Commit Graph

737 Commits

Author SHA1 Message Date
Joe Pamer
1e5b9116d4 More array casting work:
- Continue adding support for checked downcasts of array types (rdar://problem/16535104)
- Fix non-bridged array conversions post-r17868
- Fix rdar://problem/16773693
- Add tests for NSArray coercions to and from Array<T>

Swift SVN r17957
2014-05-12 20:49:42 +00:00
Chris Lattner
c5d96a97a2 fix multi-stmt closures, whose bodies may not be typechecked yet.
Swift SVN r17918
2014-05-12 03:00:37 +00:00
Chris Lattner
c18c93b0c5 remove semicolons from a comment. NFC
Swift SVN r17901
2014-05-12 00:17:39 +00:00
Chris Lattner
2426134853 improve hte AST representation of capture lists to build VarDecls and
PatternBindingDecls, and inject the vardecls into the name resolution
scope while parsing the body of the closure.  This allows references
from the body of the closure to be resolved to the capture list,
e.g. in cases like the testcase.


Swift SVN r17760
2014-05-09 05:39:28 +00:00
Joe Pamer
2eedc06d66 Begin adding plumbing for the type checker to accept "forward" bridged array conversions. (rdar://problem/16540403)
Swift SVN r17640
2014-05-07 19:45:37 +00:00
Joe Pamer
d22ffa8cb8 Re-lazify the addition of equatable conformances to imported enum types. (rdar://problem/16808612)
Rather than force conformances to Equatable to be added to all imported enumeration types outright, change them back to being lazily added. We can then handle situations where new overloads of '==' are introduced during constraint generation by re-writing the relevant overload disjunction constraint to include the newly forced declarations as bind options.

Swift SVN r17557
2014-05-06 19:56:29 +00:00
Chris Lattner
fcb3b0e98c Rework capture list parsing and generalize it. Now the preparse is
much fuzzier, and the real parse is stricter.  Also, generalize this
to support the full "unowned name = expr" syntax in the capture list.

There is still a lot missing here.



Swift SVN r17499
2014-05-05 23:53:53 +00:00
Chris Lattner
d230228cdd store the capture list of a ClosureExpr in the AST and print it out
in the AST dumper.


Swift SVN r17451
2014-05-05 16:25:33 +00:00
Chris Lattner
1262105e61 Start parsing capture lists in closure expressions. Still much work
to go.



Swift SVN r17367
2014-05-04 05:39:22 +00:00
Doug Gregor
9cfb1b5ca4 Keep track of the locations of the element names in a TupleExpr.
As part of this, use tail allocation to reduce the memory footprint of
TupleExprs. Use factory methods to make it easier to construct.

I'll be using this information in a follow-on patch. SourceKit
probably wants it as well.


Swift SVN r17129
2014-05-01 00:16:36 +00:00
Dmitri Hrybenko
669f633070 Add "single extended grapheme cluster" literals (SEGCL) -- a subset of
double-quoted string literals that contain a single extended grapheme cluster

SEGCL by default infer type String, but you can ask to infer Character
for them.

Single quoted literals continue to infer Character.

Actual extended grapheme cluster segmentation is not implemented yet,
<rdar://problem/16755123> Implement extended grapheme cluster
segmentation in libSwiftBasic

This is part of
<rdar://problem/16363872> Remove single quoted characters

Swift SVN r17034
2014-04-29 14:08:16 +00:00
Chris Lattner
db876399ad create a helper function for creating a TypeExpr from a
specialized declref, factoring some code.  NFC


Swift SVN r17021
2014-04-29 05:33:32 +00:00
Chris Lattner
30915de98f Form TypeExprs for non-specialized unqualified declrefs that refer to types... like "Int".
Building on previous work, this allows us to properly handle things like Int?() and Int[]().

Of course doing this exposed that TypeExpr was not correct in lots of ways, so this also:
 - Revamps TypeExpr processing to carry a decl in the TypeLoc instead of 
   carrying a Type.  This allows us to correctly handle more complex generics case.  
 - Enhances CSGen to properly open generic types so we can infer generic type parameters from
   context.


Swift SVN r17019
2014-04-29 05:25:21 +00:00
Chris Lattner
53a8a06b9d ongoing progress on TypeExpr rollout, this makes it handle existential metatypes
better and cleans up some interfaces.  They aren't used enough to make much of a
difference yet.



Swift SVN r16957
2014-04-28 02:22:25 +00:00
Joe Pamer
86b79d6bd3 Some code cleanup for array upcast conversions. (Part 2 of the fix for rdar://problem/16540403)
Swift SVN r16837
2014-04-25 19:52:06 +00:00
Joe Pamer
066f5e6da5 Allow for simple upcast conversions between array types. (Part 1 of the fix for rdar://problem/16540403)
Swift SVN r16836
2014-04-25 19:52:05 +00:00
Joe Groff
8f51b0e738 Revert "wip"
This reverts commit r16662. Fat fingers.

Swift SVN r16663
2014-04-22 21:50:52 +00:00
Joe Groff
4a81e48ef8 wip
Swift SVN r16662
2014-04-22 21:46:36 +00:00
Chris Lattner
78e8d3f0a9 rename the MetatypeExpr AST node to DynamicTypeExpr now that it is only
used by the "foo.dynamicType" syntax.


Swift SVN r16658
2014-04-22 20:10:11 +00:00
Chris Lattner
7de9c0802a Peel off almost all of the uses of MetaTypeExpr, replacing
them with uses of TypeExpr instead.  The remaining uses of 
MetaTypeExpr (which will be renamed soon) are places where we
are applying the ".dynamicType" virtual property to an expression.

Unadorned uses of types in code, e.g. the Int in "Int.self" are
now represented with TypeExpr.

One unfortunate travesty that doing this work revealed is that we
are extremely sloppy and terrible about maintaining location information
in implicitly generated decls, and our invariants vary quite a bit.  This
is really horrible, but I'm not sure whether I'll go fix the hacks or not.

This patch perpetuates the existing crimes, but makes them more visible.

NFC!




Swift SVN r16646
2014-04-22 05:15:44 +00:00
Chris Lattner
7f3d88632d Introduce a new AST node, named TypeExpr, which will be formed by sema
when resolving identifiers into types.  This will eventually allow us to
solve annoying issues like rdar://15295763&15588967 by better modeling
what we already have.


Swift SVN r16620
2014-04-21 16:10:11 +00:00
Chris Lattner
d21157fa9b implement support for @NSCopying on optional and unchecked optional types.
Swift SVN r16544
2014-04-18 20:15:30 +00:00
John McCall
9000278dcd Introduce MetatypeErasureExpr for erasing metatype
values into existential metatypes.  Erase thin metatypes
correctly in SILGen.

rdar://16610078

Swift SVN r16477
2014-04-17 22:31:47 +00:00
Chris Lattner
f2ddc52dcd Generalize UnresolvedDeclRefExpr and ForceValueExpr to work as implicit expressions, NFC.
Swift SVN r16343
2014-04-14 23:58:28 +00:00
Joe Groff
3bad92b342 AST: Remove the stopgap BridgeToBlockExpr and handle block <-> non-block conversions freely as function conversions.
Teach SILGen to handle function representation changes as part of function conversion instead of needing to be spoonfed a special expr for the purpose. Handle representation changes in both directions to and from blocks using the same logic as the bridging conversions.

Swift SVN r16318
2014-04-14 15:00:34 +00:00
Joe Groff
8f1c2d1e79 Sema: Implement type-checking for inout writeback conversion.
Add a third branch to the constraint system for '&x' expressions that allows conversion from an lvalue to a type via an additional writeback step:

- Add an LValueConversionExpr node that converts from @lvalue T to @lvalue U, given a pair of functions that convert T -> U and U -> T, to represent the writeback temporary.
- Allow conversion in an inout expression from @lvalue T to a type U that has the following members:

  static func __writeback_conversion(Builtin.RawPointer, T.Type) -> U
  static func __writeback_conversion_get(T) -> V
  static func __writeback_conversion_set(V) -> T

which builds a solution that produces an LValueConversion from the get/set pair before passing the pointer to the writeback temporary off to the conversion function.

Swift SVN r15764
2014-04-02 00:17:51 +00:00
Doug Gregor
9189145cc5 Change DeclName over to basename(arg1:arg2:...argN:).
Swift will use the basename + argument names formulation for
names. Update the DeclName interfaces, printing, and __FUNCTION__ to
use the method syntax.

We'll still need to rework the "x.foo:bar:wibble:" syntax; that will
come (significantly) later.

Swift SVN r15763
2014-04-02 00:00:03 +00:00
Joe Groff
b3e9a17269 SILGen: Implement inout address conversion.
Implement lowering for the LValueToPointer and InOutConversion expressions. For the former, we emit the lvalue, then convert it to a RawPointer; for the latter, we introduce an InOutConversion scope, which suppresses any nested writeback conversion scopes.

This completes the implementation of inout address conversion, except that we don't implement reabstraction of the lvalue prior to taking its address. Simply report them unimplemented for now, since reabstraction should not come up for our immediate use case with C types.

Swift SVN r15595
2014-03-29 02:50:26 +00:00
Joe Groff
46f77c6181 Sema: Build the AST for inout address conversions.
Add two new AST node types:

- InOutConversionExpr, which represents an '&x' expression that involves inout conversion. This will be a signal to SILGen not to introduce a writeback scope for the nested conversion call.

- LValueToPointerExpr, which represents the primitive '@lvalue T' to 'RawPointer' conversion that produces the argument to the inout conversion.

Build an InOutConversionExpr AST when an inout expression is resolved by a conversion to an BuiltinInOutAddressConvertible type.

Swift SVN r15594
2014-03-29 02:50:25 +00:00
Joe Groff
45eadd1d9b Rename AddressOfExpr to InOutExpr.
The "address" is an implementation detail; formally, it turns an lvalue into an inout parameter.

Swift SVN r15458
2014-03-25 16:28:28 +00:00
Joe Groff
d75eeb61d5 Parser: Accept 'x as T!' as a synonym for '(x as T)!'.
Look for a postfix '!' after an 'as' production, and if we see it, carry it along in the CheckedCastExpr so we can wrap the cast in a ForceValueExpr once sequence folding resolves the LHS of the cast. Implements part of <rdar://problem/15640006>.

Swift SVN r15307
2014-03-21 00:18:26 +00:00
Joe Groff
b3e337a3dc Push the CheckedCastExpr kind into ExprBits.
NFC, just a small memory optimization.

Swift SVN r15277
2014-03-20 19:11:26 +00:00
John McCall
c40a2e54b2 Extract a method to print a CheckedCastKind and dump
it on CheckedCastExprs.

Swift SVN r15245
2014-03-19 20:25:09 +00:00
John McCall
486463a398 Track the depth of a BindOptionalExpr.
Swift SVN r15210
2014-03-18 22:57:34 +00:00
Chris Lattner
88f5d92429 add a long-overdue TupleExpr convenience ctor that produces "()".
Swift SVN r15019
2014-03-14 00:37:14 +00:00
Joe Groff
1585b625f9 Sema: Wire up compound name lookup to UnresolvedSelectorExpr.
Resolve selector references using compound name lookup, pushing DeclNames a bit deeper through the type-checker and diagnostics as necessary.

Swift SVN r14791
2014-03-07 20:52:30 +00:00
Joe Groff
9e5bc637ae Add __FUNCTION__ as a magic literal identifier.
Add __FUNCTION__ to the repertoire of magic source-location-identifying tokens. Inside a function, it gives the function name; inside a property accessor, it gives the property name; inside special members like 'init', 'subscript', and 'deinit', it gives the keyword name, and at top level, it gives the module name. As a bit of future-proofing, stringify the full DeclName, even though we only ever give declarations simple names currently.

Swift SVN r14710
2014-03-06 01:06:06 +00:00
Chris Lattner
9c5dfd61df change PreCheckExpression to keep track of the current DeclContext when it is
recursing down through ClosureExprs.  This makes sure that it performs name
lookups with the right context.  Add some assertions to make sure that it is
getting the right thing.

This exposed that PatternBinding initializer lookups were passing the wrong
declcontext: the context of the PBD, not the initializer itself.  Fixing this
allows us to correctly reject some cases that passed through before.


Swift SVN r14670
2014-03-05 02:16:07 +00:00
Chris Lattner
d758e0dfe3 Eliminate more "DynamicLookup" in favor of "AnyObject", this is the
bulk of finishing rdar://13327098.


Swift SVN r14653
2014-03-04 22:15:46 +00:00
Chris Lattner
e7fc6db069 When getting the metatype of an archetype or existential, we don't need to materialize
a +1 value.  Instead, just take the +0 value that is often sitting around, ready to be
accessed directly.



Swift SVN r14587
2014-03-03 07:30:28 +00:00
Doug Gregor
8f64658fc1 Misc. cleanups related to SuperRefExpr queries.
Swift SVN r14558
2014-03-01 18:54:34 +00:00
Joe Groff
363a324984 Parse: Start parsing selector member references.
Parse 'x.y:z:' for at least two selector pieces as an UnresolvedSelectorExpr, and declare it unimplemented in Sema.

Swift SVN r14492
2014-02-28 01:47:32 +00:00
Joe Pamer
c9bd295533 When contextualizing closure expressions wrapped in auto closures, ensure that the inner closure's parent context is properly adjusted to reflect the auto closure's newly adjusted parent context.
Swift SVN r14482
2014-02-27 22:29:35 +00:00
Joe Groff
4e87971d81 Disallow bare type references.
Diagnose a metatype reference that doesn't appear as part of a call or member reference, offering fixits to either default-construct the type or get at the metatype explicitly using '.self'. Also diagnose an attempt to refer to 'T.type' by fixiting it to '.self'.

Swift SVN r14433
2014-02-27 00:22:02 +00:00
Joe Groff
c0d8ae7c13 Parse 'x.self' as an identity expression.
Factor an IdentityExpr base class out of ParenExpr, and migrate most of the logic to see through ParenExprs to see through IdentityExprs instead. Add DotSelfExpr as a new subclass of IdentityExpr, produced by parsing 'x.self'.

Swift SVN r14381
2014-02-26 06:23:55 +00:00
Doug Gregor
0bde325327 Collapse 'DynamicSelf' into 'Self'.
Swift SVN r14377
2014-02-26 05:04:05 +00:00
Chris Lattner
3392c4e8ab remove ArchetypeSubscriptExpr, since it is dead now.
Swift SVN r14284
2014-02-23 08:04:51 +00:00
Chris Lattner
30f4b1ba4a remove the unused ArchetypeMemberRefExpr and ExistentialMemberRefExpr nodes.
Swift SVN r14274
2014-02-22 22:09:38 +00:00
Dmitri Hrybenko
3da05e347d Change property accessor syntax to include braces
See release notes update for details.

rdar://15966905


Swift SVN r14271
2014-02-22 21:00:56 +00:00
Chris Lattner
380e44c615 remove ExistentialSubscriptExpr. We don't need specialized forms of
subscriptexpr for various base types, for the same reason we don't need
multiple different kinds of MemberRefExpr.


Swift SVN r14268
2014-02-22 20:18:02 +00:00