all the work trying to write a validator

assets/test_prelude.ld

@@ -0,0 +1,5 @@
+base :print! ("Hello from Prelude")
+
+fn add (x, y) -> base :add (x, y)
+
+#{add}

src/context.rs

@@ -6,17 +6,6 @@ use imbl::Vector;
 use std::cell::RefCell;
 use std::rc::Rc;
 
-pub fn match_eq<T, U>(x: T, y: T, z: U) -> Option<U>
-where
-    T: PartialEq,
-{
-    if x == y {
-        Some(z)
-    } else {
-        None
-    }
-}
-
 pub struct LErr {
     pub msg: String,
     pub trace: Vec<String>,
@@ -41,7 +30,7 @@ type LResult<'src> = Result<Value<'src>, LErr>;
 pub struct Context<'src> {
     pub locals: Vec<(String, Value<'src>)>,
     pub prelude: Vec<(String, Value<'src>)>,
-    pub prelude_ast: &'src Ast,
+    // pub prelude_ast: &'src Ast,
     pub ast: &'src Ast,
 }
 
@@ -76,7 +65,7 @@ impl<'src> Context<'src> {
         T: PartialEq,
     {
         if x == y {
-            Some(&self)
+            Some(self)
         } else {
             None
         }

src/main.rs

@@ -50,12 +50,12 @@ use crate::value::*;
 mod parser;
 use crate::parser::*;
 
-// mod vm;
-// use crate::vm::*;
-
 mod base;
 use crate::base::*;
 
+mod validator;
+use crate::validator::*;
+
 mod context;
 use crate::context::*;
 
@@ -64,7 +64,7 @@ use crate::context::*;
 struct Asset;
 
 pub fn prelude<'src>() -> Context<'src> {
-    let prelude = Asset::get("prelude.ld").unwrap().data.into_owned();
+    let prelude = Asset::get("test_prelude.ld").unwrap().data.into_owned();
     // we know for sure Prelude should live through the whole run of the program
     let leaked = Box::leak(Box::new(prelude));
     let prelude = std::str::from_utf8(leaked).unwrap();
@@ -94,7 +94,7 @@ pub fn prelude<'src>() -> Context<'src> {
         locals: vec![],
         ast: p_ast,
         prelude: base_pkg,
-        prelude_ast: &Ast::Nil,
+        // prelude_ast: &Ast::Nil,
     };
 
     let prelude = base_ctx.eval();
@@ -122,7 +122,7 @@ pub fn prelude<'src>() -> Context<'src> {
         locals: vec![],
         ast: &Ast::Nil,
         prelude: p_ctx,
-        prelude_ast: p_ast,
+        // prelude_ast: p_ast,
     }
 }
 
@@ -158,16 +158,7 @@ pub fn run(src: &'static str) {
 
 pub fn main() {
     let src = "
-fn fib {
+add (1, 2)
-    (1) -> 1
-    (2) -> 1
-    (n) -> add (
-        fib (dec (n))
-        fib (sub (n, 2))
-    )
-}
-
-fib (25)
     ";
     run(src);
     // struct_scalpel::print_dissection_info::<value::Value>()

src/validator.rs

@@ -0,0 +1,377 @@
+use crate::parser::*;
+use crate::spans::Span;
+use std::collections::{HashMap, HashSet};
+
+#[derive(Clone, Debug, PartialEq)]
+pub struct VErr {
+    msg: String,
+    span: Span,
+}
+
+impl VErr {
+    pub fn new(msg: String, span: Span) -> VErr {
+        VErr { msg, span }
+    }
+}
+
+#[derive(Clone, Debug, PartialEq)]
+struct VStatus {
+    tail_position: bool,
+    in_loop: bool,
+    last_term: bool,
+    has_placeholder: bool,
+    used_bindings: Vec<String>,
+}
+
+#[derive(Clone, Debug, PartialEq, Eq, Hash)]
+pub enum Arity {
+    Fixed(u8),
+    Splat(u8),
+}
+
+#[derive(Clone, Debug, PartialEq, Eq)]
+pub enum FnInfo {
+    Declared,
+    Defined(HashSet<Arity>, HashSet<String>),
+    Unknown,
+}
+
+#[derive(Debug, PartialEq)]
+pub struct Validator<'a> {
+    // TODO: add another term here: FnStatus. See Issue #18.
+    pub locals: Vec<(String, Span, FnInfo)>,
+    pub prelude: &'a Vec<String>,
+    pub ast: &'a Ast,
+    pub span: Span,
+    pub errors: Vec<VErr>,
+    pub fn_info: HashMap<*const Ast, FnInfo>,
+    status: VStatus,
+}
+
+impl<'a> Validator<'a> {
+    fn new(ast: &'a mut Ast, span: Span, prelude: &'a Vec<String>) -> Validator<'a> {
+        Validator {
+            locals: vec![],
+            prelude,
+            ast,
+            span,
+            fn_info: std::collections::HashMap::new(),
+            errors: vec![],
+            status: VStatus {
+                tail_position: false,
+                in_loop: false,
+                last_term: false,
+                has_placeholder: false,
+                used_bindings: vec![],
+            },
+        }
+    }
+
+    fn bind(&mut self, name: String) {
+        self.locals.push((name, self.span, FnInfo::Unknown));
+    }
+
+    fn declare_fn(&mut self, name: String) {
+        self.locals.push((name, self.span, FnInfo::Declared));
+    }
+
+    fn define_fn(&mut self, name: String, info: FnInfo) {
+        self.locals.push((name, self.span, info));
+    }
+
+    fn resolved(&self, name: &str) -> bool {
+        self.locals.iter().any(|(bound, ..)| name == bound.as_str())
+            || self.prelude.iter().any(|bound| name == bound.as_str())
+    }
+
+    fn bound(&self, name: &str) -> Option<&(String, Span, FnInfo)> {
+        match self.locals.iter().rev().find(|(bound, ..)| name == bound) {
+            Some(binding) => Some(binding),
+            None => None,
+        }
+    }
+
+    fn err(&mut self, msg: String) {
+        self.errors.push(VErr::new(msg, self.span))
+    }
+
+    fn use_name(&mut self, name: String) {
+        self.status.used_bindings.push(name);
+    }
+
+    fn validate(&mut self) {
+        let root = self.ast;
+        match root {
+            Ast::Error => unreachable!(),
+            Ast::Word(name) | Ast::Splat(name) => {
+                if !self.resolved(name) {
+                    self.err(format!("unbound name {name}"))
+                }
+            }
+            Ast::Interpolated(parts) => {
+                for part in parts {
+                    if let (StringPart::Word(name), span) = part {
+                        self.span = *span;
+                        if !self.resolved(name.as_str()) {
+                            self.err(format!("unbound name {name}"))
+                        }
+                    }
+                }
+            }
+            // validate each line
+            // ensure it's not empty
+            // pass through tail position validation
+            // check if there are any declared but undefined functions
+            // pop all the bindings off the local stack
+            Ast::Block(block) => {
+                if block.is_empty() {
+                    self.err("blocks must have at least one expression".to_string());
+                    return;
+                }
+                let to = self.locals.len();
+                let tailpos = self.status.tail_position;
+                for (expr, span) in block.iter().take(block.len() - 1) {
+                    self.status.tail_position = false;
+                    self.ast = expr;
+                    self.span = *span;
+                    self.validate();
+                }
+
+                let (expr, span) = block.last().unwrap();
+                self.ast = expr;
+                self.span = *span;
+                self.status.tail_position = tailpos;
+                self.validate();
+
+                let block_bindings = self.locals.split_off(to);
+
+                for binding in block_bindings {
+                    let (name, _, fn_info) = binding;
+                    if matches!(fn_info, FnInfo::Declared) {
+                        self.err(format!("fn `{name}` is declared but not defined"))
+                    }
+                }
+            }
+            // if in tail position, pass through tail position validation
+            // no unbound names
+            Ast::If(cond, then, r#else) => {
+                let tailpos = self.status.tail_position;
+                self.status.tail_position = false;
+
+                let (expr, span) = cond.as_ref();
+                self.ast = expr;
+                self.span = *span;
+                self.validate();
+
+                // pass through tailpos only to then/else
+                self.status.tail_position = tailpos;
+                let (expr, span) = then.as_ref();
+                self.ast = expr;
+                self.span = *span;
+                self.validate();
+
+                let (expr, span) = r#else.as_ref();
+                self.ast = expr;
+                self.span = *span;
+                self.validate();
+            }
+            Ast::Tuple(members) => {
+                if members.is_empty() {
+                    return;
+                }
+                let tailpos = self.status.tail_position;
+                self.status.tail_position = false;
+                for (expr, span) in members {
+                    self.ast = expr;
+                    self.span = *span;
+                    self.validate();
+                }
+                self.status.tail_position = tailpos;
+            }
+            // no more than one placeholder
+            Ast::Arguments(args) => {
+                if args.is_empty() {
+                    return;
+                }
+                let tailpos = self.status.tail_position;
+                self.status.tail_position = false;
+                for (expr, span) in args {
+                    self.ast = expr;
+                    self.span = *span;
+                    self.validate();
+                }
+                self.status.has_placeholder = false;
+                self.status.tail_position = tailpos;
+            }
+            Ast::Placeholder => {
+                if self.status.has_placeholder {
+                    self.err(
+                        "you may only use one placeholder when partially applying functions"
+                            .to_string(),
+                    );
+                }
+                self.status.has_placeholder = true;
+            }
+            Ast::List(list) => {
+                if list.is_empty() {
+                    return;
+                }
+                let tailpos = self.status.tail_position;
+                self.status.tail_position = false;
+                for (expr, span) in list {
+                    self.ast = expr;
+                    self.span = *span;
+                    self.validate();
+                }
+
+                self.status.tail_position = tailpos;
+            }
+            Ast::Pair(_, value) => {
+                let (expr, span) = value.as_ref();
+                self.ast = expr;
+                self.span = *span;
+                self.validate();
+            }
+            Ast::Dict(dict) => {
+                if dict.is_empty() {
+                    return;
+                }
+                let tailpos = self.status.tail_position;
+                self.status.tail_position = false;
+                for (expr, span) in dict {
+                    self.ast = expr;
+                    self.span = *span;
+                    self.validate();
+                }
+                self.status.tail_position = tailpos;
+            }
+
+            // TODO!
+            // first check all nodes
+            // then...
+            // check arity is 1 if first term is keyword
+            // check arity against fn info if first term is word and second term is args
+            Ast::Synthetic(first, second, rest) => {
+                todo!()
+            }
+            Ast::When(clauses) => {
+                // let tailpos = self.status.tail_position;
+                // for (clause, _) in clauses {
+                //     self.status.tail_position = false;
+                //     let (expr, span) = clause.cond.clone();
+                //     self.ast = &expr;
+                //     self.span = span;
+                //     self.validate();
+
+                //     self.status.tail_position = tailpos;
+                //     let (expr, span) = clause.body;
+                //     self.ast = &expr;
+                //     self.span = span;
+                //     self.validate();
+                // }
+            }
+
+            // binding forms
+            // TODO: set up errors to include original binding
+            Ast::Box(name, boxed) => {
+                if self.bound(name).is_some() {
+                    self.err(format!("box name `{name}` is already bound"));
+                }
+                let (expr, span) = boxed.as_ref();
+                self.ast = expr;
+                self.span = *span;
+                self.validate();
+            }
+            Ast::Let(lhs, rhs) => todo!(),
+            Ast::Match(scrutinee, clauses) => todo!(),
+
+            Ast::FnDeclaration(name) => {
+                let tailpos = self.status.tail_position;
+                self.status.tail_position = false;
+                if self.bound(name).is_some() {
+                    self.err(format!("fn name `{name}` is already bound"));
+                    return;
+                }
+                self.declare_fn(name.to_string());
+                self.status.tail_position = tailpos;
+            }
+            Ast::Fn(name, clauses, ..) => {
+                match self.bound(name) {
+                    Some((_, _, FnInfo::Declared)) => (),
+                    None => (),
+                    _ => {
+                        self.err(format!("name `{name}` is already bound"));
+                    }
+                }
+
+                let from = self.status.used_bindings.len();
+                let arities = HashSet::new();
+
+                for clause in clauses {
+                    // TODO: validate all parts of clauses
+                    // add clause arity to arities
+                }
+
+                let mut closed_over = HashSet::new();
+
+                for binding in self.status.used_bindings.iter().skip(from) {
+                    closed_over.insert(binding.clone());
+                }
+
+                let info = FnInfo::Defined(arities, closed_over);
+
+                self.define_fn(name.to_string(), info)
+            }
+
+            Ast::Panic(msg) => {
+                let tailpos = self.status.tail_position;
+                self.status.tail_position = false;
+                let (expr, span) = msg.as_ref();
+                self.ast = expr;
+                self.span = *span;
+                self.validate();
+                self.status.tail_position = tailpos;
+            }
+            Ast::Do(terms) => {
+                for term in terms {
+                    let (expr, span) = term;
+                    self.ast = expr;
+                    self.span = *span;
+                    self.validate();
+                }
+            }
+            Ast::Repeat(times, body) => {
+                self.status.tail_position = false;
+                let (expr, span) = times.as_ref();
+                self.ast = expr;
+                self.span = *span;
+                self.validate();
+
+                let (expr, span) = body.as_ref();
+                self.ast = expr;
+                self.span = *span;
+                self.validate();
+            }
+            Ast::Loop(with, body) => {
+                let (expr, span) = with.as_ref();
+                self.span = *span;
+                self.ast = expr;
+                self.validate();
+
+                let in_loop = self.status.in_loop;
+                self.status.in_loop = true;
+
+                let (expr, span) = body;
+                self.span = span;
+                self.expr = expr;
+                self.validate();
+
+                self.status.in_loop = in_loop;
+            }
+            Ast::Recur(args) => {}
+            // terminals can never be invalid
+            Ast::Nil | Ast::Boolean(_) | Ast::Number(_) | Ast::Keyword(_) | Ast::String(_) => (),
+        };
+        self.ast = root;
+    }
+}

src/value.rs

@@ -20,17 +20,12 @@ pub enum Value<'src> {
     Boolean(bool),
     Number(f64),
     Keyword(&'static str),
-    // TODO: add a "runtime-generated" string type that wraps a Rust String
-    // this is necessary for nice documentation and string interpolation
     InternedString(&'static str),
     AllocatedString(Rc<String>),
     // on the heap for now
     Tuple(Rc<Vec<Self>>),
     Args(Rc<Vec<Self>>),
-    // ref-counted, immutable, persistent
     List(Vector<Self>),
-    // ref-counted, immutable, persistent
-    // dicts may only use keywords as keys
     Dict(HashMap<&'static str, Self>),
     Box(&'static str, Rc<RefCell<Self>>),
     Fn(Rc<Fn<'src>>),
@@ -62,7 +57,7 @@ impl<'src> Clone for Value<'src> {
             Value::Fn(f) => Value::Fn(f.clone()),
             Value::List(l) => Value::List(l.clone()),
             Value::Dict(d) => Value::Dict(d.clone()),
-            Value::Box(name, b) => Value::Box(*name, b.clone()),
+            Value::Box(name, b) => Value::Box(name, b.clone()),
             Value::Placeholder => Value::Placeholder,
             Value::Base(b) => Value::Base(b.clone()),
             Value::Recur(..) => unreachable!(),
@@ -177,7 +172,7 @@ impl Value<'_> {
                 .map(|(k, v)| format!(":{} {}", k, v.interpolate()))
                 .collect::<Vec<_>>()
                 .join(", "),
-            Value::Fn(x) => format!("fn {}", x.name.to_string()),
+            Value::Fn(x) => format!("fn {}", x.name),
             Value::Placeholder => unreachable!(),
             Value::Args(_) => unreachable!(),
             Value::Recur(_) => unreachable!(),