added MTWT functions

src/libsyntax/ast_util.rs

@@ -24,6 +24,7 @@ use core::str;
 use core::to_bytes;
 use core::vec;
 
+
 pub fn path_name_i(idents: &[ident], intr: @token::ident_interner) -> ~str {
     // FIXME: Bad copies (#2543 -- same for everything else that says "bad")
     str::connect(idents.map(|i| copy *intr.get(*i)), ~"::")
@@ -587,6 +588,280 @@ pub enum Privacy {
     Public
 }
 
+// HYGIENE FUNCTIONS
+
+/// Construct an identifier with the given repr and an empty context:
+pub fn mk_ident(repr: uint) -> ident { ident {repr: repr, ctxt: 0}}
+
+/// Extend a syntax context with a given mark
+pub fn mk_mark (m:Mrk,ctxt:SyntaxContext,table:&mut SCTable)
+    -> SyntaxContext {
+    idx_push(table,Mark(m,ctxt))
+}
+
+/// Extend a syntax context with a given rename
+pub fn mk_rename (id:ident, to:Name, tail:SyntaxContext, table: &mut SCTable)
+    -> SyntaxContext {
+    idx_push(table,Rename(id,to,tail))
+}
+
+/// Make a fresh syntax context table with EmptyCtxt in slot zero
+pub fn mk_sctable() -> SCTable { ~[EmptyCtxt] }
+
+/// Add a value to the end of a vec, return its index
+fn idx_push<T>(vec: &mut ~[T], +val: T) -> uint {
+    vec.push(val);
+    vec.len() - 1
+}
+
+/// Resolve a syntax object to a name, per MTWT.
+pub fn resolve (id : ident, table : &SCTable) -> Name {
+    match table[id.ctxt] {
+        EmptyCtxt => id.repr,
+        // ignore marks here:
+        Mark(_,subctxt) => resolve (ident{repr:id.repr, ctxt: subctxt},table),
+        // do the rename if necessary:
+        Rename(ident{repr,ctxt},toname,subctxt) => {
+            // this could be cached or computed eagerly:
+            let resolvedfrom = resolve(ident{repr:repr,ctxt:ctxt},table);
+            let resolvedthis = resolve(ident{repr:id.repr,ctxt:subctxt},table);
+            if ((resolvedthis == resolvedfrom)
+                && (marksof (ctxt,resolvedthis,table)
+                    == marksof (subctxt,resolvedthis,table))) {
+                toname
+            } else {
+                resolvedthis
+            }
+        }
+    }
+}
+
+/// Compute the marks associated with a syntax context.
+// it's not clear to me whether it's better to use a [] mutable
+// vector or a cons-list for this.
+pub fn marksof(ctxt: SyntaxContext, stopname: Name, table: &SCTable) -> ~[Mrk] {
+    let mut result = ~[];
+    let mut loopvar = ctxt;
+    loop {
+        match table[loopvar] {
+            EmptyCtxt => {return result;},
+            Mark(mark,tl) => {
+                xorPush(&mut result,mark);
+                loopvar = tl;
+            },
+            Rename(_,name,tl) => {
+                // see MTWT for details on the purpose of the stopname.
+                // short version: it prevents duplication of effort.
+                if (name == stopname) {
+                    return result;
+                } else {
+                    loopvar = tl;
+                }
+            }
+        }
+    }
+}
+
+/// Push a name... unless it matches the one on top, in which
+/// case pop and discard (so two of the same marks cancel)
+pub fn xorPush(marks: &mut ~[uint], mark: uint) {
+    if ((marks.len() > 0) && (getLast(marks) == mark)) {
+        marks.pop();
+    } else {
+        marks.push(mark);
+    }
+}
+
+// get the last element of a mutable array.
+// FIXME #4903: , must be a separate procedure for now.
+pub fn getLast(arr: &~[Mrk]) -> uint {
+    *arr.last()
+}
+
+
+#[cfg(test)]
+mod test {
+    use ast::*;
+    use super::*;
+    use core::io;
+
+    #[test] fn xorpush_test () {
+        let mut s = ~[];
+        xorPush(&mut s,14);
+        assert_eq!(s,~[14]);
+        xorPush(&mut s,14);
+        assert_eq!(s,~[]);
+        xorPush(&mut s,14);
+        assert_eq!(s,~[14]);
+        xorPush(&mut s,15);
+        assert_eq!(s,~[14,15]);
+        xorPush (&mut s,16);
+        assert_eq! (s,~[14,15,16]);
+        xorPush (&mut s,16);
+        assert_eq! (s,~[14,15]);
+        xorPush (&mut s,15);
+        assert_eq! (s,~[14]);
+    }
+
+    // convert a list of uints to an @~[ident]
+    // (ignores the interner completely)
+    fn uints_to_idents (uints: &~[uint]) -> @~[ident] {
+        @uints.map(|u|{ ident {repr:*u, ctxt: empty_ctxt} })
+    }
+
+    fn id (u : uint, s: SyntaxContext) -> ident {
+        ident{repr:u, ctxt: s}
+    }
+
+    // because of the SCTable, I now need a tidy way of
+    // creating syntax objects. Sigh.
+    #[deriving(Eq)]
+    enum TestSC {
+        M(Mrk),
+        R(ident,Name)
+    }
+
+    // unfold a vector of TestSC values into a SCTable,
+    // returning the resulting index
+    fn unfold_test_sc(tscs : ~[TestSC], tail: SyntaxContext, table : &mut SCTable)
+        -> SyntaxContext {
+        tscs.foldr(tail, |tsc : &TestSC,tail : SyntaxContext|
+                  {match *tsc {
+                      M(mrk) => mk_mark(mrk,tail,table),
+                      R(ident,name) => mk_rename(ident,name,tail,table)}})
+    }
+
+    // gather a SyntaxContext back into a vector of TestSCs
+    fn refold_test_sc(mut sc: SyntaxContext, table : &SCTable) -> ~[TestSC] {
+        let mut result = ~[];
+        loop {
+            match table[sc] {
+                EmptyCtxt => {return result;},
+                Mark(mrk,tail) => {
+                    result.push(M(mrk));
+                    sc = tail;
+                    loop;
+                },
+                Rename(id,name,tail) => {
+                    result.push(R(id,name));
+                    sc = tail;
+                    loop;
+                }
+            }
+        }
+    }
+
+    #[test] fn test_unfold_refold(){
+        let mut t = mk_sctable();
+
+        let test_sc = ~[M(3),R(id(101,0),14),M(9)];
+        assert_eq!(unfold_test_sc(test_sc,empty_ctxt,&mut t),3);
+        assert_eq!(t[1],Mark(9,0));
+        assert_eq!(t[2],Rename(id(101,0),14,1));
+        assert_eq!(t[3],Mark(3,2));
+        assert_eq!(refold_test_sc(3,&t),test_sc);
+    }
+
+
+    // extend a syntax context with a sequence of marks given
+    // in a vector. v[0] will be the outermost mark.
+    fn unfold_marks(mrks:~[Mrk],tail:SyntaxContext,table: &mut SCTable) -> SyntaxContext {
+        mrks.foldr(tail, |mrk:&Mrk,tail:SyntaxContext|
+                   {mk_mark(*mrk,tail,table)})
+    }
+
+    #[test] fn unfold_marks_test() {
+        let mut t = ~[EmptyCtxt];
+
+        assert_eq!(unfold_marks(~[3,7],empty_ctxt,&mut t),2);
+        assert_eq!(t[1],Mark(7,0));
+        assert_eq!(t[2],Mark(3,1));
+    }
+
+    #[test] fn test_marksof () {
+        let stopname = 242;
+        let name1 = 243;
+        let mut t = mk_sctable();
+        assert_eq!(marksof (empty_ctxt,stopname,&t),~[]);
+        // FIXME #5074: ANF'd to dodge nested calls
+        { let ans = unfold_marks(~[4,98],empty_ctxt,&mut t);
+         assert_eq! (marksof (ans,stopname,&t),~[4,98]);}
+        // does xoring work?
+        { let ans = unfold_marks(~[5,5,16],empty_ctxt,&mut t);
+         assert_eq! (marksof (ans,stopname,&t), ~[16]);}
+        // does nested xoring work?
+        { let ans = unfold_marks(~[5,10,10,5,16],empty_ctxt,&mut t);
+         assert_eq! (marksof (ans, stopname,&t), ~[16]);}
+        // rename where stop doesn't match:
+        { let chain = ~[M(9),
+                        R(id(name1,
+                             mk_mark (4, empty_ctxt,&mut t)),
+                          100101102),
+                        M(14)];
+         let ans = unfold_test_sc(chain,empty_ctxt,&mut t);
+         assert_eq! (marksof (ans, stopname, &t), ~[9,14]);}
+        // rename where stop does match
+        { let name1sc = mk_mark(4, empty_ctxt, &mut t);
+         let chain = ~[M(9),
+                       R(id(name1, name1sc),
+                         stopname),
+                       M(14)];
+         let ans = unfold_test_sc(chain,empty_ctxt,&mut t);
+         assert_eq! (marksof (ans, stopname, &t), ~[9]); }
+    }
+
+
+    #[test] fn resolve_tests () {
+        let a = 40;
+        let mut t = mk_sctable();
+        // - ctxt is MT
+        assert_eq!(resolve(id(a,empty_ctxt),&t),a);
+        // - simple ignored marks
+        { let sc = unfold_marks(~[1,2,3],empty_ctxt,&mut t);
+         assert_eq!(resolve(id(a,sc),&t),a);}
+        // - orthogonal rename where names don't match
+        { let sc = unfold_test_sc(~[R(id(50,empty_ctxt),51),M(12)],empty_ctxt,&mut t);
+         assert_eq!(resolve(id(a,sc),&t),a);}
+        // - rename where names do match, but marks don't
+        { let sc1 = mk_mark(1,empty_ctxt,&mut t);
+         let sc = unfold_test_sc(~[R(id(a,sc1),50),
+                                   M(1),
+                                   M(2)],
+                                 empty_ctxt,&mut t);
+        assert_eq!(resolve(id(a,sc),&t), a);}
+        // - rename where names and marks match
+        { let sc1 = unfold_test_sc(~[M(1),M(2)],empty_ctxt,&mut t);
+         let sc = unfold_test_sc(~[R(id(a,sc1),50),M(1),M(2)],empty_ctxt,&mut t);
+         assert_eq!(resolve(id(a,sc),&t), 50); }
+        // - rename where names and marks match by literal sharing
+        { let sc1 = unfold_test_sc(~[M(1),M(2)],empty_ctxt,&mut t);
+         let sc = unfold_test_sc(~[R(id(a,sc1),50)],sc1,&mut t);
+         assert_eq!(resolve(id(a,sc),&t), 50); }
+        // - two renames of the same var.. can only happen if you use
+        // local-expand to prevent the inner binding from being renamed
+        // during the rename-pass caused by the first:
+        io::println("about to run bad test");
+        { let sc = unfold_test_sc(~[R(id(a,empty_ctxt),50),
+                                    R(id(a,empty_ctxt),51)],
+                                  empty_ctxt,&mut t);
+         assert_eq!(resolve(id(a,sc),&t), 51); }
+        // the simplest double-rename:
+        { let a_to_a50 = mk_rename(id(a,empty_ctxt),50,empty_ctxt,&mut t);
+         let a50_to_a51 = mk_rename(id(a,a_to_a50),51,a_to_a50,&mut t);
+         assert_eq!(resolve(id(a,a50_to_a51),&t),51);
+         // mark on the outside doesn't stop rename:
+         let sc = mk_mark(9,a50_to_a51,&mut t);
+         assert_eq!(resolve(id(a,sc),&t),51);
+         // but mark on the inside does:
+         let a50_to_a51_b = unfold_test_sc(~[R(id(a,a_to_a50),51),
+                                              M(9)],
+                                           a_to_a50,
+                                           &mut t);
+         assert_eq!(resolve(id(a,a50_to_a51_b),&t),50);}
+    }
+
+}
+
 // Local Variables:
 // mode: rust
 // fill-column: 78;