
Bug pointed out by Michael Zolda, thanks!

llvm-svn: 44408
 2007-11-28 18:51:29 +00:00
Chris Lattner
1a6bb70ad0 Set loc earlier in CheckSingleInitializer to avoid emitting a 
diagnostic without a location.  This produces:

simpleTest.c:2:18: error: initializer element is not constant
int *myPointer = &(myArray[2]);
                 ^~~~~~~~~~~~~

instead of:

error: initializer element is not constant
llvm-svn: 44375
 2007-11-27 21:21:35 +00:00
Steve Naroff
0ee0b0ab8c Move the null pointer constant check from Sema::CheckSingleInitializer/ActOnCallExpr/CheckMessageArgumentTypes/ActOnReturnStmt to Sema::CheckSingleAssignmentConstraints. This makes sure all null pointer assignments are considered compatible. 
Thanks to Seo Sanghyeon for the bug, follow-through, and patch!

llvm-svn: 44366
 2007-11-27 17:58:44 +00:00
Chris Lattner
db3467f8d4 handle __vector_size__ like vector_size 
llvm-svn: 44358
 2007-11-27 07:28:18 +00:00
Chris Lattner
5c3f1541a7 Improve function decl merging, patch by Oliver Hunt! 
llvm-svn: 44253
 2007-11-20 19:04:50 +00:00
Steve Naroff
14f5f79bb6 Now that we are passing back "free standing decls", make sure -ast-dump works like -ast-print. 
Also added a cast to be safe...

llvm-svn: 44209
 2007-11-17 21:37:36 +00:00
Steve Naroff
c1e6d60b14 Make sure Sema::ParsedFreeStandingDeclSpec() returns a decl representing the type. 
Adding basic printing to StmtPrinter::PrintRawDecl().

llvm-svn: 44208
 2007-11-17 21:21:01 +00:00
Steve Naroff
d8ea1ac576 Implement support for variadic methods (work in progress). 
llvm-svn: 44171
 2007-11-15 12:35:21 +00:00
Steve Naroff
9e0887cff4 Allow properties within a protocol. The case below was asserting...now it works fine. 
@protocol CAMediaTiming

@property int beginTime;

@end

Comments in the code tell the rest of the story...

llvm-svn: 44117
 2007-11-14 14:15:31 +00:00
Chris Lattner
07b201d9c0 implement test/Sema/typedef-prototype.c, allowing code 
to declare a function with a typedef:

typedef int unary_int_func(int arg);
unary_int_func add_one;

This patch contributed by Seo Sanghyeon!

llvm-svn: 44100
 2007-11-14 06:34:38 +00:00
Nate Begeman
a0f78974a6 Give AST-walk passes a way to access DeclSpec attributes on functions and 
variables.

llvm-svn: 44073
 2007-11-13 22:14:47 +00:00
Nate Begeman
313f8ca67b Rename Sema method to follow class naming convention 
llvm-svn: 44069
 2007-11-13 21:49:48 +00:00
Fariborz Jahanian
3a9fe93286 Patch to set context (interface, category, etc.) in which method is declared. 
llvm-svn: 44038
 2007-11-13 01:10:08 +00:00
Steve Naroff
fedb49771d Add category method definitions incrementally, removing a FIXME (like we do for class implementations). 
llvm-svn: 44027
 2007-11-12 22:05:31 +00:00
Steve Naroff
040f696bfc Fix regression to Sema::ObjcActOnStartOfMethodDef()...need to initialize InvalidType field to false. 
llvm-svn: 44023
 2007-11-12 19:48:27 +00:00
Steve Naroff
e3d1ab29da - Minor cleanup to yesterday's changes to Sema::ObjcActOnStartOfMethodDef(); 
- Add Sema::CurMethodDecl, in preparation for adding ObjcIvarRefExpr.
- Add ObjcInterfaceDecl::lookupInstanceVariable(), in prep for adding ivars.
- A couple renames in ObjcInterfaceDecl, while I was in the vicinity:-)

llvm-svn: 44015
 2007-11-12 13:56:41 +00:00
Steve Naroff
ff4dbff4f4 Remove Action::ObjcActOnMethodDefinition(). Rationale: 
- It is not an "action" - it is never called by the parser.
- It was only used by one method, Sema::ObjcActOnStartOfMethodDef().

As a result, the logic it embodied is now directly implemented in Sema::ObjcActOnStartOfMethodDef().

llvm-svn: 44008
 2007-11-12 04:59:00 +00:00
Steve Naroff
3434bebec9 Make sure @property is allowed within a category. 
Bug submitted by Keith Bauer.

CookieJar:Desktop keith$ cat test.m
#import <WebKit/WebKit.h>

llvm-svn: 44007
 2007-11-12 04:22:52 +00:00
Steve Naroff
d0bf516e70 Remove Sema::ObjcBuildMethodParameter(). 
Modify Sema::ParseParamDeclarator() to work for both ActOnStartOfFunctionDef() and ObjcActOnStartOfMethodDef().

llvm-svn: 44006
 2007-11-12 03:44:46 +00:00
Steve Naroff
b313fc3203 Replace 2 method definition actions (ActOnFunctionDefBody, ActOnMethodDefBody) with 1 method definition action (ActOnFinishFunctionBody). I can't think of any reason that we would need two action hooks. 
llvm-svn: 44000
 2007-11-11 23:20:51 +00:00
Steve Naroff
cac26f4f5f This is the last 5% of the solution to teaching Sema::ActOnInstanceMessage() about private methods (r43989). 
While the diff is large, the idea is very simple. When we parse method definitions (in an @implementation), we need to add them incrementally (rather than wait until the @end).

Other details...

- Renamed Sema::ActOnAddMethodsToObjcDecl() to Sema::ActOnAtEnd(). The methods are now optional arguments.
- Removed Parser::AllImplMethods (a nice cleanup).
- Added location info to ObjcImplementationDecl (since we will need it very soon:-)
- Modified message.m test to no longer allow the bogus diagnostic.

llvm-svn: 43995
 2007-11-11 17:19:15 +00:00
Steve Naroff
22e078e013 Teach Sema::ActOnInstanceMessage() about private methods. That is, methods declared in an implementation (but not listed in the interface). 
This commit is only 95% of the bug fix. The last piece to this puzzle is to add the method decls to the implementation incrementally (as we encounter them). At the moment, the methods aren't added until we see an @end (which is too late).

I will complete this later...

llvm-svn: 43989
 2007-11-11 00:10:47 +00:00
Fariborz Jahanian
0bd56b7727 Fixed a bug which exposed the internally built type to user code. 
llvm-svn: 43987
 2007-11-10 22:00:55 +00:00
Fariborz Jahanian
6aafd4130b Minor code clean up in method def area. 
llvm-svn: 43980
 2007-11-10 17:40:57 +00:00
Fariborz Jahanian
85e1d0d807 Represent method definitions as separate AST nodes. Pretty print will come next. 
llvm-svn: 43979
 2007-11-10 16:31:34 +00:00
Fariborz Jahanian
7a017215eb Some code clean up in the form of name changes for functions which 
process method definitions.

llvm-svn: 43967
 2007-11-09 22:27:59 +00:00
Fariborz Jahanian
b5605179c4 Added class context to method declarations. Provide "interface *" type 
to 'self' method of instance methods.

llvm-svn: 43957
 2007-11-09 19:52:12 +00:00
Fariborz Jahanian
19d4dbd217 Insert invisble arguments to method definition header. 
llvm-svn: 43948
 2007-11-09 17:18:29 +00:00
Fariborz Jahanian
56ff146ec4 First patch toward rewriting of method definitions. This is work in progress. 
llvm-svn: 43915
 2007-11-08 23:49:49 +00:00
Fariborz Jahanian
f76f2b0c1c Patch for objc2's property ASTs, as well as pretty-priting the ASTs. 
llvm-svn: 43778
 2007-11-06 22:01:00 +00:00
Chris Lattner
45d561ad99 improve decl merging logic to be more correct with 
functions.  Patch contributed by Nuno Lopes, thanks!

llvm-svn: 43757
 2007-11-06 06:07:26 +00:00
Chris Lattner
3209725c68 Add better validation for array types when merging decls. Patch 
contributed by Oliver Hunt, thanks!

llvm-svn: 43750
 2007-11-06 04:28:31 +00:00
Fariborz Jahanian
ac73ff8868 Remaining work to collect objective-c's type qualifiers and use them to encode 
method types.

llvm-svn: 43617
 2007-11-01 17:18:37 +00:00
Devang Patel
32714064b1 Propagate bitfield info. 
llvm-svn: 43613
 2007-11-01 16:29:56 +00:00
Fariborz Jahanian
7a9c47480d 1) More additions for objective-c's qualifier type. 
2) Fixed a test failure (which should have failed all along!).

llvm-svn: 43589
 2007-10-31 23:53:01 +00:00
Fariborz Jahanian
95b6076c77 Fixed problem with rewriting stand-alone @implementation (with no matching @interface). 
A new test case added.

llvm-svn: 43568
 2007-10-31 18:48:14 +00:00
Steve Naroff
6d40db0dde Implement a more sensible strategy for ObjC built-in types (addressing a long standing FIXME in Sema::GetObjcIdType()). 
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.

llvm-svn: 43567
 2007-10-31 18:42:27 +00:00
Fariborz Jahanian
d728e949bb After Anders check-in, we can now encode 'Class' type. 
llvm-svn: 43556
 2007-10-31 16:00:13 +00:00
Fariborz Jahanian
ca5338196f Added new type and bitfield fields in some decl types in preparation for objective-c's type qualifiers. 
Added initialization of Class/SEMA types.

llvm-svn: 43534
 2007-10-31 00:12:35 +00:00
Chris Lattner
0b11172e8c minor tweaks 
llvm-svn: 43515
 2007-10-30 20:57:56 +00:00
Fariborz Jahanian
18d7b30241 Revisited my last patch to be able to do encoding of ivar types with 'id'. 
llvm-svn: 43507
 2007-10-30 18:27:03 +00:00
Fariborz Jahanian
509d8d6fc6 Added type encoding for 'id' type. 
llvm-svn: 43504
 2007-10-30 17:06:23 +00:00
Steve Naroff
5448cf6d61 - Add location info to category/protocol AST's 
- Rewrite categories.

llvm-svn: 43501
 2007-10-30 13:30:57 +00:00
Steve Naroff
4cd61acc33 Remove a couple FIXME's for rewriting ObjC interfaces (which are now being rewritten properly). 
llvm-svn: 43494
 2007-10-30 03:43:13 +00:00