auto merge of #6559 : jbclements/rust/hygiene-fns-and-cleanup, r=jbcl…

…ements

This includes new, tested, hygiene support functions. It also removes the interner_key! macro and replaces it with a function, which should be inline-able. It also contains some parser patch-ups and some docfixes.

On my machine, this patch passes all tests.

doc/rust.md

@@ -2250,6 +2250,14 @@ do_expr : "do" expr [ '|' ident_list '|' ] ? '{' block '}' ;
 A _do expression_ provides a more-familiar block-syntax for a [lambda expression](#lambda-expressions),
 including a special translation of [return expressions](#return-expressions) inside the supplied block.
 
+Any occurrence of a [return expression](#return-expressions)
+inside this `block` expression is rewritten
+as a reference to an (anonymous) flag set in the caller's environment,
+which is checked on return from the `expr` and, if set,
+causes a corresponding return from the caller.
+In this way, the meaning of `return` statements in language built-in control blocks is preserved,
+if they are rewritten using lambda functions and `do` expressions as abstractions.
+
 The optional `ident_list` and `block` provided in a `do` expression are parsed as though they constitute a lambda expression;
 if the `ident_list` is missing, an empty `ident_list` is implied.
 
@@ -2296,19 +2304,15 @@ A _for expression_ is similar to a [`do` expression](#do-expressions),
 in that it provides a special block-form of lambda expression,
 suited to passing the `block` function to a higher-order function implementing a loop.
 
-Like a `do` expression, a `return` expression inside a `for` expresison is rewritten,
-to access a local flag that causes an early return in the caller.
-
-Additionally, any occurrence of a [return expression](#return-expressions)
-inside the `block` of a `for` expression is rewritten
-as a reference to an (anonymous) flag set in the caller's environment,
-which is checked on return from the `expr` and, if set,
-causes a corresponding return from the caller.
-In this way, the meaning of `return` statements in language built-in control blocks is preserved,
-if they are rewritten using lambda functions and `do` expressions as abstractions.
+In contrast to a `do` expression, a `for` expression is designed to work
+with methods such as `each` and `times`, that require the body block to
+return a boolean. The `for` expression accommodates this by implicitly
+returning `true` at the end of each block, unless a `break` expression
+is evaluated.
 
-Like `return` expressions, any [`break`](#break-expressions) and [`loop`](#loop-expressions) expressions
-are rewritten inside `for` expressions, with a combination of local flag variables,
+In addition, [`break`](#break-expressions) and [`loop`](#loop-expressions) expressions
+are rewritten inside `for` expressions in the same way that `return` expressions are,
+with a combination of local flag variables,
 and early boolean-valued returns from the `block` function,
 such that the meaning of `break` and `loop` is preserved in a primitive loop
 when rewritten as a `for` loop controlled by a higher order function.

src/librustdoc/extract.rs

@@ -17,24 +17,18 @@ use doc;
 use core::local_data::local_data_get;
 use syntax::ast;
 use syntax;
-
-/* can't import macros yet, so this is copied from token.rs. See its comment
- * there. */
-macro_rules! interner_key (
-    () => (cast::transmute::<(uint, uint),
-           &fn(v: @@syntax::parse::token::ident_interner)>((-3 as uint, 0u)))
-)
+use syntax::parse::token::{ident_interner};
+use syntax::parse::token;
 
 // Hack; rather than thread an interner through everywhere, rely on
 // thread-local data
 pub fn to_str(id: ast::ident) -> ~str {
-    let intr = unsafe{ local_data_get(interner_key!()) };
-
-    return copy *(*intr.get()).get(id);
+    let intr = token::get_ident_interner();
+    return copy *(*intr).get(id);
 }
 
-pub fn interner() -> @syntax::parse::token::ident_interner {
-    return *(unsafe{ local_data_get(interner_key!()) }).get();
+pub fn interner() -> @ident_interner {
+    return token::get_ident_interner();
 }
 
 pub fn from_srv(

src/libsyntax/ast.rs

@@ -13,12 +13,14 @@
 use codemap::{span, spanned};
 use abi::AbiSet;
 use opt_vec::OptVec;
+use parse::token::get_ident_interner;
 
 use core::cast;
-use core::option::{None, Option, Some};
+use core::option::{Option};
 use core::to_bytes;
 use core::to_bytes::IterBytes;
 use core::to_str::ToStr;
+use core::hashmap::HashMap;
 use std::serialize::{Encodable, Decodable, Encoder, Decoder};
 
 
@@ -38,14 +40,20 @@ pub struct ident { repr: Name, ctxt: SyntaxContext }
 // that's causing unreleased memory to cause core dumps
 // and also perhaps to save some work in destructor checks.
 // the special uint '0' will be used to indicate an empty
-// syntax context
+// syntax context.
 
 // this uint is a reference to a table stored in thread-local
 // storage.
 pub type SyntaxContext = uint;
 
-pub type SCTable = ~[SyntaxContext_];
+pub struct SCTable {
+    table : ~[SyntaxContext_],
+    mark_memo : HashMap<(SyntaxContext,Mrk),SyntaxContext>,
+    rename_memo : HashMap<(SyntaxContext,ident,Name),SyntaxContext>
+}
+// NB: these must be placed in any SCTable...
 pub static empty_ctxt : uint = 0;
+pub static illegal_ctxt : uint = 1;
 
 #[deriving(Eq, Encodable, Decodable)]
 pub enum SyntaxContext_ {
@@ -59,7 +67,8 @@ pub enum SyntaxContext_ {
     // "to" slot must have the same name and context
     // in the "from" slot. In essence, they're all
     // pointers to a single "rename" event node.
-    Rename (ident,Name,SyntaxContext)
+    Rename (ident,Name,SyntaxContext),
+    IllegalCtxt()
 }
 
 // a name represents an identifier
@@ -70,27 +79,14 @@ pub type Mrk = uint;
 
 impl<S:Encoder> Encodable<S> for ident {
     fn encode(&self, s: &mut S) {
-        unsafe {
-            let intr =
-                match local_data::local_data_get(interner_key!()) {
-                    None => fail!("encode: TLS interner not set up"),
-                    Some(intr) => intr
-                };
-
-            s.emit_str(*(*intr).get(*self));
-        }
+        let intr = get_ident_interner();
+        s.emit_str(*(*intr).get(*self));
     }
 }
 
 impl<D:Decoder> Decodable<D> for ident {
     fn decode(d: &mut D) -> ident {
-        let intr = match unsafe {
-            local_data::local_data_get(interner_key!())
-        } {
-            None => fail!("decode: TLS interner not set up"),
-            Some(intr) => intr
-        };
-
+        let intr = get_ident_interner();
         (*intr).intern(d.read_str())
     }
 }