Commit Graph

4518 Commits

Author SHA1 Message Date
Chris Willmore
cfd450391b Don't mutate defaultArgsOwner with getCallerDefaultArg() directly, so we
can make a more precise assertion that all default arguments have the
same owner.

<rdar://problem/20749423> Compiler crashed while building simple subclass code

Swift SVN r28251
2015-05-07 01:18:24 +00:00
John McCall
36c605f7dc Remove ScalarToTupleExpr in favor of a flag on TupleShuffleExpr.
Also, implement in-place initialization through tuple shuffles.

Swift SVN r28227
2015-05-06 23:44:26 +00:00
Chris Lattner
37f5452d15 require -> guard.
Swift SVN r28223
2015-05-06 22:53:38 +00:00
Doug Gregor
a99e995094 Validate an associated type before looking at its default definition.
No test case; this triggers on Basis and is extremely hard to minimize
outside of a large project. Fixes rdar://problem/20829839.

Swift SVN r28222
2015-05-06 22:52:35 +00:00
Joe Pamer
3b57cabae7 Consider default argument patterns, as they relate to actual arguments, when deciding on a specific overload to favor for a function application. Doing so addresses another class of exponential behavior bugs in the type checker (rdar://problem/19779591 and rdar://problem/20772053). There's still some work left to do, though - hence the change to Concatenate.swift, to work around rdar://problem/20789500.
Swift SVN r28221
2015-05-06 22:32:07 +00:00
Chris Lattner
ea52d4fbc7 fix <rdar://problem/20749592> Conditional Optional binding hides compiler error
Swift SVN r28220
2015-05-06 22:12:34 +00:00
Joe Groff
ab09922966 Runtime/IRGen: Replace the _SwiftNativeNS*Base +load hack with a compiler hack.
Rather than swizzle the superclass of these bridging classes at +load time, have the compiler set their ObjC runtime base classes, using a "@_swift_native_objc_runtime_base" attribute that tells the compiler to use a different implicit base class from SwiftObject. This lets the runtime shed its last lingering +loads, and should overall be more robust, since it doesn't rely on static initialization order or deprecated ObjC runtime calls.

Swift SVN r28219
2015-05-06 22:00:59 +00:00
Chris Willmore
f3670d3a6f When adding '!' in fix-it, make sure that it doesn't fall into the
optional evaluation context that produced the optional.

<rdar://problem/20377684> Oscillating fixit for optional chain calling method that returns non-optional

Swift SVN r28212
2015-05-06 19:05:45 +00:00
Doug Gregor
a924e06025 Don't require 'Self.' within the where clause of a constrained extension.
Within the where clause of a constrained (protocol) extension, allow
us to find associated types of that protocol and anything it inherits
via unqualified lookup, e.g.,

  extension SequenceType where Generator.Element : Equatable { }

rather than

  extension SequenceType where Self.Generator.Element : Equatable { }

Implements rdar://problem/20722467.

Swift SVN r28208
2015-05-06 17:05:28 +00:00
Doug Gregor
83d336e714 Stop using TupleTypeElts in the type checking for arg/param matching.
Instead, use a dedicated struct. NFC

Swift SVN r28207
2015-05-06 17:05:27 +00:00
Chris Willmore
6263024a91 Coerce UnresolvedMemberExpr to its assigned type if it has an argument,
since the type might not match the return type of the function exactly
in that case (CSGen only emits a conversion constraint).

<rdar://problem/20087517> Crash when using .staticShorthand syntax with NSColor/UIColor factories

Swift SVN r28200
2015-05-06 08:25:05 +00:00
Roman Levenstein
984fcef576 Produce an error for generic parameters of functions if those parameters are not used in function signature.
If a generic parameter is not referred to from a function signature, it can never be inferred and thus such a function can never be invoked.

We now produce the following error:

generic parameter 'T' is not used in function signature
func f8<T> (x: Int) {}

This commit takes Jordan't comments on r28181 into account:
- it produces a shorter error message
- it does not change the compiler_crashers_fixed test and add a new expected error instead

Swift SVN r28194
2015-05-06 02:20:39 +00:00
Roman Levenstein
a3a25000ff Revert "Produce an error for generic parameters of functions if those parameters are not used in function signature."
This reverts commit r28181. I'll change it according to Jordan's comments and re-commit.

Swift SVN r28193
2015-05-06 02:20:36 +00:00
Roman Levenstein
ebe3fddbe6 Produce an error for generic parameters of functions if those parameters are not used in function signature.
If a generic parameter is not referred to from a function signature, it can never be inferred and thus such a function can never be invoked.

We now produce the following error:

There is no way to infer the generic parameter 'T' if it is not used in function signature
func f8<T> (x: Int) {}
             ^

Swift SVN r28181
2015-05-05 21:02:11 +00:00
Jordan Rose
88c9ab591f Make sure we validate the synthesized accessors for NSManaged properties.
(as well as those for lazy properties, which seem to be working already)

This fixes a problem with @NSManaged properties being declared in an
extension in a generated file you're not supposed to modify, which
unfortunately is exactly how Xcode's generating them these days.

rdar://problem/20821582

Swift SVN r28180
2015-05-05 20:02:12 +00:00
Jordan Rose
edf1958f86 Sema: ParamDecls never get accessors.
No functionality change; they wouldn't have ever hit either of the cases
later either.

Swift SVN r28179
2015-05-05 20:02:09 +00:00
Doug Gregor
6e114e3cfe Reinstate r26814: Allow 'var' parameters in @objc methods.
'var' parameters affect the definition of the method itself, not its
signature. Fixes rdar://problem/20543054.

Swift SVN r28167
2015-05-05 16:34:09 +00:00
Chris Lattner
90385937f2 remove some dead code, change the text of a theoretically dead diagnostic in case it ever comes up.
Swift SVN r28152
2015-05-05 05:20:40 +00:00
Jordan Rose
841c4c7e63 Be more aggressive about access control consistency when offering warnings.
Otherwise, we'll get assertion failures and verifier errors down the line.

rdar://problem/20689300

Swift SVN r28144
2015-05-05 01:41:10 +00:00
Slava Pestov
43c96de2b0 Sema: slightly better diagnostics for @objc
If we inferred @objc, say so instead of telling the user they
"marked" the declaration @objc.

Swift SVN r28128
2015-05-04 19:26:25 +00:00
Slava Pestov
222781b1f2 Sema: Rename ObjCReason::DontDiagnose => DoNotDiagnose
I'm going to have to side with Ted on this one. NFC

Swift SVN r28127
2015-05-04 19:26:24 +00:00
Slava Pestov
58f0b46335 Implement @nonobjc attribute
The following declaration kinds can be marked with this attribute:
- method
- property
- property accessor
- subscript
- constructor

Use cases include resolving circularity for bridging methods in an @objc
class, and allowing overloading methods and constructors in an @objc class
by signature by marking some of them @nonobjc.

It is an error to override an @objc method with a @nonobjc method. The
converse, where we override a @nonobjc method with a @objc method, is
explicitly supported.

It is also an error to put a @nonobjc attribute on a method which is
inferred as @objc due to being part of an @objc protocol conformance.

Fixes <rdar://problem/16763754>.

Swift SVN r28126
2015-05-04 19:26:23 +00:00
Slava Pestov
12d835c1d1 Sema: clean up @objc attribute handling a bit
There was a fair amount of code duplication in handling the various
places where @objc could either be explictly specified or be inferred;
centralize these in a new shouldMarkAsObjC() function. NFC

Swift SVN r28125
2015-05-04 19:26:21 +00:00
Doug Gregor
11b820dbcc Ban extension of the 'AnyObject' protocol.
AnyObject won't always be a protocol, and it may be de-protocol'ified
well before we get the ability to extend an arbitrary type (if that
ever happens), so ban this for now.

Swift SVN r28120
2015-05-04 16:37:26 +00:00
Chris Lattner
e31b915f54 fix <rdar://problem/20800015> Fix error message for invalid if-let
Emitting an error message about a pattern the user didn't write isn't awesome,
complain about the type requirements of an if/let binding specifically.


Swift SVN r28119
2015-05-04 16:36:13 +00:00
Devin Coughlin
8a28d46be2 Sema: Teach availability checking about require/else.
We now introduce a TypeRefinementContext for the fallthrough branch of a require/else
statement that continues until the end of the BraceStmt that contains the RequireStmt. The
body of  the else is checked in the context that contains the RequireStmt.

This enables availability checking with early return:

require #available(iOS 8.0, *) else { return }

Swift SVN r28113
2015-05-04 05:44:06 +00:00
Joe Groff
e2962ed213 SILGen: Implement recursive local function references.
Instead of immediately creating closures for local function declarations and treating them directly as capturable values, break function captures down and transitively capture the storage necessary to invoke the captured functions. Change the way SILGen emits calls to closures and local functions so that it treats the capture list as the first curry level of an invocation, so that full applications of closure literals or nested functions don't require a partial apply at all. This allows references among local functions with captures to work within the existing confines of partial_apply, and also has the nice benefit that circular references would work without creating reference cycles (though Sema unfortunately rejects them; something we arguably ought to fix.)

This fixes rdar://problem/11266246 and improves codegen of local functions. Full applications of functions, or immediate applications of closure literals like { }(), now never need to allocate a closure.

Swift SVN r28112
2015-05-04 05:33:55 +00:00
Chris Lattner
7927a230ae remove compiler support for let/else. This simplifies PBD back to being
an unconditional binding, yay.


Swift SVN r28101
2015-05-03 22:13:02 +00:00
Devin Coughlin
d04cc58c6c Sema: Refine availability context in IfStmt guard conditions following #available()
Loosen restrictions on where #available() can appear in IfStmt guards and refine the
context for guard StmtConditionElements following an availability check.

This enables #available() to be combined with if let optional binding:

if #available(iOS 8.0, *),
   let x = someIOS8API() {
  // Do more iOS 8 stuff
}

and

if let x = someIOS7API() where #available(iOS 8.0, *),
   let y = someIOS8API() {
  // Do more iOS 8 stuff
}

Swift SVN r28096
2015-05-03 20:27:29 +00:00
John McCall
204bb04f04 In closure 'throws' inference, infer 'throw' as throwing.
Also, walk into 'do' bodies when the catches aren't
exhaustive, but don't walk into try! operands.

Swift SVN r28092
2015-05-02 19:50:21 +00:00
Joe Groff
d0473756ec ClangImporter etc.: Remap C vector types to nested BaseType.VectorN types.
The design we landed on for SIMD is to define the vector types as nested types of their element, e.g. Float.Vector4, Int32.Vector2, etc. Update the Clang importer and other mapping facilities to match.

Swift SVN r28087
2015-05-02 15:04:43 +00:00
John McCall
5c171fd448 Parsing, type-checking, SILGen, and IRGen for try!.
Swift SVN r28085
2015-05-02 08:03:15 +00:00
John McCall
9065880e5a When an error import would conflict with another method,
preserve the original method name.

This heuristic is based on the Objective-C selector and therefore
doesn't really handle factory methods that would conflict with
initializers, but we can hope that those simply don't come up in
the wild.

It's not clear that this is the best thing to do --- it tends to
promote the non-throwing API over what's probably a newer, throwing
API --- but it's significantly easier, and it unblocks code without
creating deployment problems.

Swift SVN r28066
2015-05-02 01:52:37 +00:00
Chris Lattner
0011b3ae21 rename "unless" to "require" and give it an 'else' keyword.
Swift SVN r28059
2015-05-02 00:16:44 +00:00
Chris Lattner
d5073d9e4f rework StmtCondition to be based on patterns initializers and boolean
conditions instead of being wrapped around PatternBindingDecl.  When
let/else goes away, PatternBindingDecl will become a lot simpler.


Swift SVN r28055
2015-05-01 23:33:59 +00:00
Joe Groff
fbd76737a4 Clang Importer: Rename the special vector type module to "simd".
We want this to act as an overlay/replacement for the C "simd" module.

Swift SVN r28047
2015-05-01 20:11:01 +00:00
Chris Lattner
82b190c1a6 refactor type checking of initializers in PBDs a bit, this exposes
functionality better and silences a few follow-on errors by applying ErrorType
to decls more consistently.


Swift SVN r28045
2015-05-01 19:11:18 +00:00
Chris Willmore
331b570329 Remove reverse subtype constraint between Objective-C classes when type
checking checked cast via bridging. It prevented bridging upcasts using
'as!' from typechecking; we should emit an 'as!'->'as' warning instead.

Also, use ExplicitConversion constraint instead of Conversion when
determining whether a checked cast can be carried out unconditionally.
This matches the constraint used after applying the 'as!'->'as' fixit.

(Also, fix the error that was responsible for breaking
the expr/cast/bridged.swift test.)

<rdar://problem/19813772>

Swift SVN r28034
2015-05-01 08:27:19 +00:00
Ted Kremenek
acf0c496e2 Revert "Remove reverse subtype constraint between Objective-C classes when type"
This is breaking TEST 'Swift :: expr/cast/bridged.swift'.

Swift SVN r28030
2015-05-01 06:37:59 +00:00
Chris Willmore
7d413057aa Remove reverse subtype constraint between Objective-C classes when type
checking checked cast via bridging. It prevented bridging upcasts using
'as!' from typechecking; we should emit an 'as!'->'as' warning instead.

Also, use ExplicitConversion constraint instead of Conversion when
determining whether a checked cast can be carried out unconditionally.
This matches the constraint used after applying the 'as!'->'as' fixit.

<rdar://problem/19813772>

Swift SVN r28028
2015-05-01 06:21:50 +00:00
Doug Gregor
5cfe5b3383 Diagnose attempts to extend a protocol via a typealias.
Fixes rdar://problem/20756244.

Swift SVN r28026
2015-05-01 05:34:29 +00:00
Devin Coughlin
37088d4fb9 Parse: Update parsing of #available(...) to no longer user >= version comparison
Change the syntax of availability queries from #available(iOS >= 8.0, OSX >= 10.10, *) to

This change reflects the fact that now that we spell the query '#available()' rather than
'#os()', the specification is about availability of the APIs introduced in a particular OS
release rather than an explicit range of OS versions on which the developer expects the
code to run.

There is a Fix-It to remove '>=' to ease adopting the new syntax.

Swift SVN r28025
2015-05-01 05:34:10 +00:00
Doug Gregor
de635a8cd9 Implement the 'warn_unused_result' attribute.
@warn_unused_result can be attached to function declarations to
produce a warning if the function is called but its result is not
used. It has two optional parameters that can be placed in
parentheses:

  message="some message": a message to include with the warning.

  mutable_variant="somedecl": the name of the mutable variant of the
  method that should be suggested when the subject method is called on
  a mutable value.

The specific use we're implementing this for now is for the mutating
and in-place operations. For example:

  @warn_unused_result(mutable_variant="sortInPlace") func sort() -> [Generator.Element] { ... }
  mutating func sortInPlace() { ... }

Translate Clang's __attribute__((warn_unused_result)) into
@warn_unused_result.

Implements rdar://problem/18165189.

Swift SVN r28019
2015-05-01 04:10:40 +00:00
Chris Lattner
2ffb5bb23c diagnose always-true conditions.
Swift SVN r28017
2015-05-01 03:55:08 +00:00
Doug Gregor
f9b09aa9c5 Eliminate uses of getProtocols() from declaration checking. NFC
Swift SVN r27978
2015-04-30 16:13:44 +00:00
Doug Gregor
cf1bb3a8ce Remove the old "delayed protocol conformances" code.
It's in the way of progress; a better solution is coming.

Swift SVN r27970
2015-04-30 16:13:39 +00:00
Chris Lattner
c6aa041fb9 Add parser/ast/sema/sourcekit/etc support for 'unless' statement.
SILGen support still missing.



Swift SVN r27961
2015-04-30 05:55:11 +00:00
Chris Lattner
31c01eab73 Change the meaning of "if let x = foo()" back to Xcode 6.4 semantics. The compiler
includes a number of QoI things to help people write the correct code.  I will commit
the testcase for it as the next patch.

The bulk of this patch is moving the stdlib, testsuite and validation testsuite to
the new syntax.  I moved a few uses of "as" patterns back to as? expressions in the 
stdlib as well.



Swift SVN r27959
2015-04-30 04:38:13 +00:00
Chris Willmore
c7a0963d60 Add --enable-throw-without-try option to suppress warning about missing 'try'.
To be used by the debugger so expression parsing doesn't require 'try'
everywhere. <rdar://problem/20356764>

Swift SVN r27949
2015-04-29 23:51:40 +00:00
Doug Gregor
a815ab7386 Don't eagerly check protocol conformances for Clang-imported AST nodes.
The Clang importer introduces a number of synthesized conformances for
imported enums (normal, NS_ENUMS, or NS_OPTIONS-based all have the
same issue) that aren't used in most translation units. Rather than go
through the effort of fully checking these conformances and generating
SIL for them always, rely on semantic analysis to force them to be
fully checked when the conformance is required. This cuts down on the
amount of work we need to do for imported enumeration types
considerably. For a simple program consisting of only:

    import Foundation
    var str = NSString()

My not-entirely-scientific measurements show that:
  * Time to parse + type-check is reduced by 34%
  * Time to generate SIL is reduced by 50%
  * Time to generate IR is reduced by 47%
  * SIL output size is reduced by 66%

Fixes rdar://problem/20047340.

Swift SVN r27946
2015-04-29 23:20:54 +00:00