Some initial work on a better repl

Just playing around for now

.gitignore

@@ -2,3 +2,4 @@ Cargo.lock
 target
 .schala_repl
 .schala_history
+rusty-tags.vi

Cargo.toml

@@ -6,11 +6,12 @@ authors = ["greg <greg.shuflin@protonmail.com>"]
 [dependencies]
 
 schala-repl = { path = "schala-repl" }
-schala-codegen = { path = "schala-codegen" }
+schala-repl-codegen = { path = "schala-repl-codegen" }
 maaru-lang = { path = "maaru" }
 rukka-lang = { path = "rukka" }
 robo-lang = { path = "robo" }
-schala-lang = { path = "schala-lang" }
+schala-lang = { path = "schala-lang/language" }
+schala-lang-codegen = { path = "schala-lang/codegen" }
 
 [build-dependencies]
 includedir_codegen = "0.2.0"

Grammar

@@ -1,31 +0,0 @@
-
-
-<program> := <statements> EOF
-
-<statements> := <statement>
-             |  <statement> SEP <statements>
-
-<statement> := let <id> = <expr>
-            |  <expr>
-            | <fn_block>
-
-<fn_block> := fn <id> ( <arg_list> ) <statements> end
-
-<arg_list> := e
-           | <id>
-           | <id> , <arg_list>
-
-<expr> := if <expr> then <statements> end
-       |  if <expr> then <statements> else <statements> end
-       |  while <expr> SEP <statements> end
-       |  ( <expr> )
-       |  <binop>
-
-<binop> := <simple_expr>
-        |  <simple_expr> <id> <binop>
-
-<simple_expr> := <id>
-              | <number>
-              | <string>
-
-

HindleyMilner.hs

@@ -0,0 +1,920 @@
+{-# LANGUAGE GeneralizedNewtypeDeriving #-}
+{-# LANGUAGE LambdaCase                 #-}
+{-# LANGUAGE OverloadedLists            #-}
+{-# LANGUAGE OverloadedStrings          #-}
+
+
+
+-- | This module is an extensively documented walkthrough for typechecking a
+-- basic functional language using the Hindley-Damas-Milner algorithm.
+--
+-- In the end, we'll be able to infer the type of expressions like
+--
+-- @
+-- find (λx. (>) x 0)
+--   :: [Integer] -> Either () Integer
+-- @
+--
+-- It can be used in multiple different forms:
+--
+--  * The source is written in literate programming style, so you can almost
+--    read it from top to bottom, minus some few references to later topics.
+--  * /Loads/ of doctests (runnable and verified code examples) are included
+--  * The code is runnable in GHCi, all definitions are exposed.
+--  * A small main module that gives many examples of what you might try out in
+--    GHCi is also included.
+--  * The Haddock output yields a nice overview over the definitions given, with
+--    a nice rendering of a truckload of Haddock comments.
+
+module HindleyMilner where
+
+import           Control.Monad.Trans
+import           Control.Monad.Trans.Except
+import           Control.Monad.Trans.State
+import           Data.Map                   (Map)
+import qualified Data.Map                   as M
+import           Data.Monoid
+import           Data.Set                   (Set)
+import qualified Data.Set                   as S
+import           Data.String
+import           Data.Text                  (Text)
+import qualified Data.Text                  as T
+
+
+
+-- $setup
+--
+-- For running doctests:
+--
+-- >>> :set -XOverloadedStrings
+-- >>> :set -XOverloadedLists
+-- >>> :set -XLambdaCase
+-- >>> import qualified Data.Text.IO as T
+-- >>> let putPprLn = T.putStrLn . ppr
+
+
+
+-- #############################################################################
+-- #############################################################################
+-- * Preliminaries
+-- #############################################################################
+-- #############################################################################
+
+
+
+-- #############################################################################
+-- ** Prettyprinting
+-- #############################################################################
+
+
+
+-- | A prettyprinter class. Similar to 'Show', but with a focus on having
+-- human-readable output as opposed to being valid Haskell.
+class Pretty a where
+    ppr :: a -> Text
+
+
+
+-- #############################################################################
+-- ** Names
+-- #############################################################################
+
+
+
+-- | A 'name' is an identifier in the language we're going to typecheck.
+-- Variables on both the term and type level have 'Name's, for example.
+newtype Name = Name Text
+    deriving (Eq, Ord, Show)
+
+-- | >>> "lorem" :: Name
+-- Name "lorem"
+instance IsString Name where
+    fromString = Name . T.pack
+
+-- | >>> putPprLn (Name "var")
+-- var
+instance Pretty Name where
+    ppr (Name n) = n
+
+
+
+-- #############################################################################
+-- ** Monotypes
+-- #############################################################################
+
+
+
+-- | A monotype is an unquantified/unparametric type, in other words it contains
+-- no @forall@s. Monotypes are the inner building blocks of all types. Examples
+-- of monotypes are @Int@, @a@, @a -> b@.
+--
+-- In formal notation, 'MType's are often called τ (tau) types.
+data MType = TVar Name           -- ^ @a@
+           | TFun MType MType    -- ^ @a -> b@
+           | TConst Name         -- ^ @Int@, @()@, …
+
+           -- Since we can't declare our own types in our simple type system
+           -- here, we'll hard-code certain basic ones so we can typecheck some
+           -- familar functions that use them later.
+           | TList MType         -- ^ @[a]@
+           | TEither MType MType -- ^ @Either a b@
+           | TTuple MType MType  -- ^ @(a,b)@
+           deriving Show
+
+-- | >>> putPprLn (TFun (TEither (TVar "a") (TVar "b")) (TFun (TVar "c") (TVar "d")))
+-- Either a b → c → d
+--
+-- Using the 'IsString' instance:
+--
+-- >>> putPprLn (TFun (TEither "a" "b") (TFun "c" "d"))
+-- Either a b → c → d
+instance Pretty MType where
+    ppr = go False
+      where
+        go _ (TVar name)   = ppr name
+        go _ (TList a)     = "[" <> ppr a <> "]"
+        go _ (TEither l r) = "Either " <> ppr l <> " " <> ppr r
+        go _ (TTuple a b)  = "(" <> ppr a <> ", " <> ppr b <> ")"
+        go _ (TConst name) = ppr name
+        go parenthesize (TFun a b)
+            | parenthesize = "(" <> lhs <> " → " <> rhs <> ")"
+            | otherwise    =        lhs <> " → " <> rhs
+            where lhs = go True a
+                  rhs = go False b
+
+-- | >>> "var" :: MType
+-- TVar (Name "var")
+instance IsString MType where
+    fromString = TVar . fromString
+
+
+
+-- | The free variables of an 'MType'. This is simply the collection of all the
+-- individual type variables occurring inside of it.
+--
+-- __Example:__ The free variables of @a -> b@ are @a@ and @b@.
+freeMType :: MType -> Set Name
+freeMType = \case
+    TVar a      -> [a]
+    TFun a b    -> freeMType a <> freeMType b
+    TList a     -> freeMType a
+    TEither l r -> freeMType l <> freeMType r
+    TTuple a b  -> freeMType a <> freeMType b
+    TConst _    -> []
+
+
+
+-- | Substitute all the contained type variables mentioned in the substitution,
+-- and leave everything else alone.
+instance Substitutable MType where
+    applySubst s = \case
+        TVar a -> let Subst s' = s
+                  in M.findWithDefault (TVar a) a s'
+        TFun f x    -> TFun (applySubst s f) (applySubst s x)
+        TList a     -> TList (applySubst s a)
+        TEither l r -> TEither (applySubst s l) (applySubst s r)
+        TTuple a b  -> TTuple (applySubst s a) (applySubst s b)
+        c@TConst {} -> c
+
+
+
+-- #############################################################################
+-- ** Polytypes
+-- #############################################################################
+
+-- | A polytype is a monotype universally quantified over a number of type
+-- variables. In Haskell, all definitions have polytypes, but since the @forall@
+-- is implicit they look a bit like monotypes, maybe confusingly so. For
+-- example, the type of @1 :: Int@ is actually @forall <nothing>. Int@, and the
+-- type of @id@ is @forall a. a -> a@, although GHC displays it as @a -> a@.
+--
+-- A polytype claims to work "for all imaginable type parameters", very similar
+-- to how a lambda claims to work "for all imaginable value parameters". We can
+-- insert a value into a lambda's parameter to evaluate it to a new value, and
+-- similarly we'll later insert types into a polytype's quantified variables to
+-- gain new types.
+--
+-- __Example:__ in a definition @id :: forall a. a -> a@, the @a@ after the
+-- ∀ ("forall") is the collection of type variables, and @a -> a@ is the 'MType'
+-- quantified over. When we have such an @id@, we also have its specialized
+-- version @Int -> Int@ available. This process will be the topic of the type
+-- inference/unification algorithms.
+--
+-- In formal notation, 'PType's are often called σ (sigma) types.
+--
+-- The purpose of having monotypes and polytypes is that we'd like to only have
+-- universal quantification at the top level, restricting our language to rank-1
+-- polymorphism, where type inferece is total (all types can be inferred) and
+-- simple (only a handful of typing rules). Weakening this constraint would be
+-- easy: if we allowed universal quantification within function types we would
+-- get rank-N polymorphism. Taking it even further to allow it anywhere,
+-- effectively replacing all occurrences of 'MType' with 'PType', yields
+-- impredicative types. Both these extensions make the type system
+-- *significantly* more complex though.
+data PType = Forall (Set Name) MType -- ^ ∀{α}. τ
+
+-- | >>> putPprLn (Forall ["a"] (TFun "a" "a"))
+-- ∀a. a → a
+instance Pretty PType where
+    ppr (Forall qs mType) = "∀" <> pprUniversals <> ". " <> ppr mType
+      where
+        pprUniversals
+          | S.null qs = "∅"
+          | otherwise = (T.intercalate " " . map ppr . S.toList) qs
+
+
+
+-- | The free variables of a 'PType' are the free variables of the contained
+-- 'MType', except those universally quantified.
+--
+-- >>> let sigma = Forall ["a"] (TFun "a" (TFun (TTuple "b" "a") "c"))
+-- >>> putPprLn sigma
+-- ∀a. a → (b, a) → c
+-- >>> let display = T.putStrLn . T.intercalate ", " . foldMap (\x -> [ppr x])
+-- >>> display (freePType sigma)
+-- b, c
+freePType :: PType -> Set Name
+freePType (Forall qs mType) = freeMType mType `S.difference` qs
+
+
+
+-- | Substitute all the free type variables.
+instance Substitutable PType where
+    applySubst (Subst subst) (Forall qs mType) =
+        let qs' = M.fromSet (const ()) qs
+            subst' = Subst (subst `M.difference` qs')
+        in Forall qs (applySubst subst' mType)
+
+
+
+-- #############################################################################
+-- ** The environment
+-- #############################################################################
+
+
+
+-- | The environment consists of all the values available in scope, and their
+-- associated polytypes. Other common names for it include "(typing) context",
+-- and because of the commonly used symbol for it sometimes directly
+-- \"Gamma"/@"Γ"@.
+--
+-- There are two kinds of membership in an environment,
+--
+--   - @∈@: an environment @Γ@ can be viewed as a set of @(value, type)@ pairs,
+--     and we can test whether something is /literally contained/ by it via
+--     x:σ ∈ Γ
+--   - @⊢@, pronounced /entails/, describes all the things that are well-typed,
+--     given an environment @Γ@. @Γ ⊢ x:τ@ can thus be seen as a judgement that
+--     @x:τ@ is /figuratively contained/ in @Γ@.
+--
+-- For example, the environment @{x:Int}@ literally contains @x@, but given
+-- this, it also entails @λy. x@, @λy z. x@, @let id = λy. y in id x@ and so on.
+--
+-- In Haskell terms, the environment consists of all the things you currently
+-- have available, or that can be built by comining them. If you import the
+-- Prelude, your environment entails
+--
+-- @
+-- id            →  ∀a. a→a
+-- map           →  ∀a b. (a→b) → [a] → [b]
+-- putStrLn      →  ∀∅. String → IO ()
+-- …
+-- id map        →  ∀a b. (a→b) → [a] → [b]
+-- map putStrLn  →  ∀∅. [String] -> [IO ()]
+-- …
+-- @
+newtype Env = Env (Map Name PType)
+
+-- | >>> :{
+--    putPprLn (Env
+--        [ ("id", Forall ["a"] (TFun "a" "a"))
+--        , ("const", Forall ["a", "b"] (TFun "a" (TFun "b" "a"))) ])
+-- :}
+-- Γ = { const : ∀a b. a → b → a
+--     , id : ∀a. a → a }
+instance Pretty Env where
+    ppr (Env env) = "Γ = { " <> T.intercalate "\n    , " pprBindings <> " }"
+      where
+        bindings = M.assocs env
+        pprBinding (name, pType) = ppr name <> " : " <> ppr pType
+        pprBindings = map pprBinding bindings
+
+
+
+-- | The free variables of an 'Env'ironment are all the free variables of the
+-- 'PType's it contains.
+freeEnv :: Env -> Set Name
+freeEnv (Env env) = let allPTypes = M.elems env
+                    in S.unions (map freePType allPTypes)
+
+
+
+-- | Performing a 'Subst'itution in an 'Env'ironment means performing that
+-- substituion on all the contained 'PType's.
+instance Substitutable Env where
+    applySubst s (Env env) = Env (M.map (applySubst s) env)
+
+
+
+-- #############################################################################
+-- ** Substitutions
+-- #############################################################################
+
+
+
+-- | A substitution is a mapping from type variables to 'MType's. Applying a
+-- substitution means applying those replacements. For example, the substitution
+-- @a -> Int@ applied to @a -> a@ yields the result @Int -> Int@.
+--
+-- A key concept behind Hindley-Milner is that once we dive deeper into an
+-- expression, we learn more about our type variables. We might learn that  @a@
+-- has to be specialized to @b -> b@, and then later on that @b@ is actually
+-- @Int@. Substitutions are an organized way of carrying this information along.
+newtype Subst = Subst (Map Name MType)
+
+
+
+-- | We're going to apply substitutions to a variety of other values that
+-- somehow contain type variables, so we overload this application operation in
+-- a class here.
+--
+-- Laws:
+--
+-- @
+-- 'applySubst' 'mempty' ≡ 'id'
+-- 'applySubst' (s1 '<>' s2) ≡ 'applySubst' s1 . 'applySubst' s2
+-- @
+class Substitutable a where
+    applySubst :: Subst -> a -> a
+
+instance (Substitutable a, Substitutable b) => Substitutable (a,b) where
+    applySubst s (x,y) = (applySubst s x, applySubst s y)
+
+-- | @'applySubst' s1 s2@ applies one substitution to another, replacing all the
+-- bindings in the second argument @s2@ with their values mentioned in the first
+-- one (@s1@).
+instance Substitutable Subst where
+    applySubst s (Subst target) = Subst (fmap (applySubst s) target)
+
+-- | >>> :{
+--    putPprLn (Subst
+--        [ ("a", TFun "b" "b")
+--        , ("b", TEither "c" "d") ])
+-- :}
+-- { a ––> b → b
+-- , b ––> Either c d }
+instance Pretty Subst where
+    ppr (Subst s) = "{ " <> T.intercalate "\n, " [ ppr k <> " ––> " <> ppr v | (k,v) <- M.toList s ] <> " }"
+
+-- | Combine two substitutions by applying all substitutions mentioned in the
+-- first argument to the type variables contained in the second.
+instance Monoid Subst where
+    -- Considering that all we can really do with a substitution is apply it, we
+    -- can use the one of 'Substitutable's laws to show that substitutions
+    -- combine associatively,
+    --
+    -- @
+    --   applySubst (compose s1 (compose s2 s3))
+    -- = applySubst s1 . applySubst (compose s2 s3)
+    -- = applySubst s1 . applySubst s2 . applySubst s3
+    -- = applySubst (compose s1 s2) . applySubst s3
+    -- = applySubst (compose (compose s1 s2) s3)
+    -- @
+    mappend subst1 subst2 = Subst (s1 `M.union` s2)
+      where
+        Subst s1 = subst1
+        Subst s2 = applySubst subst1 subst2
+
+    mempty = Subst M.empty
+
+
+
+-- #############################################################################
+-- #############################################################################
+-- * Typechecking
+-- #############################################################################
+-- #############################################################################
+
+-- $ Typechecking does two things:
+--
+-- 1. If two types are not immediately identical, attempt to 'unify' them
+--    to get a type compatible with both of them
+-- 2. 'infer' the most general type of a value by comparing the values in its
+--    definition with the 'Env'ironment
+
+
+
+-- #############################################################################
+-- ** Inference context
+-- #############################################################################
+
+
+
+-- | The inference type holds a supply of unique names, and can fail with a
+-- descriptive error if something goes wrong.
+--
+-- /Invariant:/ the supply must be infinite, or we might run out of names to
+-- give to things.
+newtype Infer a = Infer (ExceptT InferError (State [Name]) a)
+    deriving (Functor, Applicative, Monad)
+
+-- | Errors that can happen during the type inference process.
+data InferError =
+    -- | Two types that don't match were attempted to be unified.
+    --
+    -- For example, @a -> a@ and @Int@ do not unify.
+    --
+    -- >>> putPprLn (CannotUnify (TFun "a" "a") (TConst "Int"))
+    -- Cannot unify a → a with Int
+      CannotUnify MType MType
+
+    -- | A 'TVar' is bound to an 'MType' that already contains it.
+    --
+    -- The canonical example of this is @λx. x x@, where the first @x@
+    -- in the body has to have type @a -> b@, and the second one @a@. Since
+    -- they're both the same @x@, this requires unification of @a@ with
+    -- @a -> b@, which only works if @a = a -> b = (a -> b) -> b = …@, yielding
+    -- an infinite type.
+    --
+    -- >>> putPprLn (OccursCheckFailed "a" (TFun "a" "a"))
+    -- Occurs check failed: a already appears in a → a
+    | OccursCheckFailed Name MType
+
+    -- | The value of an unknown identifier was read.
+    --
+    -- >>> putPprLn (UnknownIdentifier "a")
+    -- Unknown identifier: a
+    | UnknownIdentifier Name
+    deriving Show
+
+-- | >>> putPprLn (CannotUnify (TEither "a" "b") (TTuple "a" "b"))
+-- Cannot unify Either a b with (a, b)
+instance Pretty InferError where
+    ppr = \case
+        CannotUnify t1 t2 ->
+            "Cannot unify " <> ppr t1 <> " with " <> ppr t2
+        OccursCheckFailed name ty ->
+            "Occurs check failed: " <> ppr name <> " already appears in " <> ppr ty
+        UnknownIdentifier name ->
+            "Unknown identifier: " <> ppr name
+
+
+
+-- | Evaluate a value in an 'Infer'ence context.
+--
+-- >>> let expr = EAbs "f" (EAbs "g" (EAbs "x" (EApp (EApp "f" "x") (EApp "g" "x"))))
+-- >>> putPprLn expr
+-- λf g x. f x (g x)
+-- >>> let inferred = runInfer (infer (Env []) expr)
+-- >>> let demonstrate = \case Right (_, ty) -> T.putStrLn (":: " <> ppr ty)
+-- >>> demonstrate inferred
+-- :: (c → e → f) → (c → e) → c → f
+runInfer :: Infer a -- ^ Inference data
+         -> Either InferError a
+runInfer (Infer inf) =
+    evalState (runExceptT inf) (map Name (infiniteSupply alphabet))
+  where
+
+    alphabet = map T.singleton ['a'..'z']
+
+    -- [a, b, c] ==> [a,b,c, a1,b1,c1, a2,b2,c2, …]
+    infiniteSupply supply = supply <> addSuffixes supply (1 :: Integer)
+      where
+        addSuffixes xs n = map (\x -> addSuffix x n) xs <> addSuffixes xs (n+1)
+        addSuffix x n = x <> T.pack (show n)
+
+
+
+-- | Throw an 'InferError' in an 'Infer'ence context.
+--
+-- >>> case runInfer (throw (UnknownIdentifier "var")) of Left err -> putPprLn err
+-- Unknown identifier: var
+throw :: InferError -> Infer a
+throw = Infer . throwE
+
+
+
+-- #############################################################################
+-- ** Unification
+-- #############################################################################
+
+-- $ Unification describes the process of making two different types compatible
+-- by specializing them where needed. A desirable property to have here is being
+-- able to find the most general unifier. Luckily, we'll be able to do that in
+-- our type system.
+
+
+
+-- | The unification of two 'MType's is the most general substituion that can be
+-- applied to both of them in order to yield the same result.
+--
+-- >>> let m1 = TFun "a" "b"
+-- >>> putPprLn m1
+-- a → b
+-- >>> let m2 = TFun "c" (TEither "d" "e")
+-- >>> putPprLn m2
+-- c → Either d e
+-- >>> let inferSubst = unify (m1, m2)
+-- >>> case runInfer inferSubst of Right subst -> putPprLn subst
+-- { a ––> c
+-- , b ––> Either d e }
+unify :: (MType, MType) -> Infer Subst
+unify = \case
+    (TFun a b,    TFun x y)          -> unifyBinary (a,b) (x,y)
+    (TVar v,      x)                 -> v `bindVariableTo` x
+    (x,           TVar v)            -> v `bindVariableTo` x
+    (TConst a,    TConst b) | a == b -> pure mempty
+    (TList a,     TList b)           -> unify (a,b)
+    (TEither a b, TEither x y)       -> unifyBinary (a,b) (x,y)
+    (TTuple a b,  TTuple x y)        -> unifyBinary (a,b) (x,y)
+    (a, b)                           -> throw (CannotUnify a b)
+
+  where
+
+    -- Unification of binary type constructors, such as functions and Either.
+    -- Unification is first done for the first operand, and assuming the
+    -- required substitution, for the second one.
+    unifyBinary :: (MType, MType) -> (MType, MType) -> Infer Subst
+    unifyBinary (a,b) (x,y) = do
+        s1 <- unify (a, x)
+        s2 <- unify (applySubst s1 (b, y))
+        pure (s1 <> s2)
+
+
+
+-- | Build a 'Subst'itution that binds a 'Name' of a 'TVar' to an 'MType'. The
+-- resulting substitution should be idempotent, i.e. applying it more than once
+-- to something should not be any different from applying it only once.
+--
+-- - In the simplest case, this just means building a substitution that just
+--   does that.
+-- - Substituting a 'Name' with a 'TVar' with the same name unifies a type
+--   variable with itself, and the resulting substitution does nothing new.
+-- - If the 'Name' we're trying to bind to an 'MType' already occurs in that
+--   'MType', the resulting substitution would not be idempotent: the 'MType'
+--   would be replaced again, yielding a different result. This is known as the
+--   Occurs Check.
+bindVariableTo :: Name -> MType -> Infer Subst
+
+bindVariableTo name (TVar v) | boundToSelf = pure mempty
+  where
+    boundToSelf = name == v
+
+bindVariableTo name mType | name `occursIn` mType = throw (OccursCheckFailed name mType)
+  where
+    n `occursIn` ty = n `S.member` freeMType ty
+
+bindVariableTo name mType = pure (Subst (M.singleton name mType))
+
+
+
+-- #############################################################################
+-- ** Type inference
+-- #############################################################################
+
+-- $ Type inference is the act of finding out a value's type by looking at the
+-- environment it is in, in order to make it compatible with it.
+--
+-- In literature, the Hindley-Damas-Milner inference algorithm ("Algorithm W")
+-- is often presented in the style of logical formulas, and below you'll find
+-- that version along with code that actually does what they say.
+--
+-- These formulas look a bit like fractions, where the "numerator" is a
+-- collection of premises, and the denominator is the consequence if all of them
+-- hold.
+--
+-- __Example:__
+--
+-- @
+-- Γ ⊢ even : Int → Bool   Γ ⊢ 1 : Int
+-- –––––––––––––––––––––––––––––––––––
+--          Γ ⊢ even 1 : Bool
+-- @
+--
+-- means that if we have a value of type @Int -> Bool@ called "even" and a value
+-- of type @Int@ called @1@, then we also have a value of type @Bool@ via
+-- @even 1@ available to us.
+--
+-- The actual inference rules are polymorphic versions of this example, and
+-- the code comments will explain each step in detail.
+
+
+
+-- -----------------------------------------------------------------------------
+-- *** The language: typed lambda calculus
+-- -----------------------------------------------------------------------------
+
+
+
+-- | The syntax tree of the language we'd like to typecheck. You can view it as
+-- a close relative to simply typed lambda calculus, having only the most
+-- necessary syntax elements.
+--
+-- Since 'ELet' is non-recursive, the usual fixed-point function
+-- @fix : (a → a) → a@ can be introduced to allow recursive definitions.
+data Exp = ELit Lit          -- ^ True, 1
+         | EVar Name         -- ^ @x@
+         | EApp Exp Exp      -- ^ @f x@
+         | EAbs Name Exp     -- ^ @λx. e@
+         | ELet Name Exp Exp -- ^ @let x = e in e'@ (non-recursive)
+         deriving Show
+
+
+
+-- | Literals we'd like to support. Since we can't define new data types in our
+-- simple type system, we'll have to hard-code the possible ones here.
+data Lit = LBool Bool
+         | LInteger Integer
+         deriving Show
+
+
+
+-- | >>> putPprLn (EAbs "f" (EAbs "g" (EAbs "x" (EApp (EApp "f" "x") (EApp "g" "x")))))
+-- λf g x. f x (g x)
+instance Pretty Exp where
+    ppr (ELit lit) = ppr lit
+
+    ppr (EVar name) = ppr name
+
+    ppr (EApp f x) = pprApp1 f <> " " <> pprApp2 x
+      where
+        pprApp1 = \case
+            eLet@ELet{} -> "(" <> ppr eLet <> ")"
+            eLet@EAbs{} -> "(" <> ppr eLet <> ")"
+            e -> ppr e
+        pprApp2 = \case
+            eApp@EApp{} -> "(" <> ppr eApp <> ")"
+            e -> pprApp1 e
+
+    ppr x@EAbs{} = pprAbs True x
+      where
+        pprAbs True  (EAbs name expr) = "λ" <> ppr name <> pprAbs False expr
+        pprAbs False (EAbs name expr) = " " <> ppr name <> pprAbs False expr
+        pprAbs _ expr                 = ". " <> ppr expr
+
+    ppr (ELet name value body) =
+        "let " <> ppr name <> " = " <> ppr value <> " in " <> ppr body
+
+-- | >>> putPprLn (LBool True)
+-- True
+--
+-- >>> putPprLn (LInteger 127)
+-- 127
+instance Pretty Lit where
+    ppr = \case
+        LBool    b -> showT b
+        LInteger i -> showT i
+      where
+        showT :: Show a => a -> Text
+        showT = T.pack . show
+
+-- | >>> "var" :: Exp
+-- EVar (Name "var")
+instance IsString Exp where
+    fromString = EVar . fromString
+
+
+
+-- -----------------------------------------------------------------------------
+-- *** Some useful definitions
+-- -----------------------------------------------------------------------------
+
+
+
+-- | Generate a fresh 'Name' in a type 'Infer'ence context. An example use case
+-- of this is η expansion, which transforms @f@ into @λx. f x@, where "x" is a
+-- new name, i.e. unbound in the current context.
+fresh :: Infer MType
+fresh = drawFromSupply >>= \case
+    Right name -> pure (TVar name)
+    Left err -> throw err
+
+  where
+
+    drawFromSupply :: Infer (Either InferError Name)
+    drawFromSupply = Infer (do
+        s:upply <- lift get
+        lift (put upply)
+        pure (Right s) )
+
+
+
+-- | Add a new binding to the environment.
+--
+-- The Haskell equivalent would be defining a new value, for example in module
+-- scope or in a @let@ block. This corresponds to the "comma" operation used in
+-- formal notation,
+--
+-- @
+-- Γ, x:σ  ≡  extendEnv Γ (x,σ)
+-- @
+extendEnv :: Env -> (Name, PType) -> Env
+extendEnv (Env env) (name, pType) = Env (M.insert name pType env)
+
+
+
+-- -----------------------------------------------------------------------------
+-- *** Inferring the types of all language constructs
+-- -----------------------------------------------------------------------------
+
+
+
+-- | Infer the type of an 'Exp'ression in an 'Env'ironment, resulting in the
+-- 'Exp's 'MType' along with a substitution that has to be done in order to reach
+-- this goal.
+--
+-- This is widely known as /Algorithm W/.
+infer :: Env -> Exp -> Infer (Subst, MType)
+infer env = \case
+    ELit lit    -> inferLit lit
+    EVar name   -> inferVar env name
+    EApp f x    -> inferApp env f x
+    EAbs x e    -> inferAbs env x e
+    ELet x e e' -> inferLet env x e e'
+
+
+
+-- | Literals such as 'True' and '1' have their types hard-coded.
+inferLit :: Lit -> Infer (Subst, MType)
+inferLit lit = pure (mempty, TConst litTy)
+  where
+    litTy = case lit of
+        LBool    {} -> "Bool"
+        LInteger {} -> "Integer"
+
+
+
+-- | Inferring the type of a variable is done via
+--
+-- @
+-- x:σ ∈ Γ   τ = instantiate(σ)
+-- ––––––––––––––––––––––––––––  [Var]
+--            Γ ⊢ x:τ
+-- @
+--
+-- This means that if @Γ@ /literally contains/ (@∈@) a value, then it also
+-- /entails it/ (@⊢@) in all its instantiations.
+inferVar :: Env -> Name -> Infer (Subst, MType)
+inferVar env name = do
+    sigma <- lookupEnv env name -- x:σ ∈ Γ
+    tau <- instantiate sigma    -- τ = instantiate(σ)
+                                -- ------------------
+    pure (mempty, tau)          -- Γ ⊢ x:τ
+
+
+
+-- | Look up the 'PType' of a 'Name' in the 'Env'ironment.
+--
+-- This checks whether @x:σ@ is /literally contained/ in @Γ@. For more details
+-- about this, see the documentation of 'Env'.
+--
+-- To give a Haskell analogon, looking up @id@ when @Prelude@ is loaded, the
+-- resulting 'PType' would be @id@'s type, namely @forall a. a -> a@.
+lookupEnv :: Env -> Name -> Infer PType
+lookupEnv (Env env) name = case M.lookup name env of
+    Just x  -> pure x
+    Nothing -> throw (UnknownIdentifier name)
+
+
+
+-- | Bind all quantified variables of a 'PType' to 'fresh' type variables.
+--
+-- __Example:__ instantiating @forall a. a -> b -> a@ results in the 'MType'
+-- @c -> b -> c@, where @c@ is a fresh name (to avoid shadowing issues).
+--
+-- You can picture the 'PType' to be the prototype converted to an instantiated
+-- 'MType', which can now be used in the unification process.
+--
+-- Another way of looking at it is by simply forgetting which variables were
+-- quantified, carefully avoiding name clashes when doing so.
+--
+-- 'instantiate' can also be seen as the opposite of 'generalize', which we'll
+-- need later to convert an 'MType' to a 'PType'.
+instantiate :: PType -> Infer MType
+instantiate (Forall qs t) = do
+    subst <- substituteAllWithFresh qs
+    pure (applySubst subst t)
+
+  where
+    -- For each given name, add a substitution from that name to a fresh type
+    -- variable to the result.
+    substituteAllWithFresh :: Set Name -> Infer Subst
+    substituteAllWithFresh xs = do
+        let freshSubstActions = M.fromSet (const fresh) xs
+        freshSubsts <- sequenceA freshSubstActions
+        pure (Subst freshSubsts)
+
+
+
+-- | Function application captures the fact that if we have a function and an
+-- argument we can give to that function, we also have the result value of the
+-- result type available to us.
+--
+-- @
+-- Γ ⊢ f : fτ   Γ ⊢ x : xτ   fxτ = fresh   unify(fτ, xτ → fxτ)
+-- –––––––––––––––––––––––––––––––––––––––––––––––––––––––––––  [App]
+--                       Γ ⊢ f x : fxτ
+-- @
+--
+-- This rule says that given a function and a value with a type, the function
+-- type has to unify with a function type that allows the value type to be its
+-- argument.
+inferApp
+    :: Env
+    -> Exp -- ^ __f__ x
+    -> Exp -- ^ f __x__
+    -> Infer (Subst, MType)
+inferApp env f x = do
+    (s1, fTau) <- infer env f                         -- f : fτ
+    (s2, xTau) <- infer (applySubst s1 env) x         -- x : xτ
+    fxTau <- fresh                                    -- fxτ = fresh
+    s3 <- unify (applySubst s2 fTau, TFun xTau fxTau) -- unify (fτ, xτ → fxτ)
+    let s = s3 <> s2 <> s1                            -- --------------------
+    pure (s, applySubst s3 fxTau)                     -- f x : fxτ
+
+
+
+-- | Lambda abstraction is based on the fact that when we introduce a new
+-- variable, the resulting lambda maps from that variable's type to the type of
+-- the body.
+--
+-- @
+-- τ = fresh   σ = ∀∅. τ   Γ, x:σ ⊢ e:τ'
+-- –––––––––––––––––––––––––––––––––––––  [Abs]
+--             Γ ⊢ λx.e : τ→τ'
+-- @
+--
+-- Here, @Γ, x:τ@ is @Γ@ extended by one additional mapping, namely @x:τ@.
+--
+-- Abstraction is typed by extending the environment by a new 'MType', and if
+-- under this assumption we can construct a function mapping to a value of that
+-- type, we can say that the lambda takes a value and maps to it.
+inferAbs
+    :: Env
+    -> Name -- ^ λ__x__. e
+    -> Exp  -- ^ λx. __e__
+    -> Infer (Subst, MType)
+inferAbs env x e = do
+    tau <- fresh                           -- τ = fresh
+    let sigma = Forall [] tau              -- σ = ∀∅. τ
+        env' = extendEnv env (x, sigma)    -- Γ, x:σ …
+    (s, tau') <- infer env' e              --        … ⊢ e:τ'
+                                           -- ---------------
+    pure (s, TFun (applySubst s tau) tau') -- λx.e : τ→τ'
+
+
+
+-- | A let binding allows extending the environment with new bindings in a
+-- principled manner. To do this, we first have to typecheck the expression to
+-- be introduced. The result of this is then generalized to a 'PType', since let
+-- bindings introduce new polymorphic values, which are then added to the
+-- environment. Now we can finally typecheck the body of the "in" part of the
+-- let binding.
+--
+-- Note that in our simple language, let is non-recursive, but recursion can be
+-- introduced as usual by adding a primitive @fix : (a → a) → a@ if desired.
+--
+-- @
+-- Γ ⊢ e:τ   σ = gen(Γ,τ)   Γ, x:σ ⊢ e':τ'
+-- –––––––––––––––––––––––––––––––––––––––  [Let]
+--         Γ ⊢ let x = e in e' : τ'
+-- @
+inferLet
+    :: Env
+    -> Name -- ^ let __x__ = e in e'
+    -> Exp -- ^ let x = __e__ in e'
+    -> Exp -- ^ let x = e in __e'__
+    -> Infer (Subst, MType)
+inferLet env x e e' = do
+    (s1, tau) <- infer env e              -- Γ ⊢ e:τ
+    let env' = applySubst s1 env
+    let sigma = generalize env' tau       -- σ = gen(Γ,τ)
+    let env'' = extendEnv env' (x, sigma) -- Γ, x:σ
+    (s2, tau') <- infer env'' e'          -- Γ ⊢ …
+                                          -- --------------------------
+    pure (s2 <> s1, tau')                 --     … let x = e in e' : τ'
+
+
+
+-- | Generalize an 'MType' to a 'PType' by universally quantifying over all the
+-- type variables contained in it, except those already free in the environment.
+--
+-- >>> let tau = TFun "a" (TFun "b" "a")
+-- >>> putPprLn tau
+-- a → b → a
+-- >>> putPprLn (generalize (Env [("x", Forall [] "b")]) tau)
+-- ∀a. a → b → a
+--
+-- In more formal notation,
+--
+-- @
+-- gen(Γ,τ) = ∀{α}. τ
+--     where {α} = free(τ) – free(Γ)
+-- @
+--
+-- 'generalize' can also be seen as the opposite of 'instantiate', which
+-- converts a 'PType' to an 'MType'.
+generalize :: Env -> MType -> PType
+generalize env mType = Forall qs mType
+  where
+    qs = freeMType mType `S.difference` freeEnv env

Main.hs

@@ -0,0 +1,185 @@
+{-# LANGUAGE OverloadedLists   #-}
+{-# LANGUAGE OverloadedStrings #-}
+
+module Main where
+
+
+
+import qualified Data.Map     as M
+import           Data.Monoid
+import           Data.Text    (Text)
+import qualified Data.Text.IO as T
+
+import HindleyMilner
+
+
+
+-- #############################################################################
+-- #############################################################################
+-- * Testing
+-- #############################################################################
+-- #############################################################################
+
+
+
+-- #############################################################################
+-- ** A small custom Prelude
+-- #############################################################################
+
+
+
+prelude :: Env
+prelude = Env (M.fromList
+    [ ("(*)",        Forall []              (tInteger ~> tInteger ~> tInteger))
+    , ("(+)",        Forall []              (tInteger ~> tInteger ~> tInteger))
+    , ("(,)",        Forall ["a","b"]       ("a" ~> "b" ~> TTuple "a" "b"))
+    , ("(-)",        Forall []              (tInteger ~> tInteger ~> tInteger))
+    , ("(.)",        Forall ["a", "b", "c"] (("b" ~> "c") ~> ("a" ~> "b") ~> "a" ~> "c"))
+    , ("(<)",        Forall []              (tInteger ~> tInteger ~> tBool))
+    , ("(<=)",       Forall []              (tInteger ~> tInteger ~> tBool))
+    , ("(>)",        Forall []              (tInteger ~> tInteger ~> tBool))
+    , ("(>=)",       Forall []              (tInteger ~> tInteger ~> tBool))
+    , ("const",      Forall ["a","b"]       ("a" ~> "b" ~> "a"))
+    , ("Cont/>>=",   Forall ["a"]           ((("a" ~> "r") ~> "r") ~> ("a" ~> (("b" ~> "r") ~> "r")) ~> (("b" ~> "r") ~> "r")))
+    , ("find",       Forall ["a","b"]       (("a" ~> tBool) ~> TList "a" ~> tMaybe "a"))
+    , ("fix",        Forall ["a"]           (("a" ~> "a") ~> "a"))
+    , ("foldr",      Forall ["a","b"]       (("a" ~> "b" ~> "b") ~> "b" ~> TList "a" ~> "b"))
+    , ("id",         Forall ["a"]           ("a" ~> "a"))
+    , ("ifThenElse", Forall ["a"]           (tBool ~> "a" ~> "a" ~> "a"))
+    , ("Left",       Forall ["a","b"]       ("a" ~> TEither "a" "b"))
+    , ("length",     Forall ["a"]           (TList "a" ~> tInteger))
+    , ("map",        Forall ["a","b"]       (("a" ~> "b") ~> TList "a" ~> TList "b"))
+    , ("reverse",    Forall ["a"]           (TList "a" ~> TList "a"))
+    , ("Right",      Forall ["a","b"]       ("b" ~> TEither "a" "b"))
+    , ("[]",         Forall ["a"]           (TList "a"))
+    , ("(:)",        Forall ["a"]           ("a" ~> TList "a" ~> TList "a"))
+    ])
+  where
+    tBool = TConst "Bool"
+    tInteger = TConst "Integer"
+    tMaybe = TEither (TConst "()")
+
+
+
+-- | Synonym for 'TFun' to make writing type signatures easier.
+--
+-- Instead of
+--
+-- @
+-- Forall ["a","b"] (TFun "a" (TFun "b" "a"))
+-- @
+--
+-- we can write
+--
+-- @
+-- Forall ["a","b"] ("a" ~> "b" ~> "a")
+-- @
+(~>) :: MType -> MType -> MType
+(~>) = TFun
+infixr 9 ~>
+
+
+
+-- #############################################################################
+-- ** Run it!
+-- #############################################################################
+
+
+
+-- | Run type inference on a cuple of values
+main :: IO ()
+main = do
+    let inferAndPrint = T.putStrLn . ("  " <>) . showType prelude
+    T.putStrLn "Well-typed:"
+    do
+        inferAndPrint (lambda ["x"] "x")
+        inferAndPrint (lambda ["f","g","x"] (apply "f" ["x", apply "g" ["x"]]))
+        inferAndPrint (lambda ["f","g","x"] (apply "f" [apply "g" ["x"]]))
+        inferAndPrint (lambda ["m", "k", "c"] (apply "m" [lambda ["x"] (apply "k" ["x", "c"])])) -- >>= for Cont
+        inferAndPrint (lambda ["f"] (apply "(.)" ["reverse", apply "map" ["f"]]))
+        inferAndPrint (apply "find" [lambda ["x"] (apply "(>)" ["x", int 0])])
+        inferAndPrint (apply "map" [apply "map" ["map"]])
+        inferAndPrint (apply "(*)" [int 1, int 2])
+        inferAndPrint (apply "foldr" ["(+)", int 0])
+        inferAndPrint (apply "map" ["length"])
+        inferAndPrint (apply "map" ["map"])
+        inferAndPrint (lambda ["x"] (apply "ifThenElse" [apply "(<)" ["x", int 0], int 0, "x"]))
+        inferAndPrint (lambda ["x"] (apply "fix" [lambda ["xs"] (apply "(:)" ["x", "xs"])]))
+    T.putStrLn "Ill-typed:"
+    do
+        inferAndPrint (apply "(*)" [int 1, bool True])
+        inferAndPrint (apply "foldr" [int 1])
+        inferAndPrint (lambda ["x"] (apply "x" ["x"]))
+        inferAndPrint (lambda ["x"] (ELet "xs" (apply "(:)" ["x", "xs"]) "xs"))
+
+
+
+-- | Build multiple lambda bindings.
+--
+-- Instead of
+--
+-- @
+-- EAbs "f" (EAbs "x" (EApp "f" "x"))
+-- @
+--
+-- we can write
+--
+-- @
+-- lambda ["f", "x"] (EApp "f" "x")
+-- @
+--
+-- for
+--
+-- @
+-- λf x. f x
+-- @
+lambda :: [Name] -> Exp -> Exp
+lambda names expr = foldr EAbs expr names
+
+
+
+-- | Apply a function to multiple arguments.
+--
+-- Instead of
+--
+-- @
+-- EApp (EApp (EApp "f" "x") "y") "z")
+-- @
+--
+-- we can write
+--
+-- @
+-- apply "f" ["x", "y", "z"]
+-- @
+--
+-- for
+--
+-- @
+-- f x y z
+-- @
+apply :: Exp -> [Exp] -> Exp
+apply = foldl EApp
+
+
+
+-- | Construct an integer literal.
+int :: Integer -> Exp
+int = ELit . LInteger
+
+
+
+-- | Construct a boolean literal.
+bool :: Bool -> Exp
+bool = ELit . LBool
+
+
+
+-- | Convenience function to run type inference algorithm
+showType :: Env    -- ^ Starting environment, e.g. 'prelude'.
+         -> Exp    -- ^ Expression to typecheck
+         -> Text   -- ^ Text representation of the result. Contains an error
+                   --   message on failure.
+showType env expr =
+    case (runInfer . fmap (generalize (Env mempty) . uncurry applySubst) . infer env) expr of
+        Left err -> "Error inferring type of " <> ppr expr <>": " <> ppr err
+        Right ty -> ppr expr <> " :: " <> ppr ty

README.md

@@ -1,21 +1,21 @@
-
 # Schala - a programming language meta-interpreter
 
-Schala is a Rust framework written to make it easy to
-create and experiment with toy programming languages. It provides
-a common REPL, and a trait `ProgrammingLanguage` with provisions 
-for tokenizing text, parsing tokens, evaluating an abstract syntax tree,
-and other tasks that are common to all programming languages.
+Schala is a Rust framework written to make it easy to create and experiment
+with toy programming languages. It provides a cross-language REPL and
+provisions for tokenizing text, parsing tokens, evaluating an abstract syntax
+tree, and other tasks that are common to all programming languages.
 
-Schala is implemented as a Rust library `schala_lib`, which provides a
-`schala_main` function. This function serves as the main loop of the REPL, if run
-interactively, or otherwise reads and interprets programming language source
-files. It expects as input a vector of `PLIGenerator`, which is a type representing
-a closure that returns a boxed trait object that implements the `ProgrammingLanguage` trait,
-and stores any persistent state relevant to that programming language. The ability
-to share state between different programming languages is in the works.
+Schala is implemented as a Rust library `schala-repl`, which provides a
+function `repl_main` meant to be used as the equivalent of main() for library
+users. This function parses command-line arguments and either runs an interactive
+REPL or interprets a program non-interactively.
 
-## About
+Individual programming language implementations are Rust types that implement
+the `ProgrammingLanguageInterface` trait and store whatever persistent state is
+relevant to that language. The ability to share state between different
+programming languages is in the works.
+
+## History
 
 Schala started out life as an experiment in writing a Javascript-like
 programming language that would never encounter any kind of runtime value
@@ -58,6 +58,9 @@ of learning how to write a programming language.
 
 ### Type-checking
 https://skillsmatter.com/skillscasts/10868-inside-the-rust-compiler
+https://www.youtube.com/watch?v=il3gD7XMdmA
+http://dev.stephendiehl.com/fun/006_hindley_milner.html
+https://rust-lang-nursery.github.io/rustc-guide/type-inference.html
 
 ### Evaluation
 *Understanding Computation*, Tom Stuart, O'Reilly 2013
@@ -66,6 +69,7 @@ https://skillsmatter.com/skillscasts/10868-inside-the-rust-compiler
 
 ### Parsing
 http://journal.stuffwithstuff.com/2011/03/19/pratt-parsers-expression-parsing-made-easy/
+https://soc.github.io/languages/unified-condition-syntax
 
 [Crafting Interpreters](http://www.craftinginterpreters.com/)
 
@@ -74,4 +78,5 @@ http://blog.ulysse.io/2016/07/03/llvm-getting-started.html
 
 ###Rust resources
 https://thefullsnack.com/en/rust-for-the-web.html
+
 https://rocket.rs/guide/getting-started/

TODO.md

@@ -1,6 +1,102 @@
+#Typechecking Notes
+
+(cf. cardelli paper)
+
+Given a length function def:
+````
+fn length(x) {
+ if x.is_null {
+   0
+  } else {
+   succ(length(x.tail))
+  }
+}
+````
+Constraints:
+.null: List a -> bool
+.tail: List a -> List a
+0: Nat
+succ: Nat -> Nat
+
+
+
 
 # TODO Items
 
+-make the REPL more advanced!
+
+-Plan of attack:
+  -write a visitor pattern for AST
+  -convert AST type to including SourceMap'd wrappers (w/ .into())
+    -at the same time, amke sure the visitor pattern "skips over" the SourceMap'd stuff
+    so it can just care about AST structure
+
+- AST : maybe replace the Expression type with "Ascription(TypeName, Box<Expression>) nodes??
+- parser: add a "debug" field to the Parser struct for all debug-related things
+
+-scala-style html"dfasfsadf${}" string interpolations!
+
+-fuzz test schala
+
+-look into Inkwell for LLVM
+
+
+*A neat idea for pattern matching optimization would be if you could match on one of several things in a list
+ex:
+if x {
+ is (comp, LHSPat, RHSPat) if comp in ["==, "<"] -> ...
+}
+
+
+- https://nshipster.com/never/
+-https://cranelift.readthedocs.io/en/latest/?badge=latest<Paste>
+
+-consult http://gluon-lang.org/book/embedding-api.html
+
+- if/match playground
+
+simple if
+`if x == 1.0 { "a" } else { "b" }`
+
+one comparison multiple targets:
+`if x == { 1.0 -> "a", 2.0 -> "b", else -> "c" }`
+
+different comparison operators/ method calls:
+`if x { == 1.0 -> "a", eq NaN -> "n", .hella() -> "h", else -> "z" }`
+
+pattern matching/introducing bindings:
+`if alice { .age < 18 -> "18", is Person("Alice", age) -> "${age}", else -> "none" }`
+
+pattern matching w/ if-let:
+`if person is Person("Alice", age) { "${age}" } else { "nope" }`
+
+-https://soc.github.io/languages/unified-condition-syntax syntax:
+
+`if <cond-expr>" then <then-expr> else <else-expr>`
+`if <half-expr> \n <rest-expr1> then <result1-expr> \n <rest-expr2> then <result-expr2> else <result3-expr>`
+-and rest-exprs (or "targets") can have 'is' for pattern-matching, actually so can a full cond-expr
+
+UNIFIED IF EXPRESSIONS FINAL WORK:
+
+basic syntax:
+
+`if_expr := if discriminator '{' (guard_expr)* '}'`
+`guard_expr := pattern 'then' block_or_expr'`
+`pattern := rhs | is_pattern`
+`is_pattern := 'is' ???`
+`rhs := expression | ???`
+
+
+if the only two guard patterns are true and false, then the abbreviated syntax:
+`'if' discriminator 'then' block_or_expr 'else' block_or_expr`
+can replace `'if' discriminator '{' 'true' 'then' block_or_expr; 'false' 'then' block_or_expr '}'`
+
+
+
+
+- Next priorities: - get ADTs working, get matches working
+
+- inclusive/exclusive range syntax like .. vs ..=
 
 - sketch of an idea for the REPL:
         -each compiler pass should be a (procedural?) macro like
@@ -44,10 +140,7 @@ type enum {
 
 
 
-- AST : maybe replace the Expression type with "Ascription(TypeName, Box<Expression>) nodes??
-- parser: add a "debug" field to the Parser struct for all debug-related things
 
--scala-style html"dfasfsadf${}" string interpolations!
 
 *Compiler passes architecture
 

maaru/src/compilation.rs

@@ -1,279 +0,0 @@
-extern crate llvm_sys;
-
-use std::collections::HashMap;
-
-use self::llvm_sys::prelude::*;
-use self::llvm_sys::{LLVMIntPredicate};
-
-use parser::{AST, Statement, Function, Prototype, Expression, BinOp};
-use schala_repl::LLVMCodeString;
-
-use schala_repl::llvm_wrap as LLVMWrap;
-
-type VariableMap = HashMap<String, LLVMValueRef>;
-
-struct CompilationData {
-    context: LLVMContextRef,
-    module: LLVMModuleRef,
-    builder: LLVMBuilderRef,
-    variables: VariableMap,
-    main_function: LLVMValueRef,
-    current_function: Option<LLVMValueRef>,
-}
-
-pub fn compile_ast(ast: AST) -> LLVMCodeString {
-    println!("Compiling!");
-    let names: VariableMap = HashMap::new();
-
-    let context = LLVMWrap::create_context();
-    let module = LLVMWrap::module_create_with_name("example module");
-    let builder = LLVMWrap::CreateBuilderInContext(context);
-
-    let program_return_type = LLVMWrap::Int64TypeInContext(context);
-    let main_function_type = LLVMWrap::FunctionType(program_return_type, Vec::new(), false);
-    let main_function: LLVMValueRef = LLVMWrap::AddFunction(module, "main", main_function_type);
-
-    let mut data = CompilationData {
-        context: context,
-        builder: builder,
-        module: module,
-        variables: names,
-        main_function: main_function,
-        current_function: None,
-    };
-
-    let bb = LLVMWrap::AppendBasicBlockInContext(data.context, data.main_function, "entry");
-    LLVMWrap::PositionBuilderAtEnd(builder, bb);
-
-    let value = ast.codegen(&mut data);
-
-    LLVMWrap::BuildRet(builder, value);
-
-    let ret = LLVMWrap::PrintModuleToString(module);
-
-    // Clean up. Values created in the context mostly get cleaned up there.
-    LLVMWrap::DisposeBuilder(builder);
-    LLVMWrap::DisposeModule(module);
-    LLVMWrap::ContextDispose(context);
-    LLVMCodeString(ret)
-}
-
-trait CodeGen {
-    fn codegen(&self, &mut CompilationData) -> LLVMValueRef;
-}
-
-impl CodeGen for AST {
-    fn codegen(&self, data: &mut CompilationData) -> LLVMValueRef {
-
-        let int_type = LLVMWrap::Int64TypeInContext(data.context);
-        let mut ret = LLVMWrap::ConstInt(int_type, 0, false);
-
-        for statement in self {
-            ret = statement.codegen(data);
-        }
-        ret
-    }
-}
-
-impl CodeGen for Statement {
-    fn codegen(&self, data: &mut CompilationData) -> LLVMValueRef {
-        use self::Statement::*;
-        match self {
-            &ExprNode(ref expr) => expr.codegen(data),
-            &FuncDefNode(ref func) => func.codegen(data),
-        }
-    }
-}
-
-impl CodeGen for Function {
-    fn codegen(&self, data: &mut CompilationData) -> LLVMValueRef {
-
-        /* should have a check here for function already being defined */
-        let function = self.prototype.codegen(data);
-        let ref body = self.body;
-
-        data.current_function = Some(function);
-
-        let return_type = LLVMWrap::Int64TypeInContext(data.context);
-        let mut ret = LLVMWrap::ConstInt(return_type, 0, false);
-
-        let block = LLVMWrap::AppendBasicBlockInContext(data.context, function, "entry");
-        LLVMWrap::PositionBuilderAtEnd(data.builder, block);
-
-        //insert function params into variables
-        for value in LLVMWrap::GetParams(function) {
-            let name = LLVMWrap::GetValueName(value);
-            data.variables.insert(name, value);
-        }
-
-        for expr in body {
-            ret = expr.codegen(data);
-        }
-
-        LLVMWrap::BuildRet(data.builder, ret);
-
-        // get basic block of main
-        let main_bb = LLVMWrap::GetBasicBlocks(data.main_function).get(0).expect("Couldn't get first block of main").clone();
-        LLVMWrap::PositionBuilderAtEnd(data.builder, main_bb);
-
-        data.current_function = None;
-
-        ret
-    }
-}
-
-impl CodeGen for Prototype {
-    fn codegen(&self, data: &mut CompilationData) -> LLVMValueRef {
-        let num_args = self.parameters.len();
-        let return_type = LLVMWrap::Int64TypeInContext(data.context);
-        let mut arguments: Vec<LLVMTypeRef> = vec![];
-
-        for _ in 0..num_args {
-            arguments.push(LLVMWrap::Int64TypeInContext(data.context));
-        }
-
-        let function_type =
-            LLVMWrap::FunctionType(return_type,
-                                   arguments,
-                                   false);
-
-        let function = LLVMWrap::AddFunction(data.module,
-                                             &*self.name,
-                                             function_type);
-
-        let function_params = LLVMWrap::GetParams(function);
-        for (index, param) in function_params.iter().enumerate() {
-            let name = self.parameters.get(index).expect(&format!("Failed this check at index {}", index));
-            let new = *param;
-
-            LLVMWrap::SetValueName(new, name);
-        }
-
-        function
-    }
-}
-
-impl CodeGen for Expression {
-    fn codegen(&self, data: &mut CompilationData) -> LLVMValueRef {
-        use self::BinOp::*;
-        use self::Expression::*;
-
-        let int_type = LLVMWrap::Int64TypeInContext(data.context);
-        let zero = LLVMWrap::ConstInt(int_type, 0, false);
-
-        match *self {
-            Variable(ref name) => *data.variables.get(&**name).expect(&format!("Can't find variable {}", name)),
-            BinExp(Assign, ref left, ref right) => {
-                if let Variable(ref name) = **left {
-                    let new_value = right.codegen(data);
-                    data.variables.insert((**name).clone(), new_value);
-                    new_value
-                } else {
-                    panic!("Bad variable assignment")
-                }
-            }
-            BinExp(ref op, ref left, ref right) => {
-                let lhs = left.codegen(data);
-                let rhs = right.codegen(data);
-                op.codegen_with_ops(data, lhs, rhs)
-            }
-            Number(ref n) => {
-                let native_val = *n as u64;
-                let int_value: LLVMValueRef = LLVMWrap::ConstInt(int_type, native_val, false);
-                int_value
-            }
-            Conditional(ref test, ref then_expr, ref else_expr) => {
-                let condition_value = test.codegen(data);
-                let is_nonzero =
-                    LLVMWrap::BuildICmp(data.builder,
-                                        LLVMIntPredicate::LLVMIntNE,
-                                        condition_value,
-                                        zero,
-                                        "ifcond");
-
-                let func = LLVMWrap::GetBasicBlockParent(LLVMWrap::GetInsertBlock(data.builder));
-
-                let mut then_block =
-                    LLVMWrap::AppendBasicBlockInContext(data.context, func, "then_block");
-                let mut else_block =
-                    LLVMWrap::AppendBasicBlockInContext(data.context, func, "else_block");
-                let merge_block =
-                    LLVMWrap::AppendBasicBlockInContext(data.context, func, "ifcont");
-
-                // add conditional branch to ifcond block
-                LLVMWrap::BuildCondBr(data.builder, is_nonzero, then_block, else_block);
-
-                // start inserting into then block
-                LLVMWrap::PositionBuilderAtEnd(data.builder, then_block);
-
-                // then-block codegen
-                let then_return = then_expr.codegen(data);
-                LLVMWrap::BuildBr(data.builder, merge_block);
-
-                // update then block b/c recursive codegen() call may have changed the notion of
-                // the current block
-                then_block = LLVMWrap::GetInsertBlock(data.builder);
-
-                // then do the same stuff again for the else branch
-                //
-                LLVMWrap::PositionBuilderAtEnd(data.builder, else_block);
-                let else_return = match *else_expr {
-                    Some(ref e) => e.codegen(data),
-                    None => zero,
-                };
-                LLVMWrap::BuildBr(data.builder, merge_block);
-                else_block = LLVMWrap::GetInsertBlock(data.builder);
-
-                LLVMWrap::PositionBuilderAtEnd(data.builder, merge_block);
-
-                let phi = LLVMWrap::BuildPhi(data.builder, int_type, "phinode");
-                let values = vec![then_return, else_return];
-                let blocks = vec![then_block, else_block];
-                LLVMWrap::AddIncoming(phi, values, blocks);
-                phi
-            }
-            Block(ref exprs) => {
-                let mut ret = zero;
-                for e in exprs.iter() {
-                    ret = e.codegen(data);
-                }
-                ret
-            }
-            ref e => {
-                println!("Unimplemented {:?}", e);
-                unimplemented!()
-            }
-        }
-    }
-}
-
-impl BinOp {
-    fn codegen_with_ops(&self, data: &CompilationData, lhs: LLVMValueRef, rhs: LLVMValueRef) -> LLVMValueRef {
-        use self::BinOp::*;
-        macro_rules! simple_binop {
-            ($fnname: expr, $name: expr) => {
-                $fnname(data.builder, lhs, rhs, $name)
-            }
-        }
-        let int_type = LLVMWrap::Int64TypeInContext(data.context);
-        match *self {
-            Add => simple_binop!(LLVMWrap::BuildAdd, "addtemp"),
-            Sub => simple_binop!(LLVMWrap::BuildSub, "subtemp"),
-            Mul => simple_binop!(LLVMWrap::BuildMul, "multemp"),
-            Div => simple_binop!(LLVMWrap::BuildUDiv, "divtemp"),
-            Mod => simple_binop!(LLVMWrap::BuildSRem, "remtemp"),
-            Less => {
-                let pred: LLVMValueRef =
-                    LLVMWrap::BuildICmp(data.builder, LLVMIntPredicate::LLVMIntULT, lhs, rhs, "tmp");
-                LLVMWrap::BuildZExt(data.builder, pred, int_type, "temp")
-            }
-            Greater => {
-                let pred: LLVMValueRef =
-                    LLVMWrap::BuildICmp(data.builder, LLVMIntPredicate::LLVMIntUGT, lhs, rhs, "tmp");
-                LLVMWrap::BuildZExt(data.builder, pred, int_type, "temp")
-            }
-            ref unknown => panic!("Bad operator {:?}", unknown),
-        }
-    }
-}
-

maaru/src/lib.rs

@@ -5,9 +5,8 @@ extern crate schala_repl;
 mod tokenizer;
 mod parser;
 mod eval;
-mod compilation;
 
-use schala_repl::{ProgrammingLanguageInterface, EvalOptions, LanguageOutput, TraceArtifact};
+use schala_repl::{ProgrammingLanguageInterface, EvalOptions, UnfinishedComputation, FinishedComputation, TraceArtifact};
 
 #[derive(Debug)]
 pub struct TokenError {
@@ -42,65 +41,36 @@ impl<'a> ProgrammingLanguageInterface for Maaru<'a> {
     format!("maaru")
   }
 
-  fn evaluate_in_repl(&mut self, input: &str, options: &EvalOptions) -> LanguageOutput {
-    let mut output = LanguageOutput::default();
+  fn execute_pipeline(&mut self, input: &str, options: &EvalOptions) -> FinishedComputation {
+    let mut output = UnfinishedComputation::default();
 
     let tokens = match tokenizer::tokenize(input) {
       Ok(tokens) => {
-        if options.debug.tokens {
+        if let Some(_) = options.debug_passes.get("tokens") {
           output.add_artifact(TraceArtifact::new("tokens", format!("{:?}", tokens)));
         }
         tokens
       },
       Err(err) => {
-        output.add_output(format!("Tokenization error: {:?}\n", err.msg));
-        return output;
+        return output.finish(Err(format!("Tokenization error: {:?}\n", err.msg)))
       }
     };
 
     let ast = match parser::parse(&tokens, &[]) {
       Ok(ast) => {
-        if options.debug.ast {
+        if let Some(_) = options.debug_passes.get("ast") {
           output.add_artifact(TraceArtifact::new("ast", format!("{:?}", ast)));
         }
         ast
       },
       Err(err) => {
-        output.add_output(format!("Parse error: {:?}\n", err.msg));
-        return output;
+        return output.finish(Err(format!("Parse error: {:?}\n", err.msg)))
       }
     };
     let mut evaluation_output = String::new();
     for s in self.evaluator.run(ast).iter() {
       evaluation_output.push_str(s);
     }
-    output.add_output(evaluation_output);
-    return output;
+    output.finish(Ok(evaluation_output))
   }
-
-  /* TODO make this work with new framework */
-  /*
-  fn can_compile(&self) -> bool {
-    true
-  }
-
-  fn compile(&mut self, input: &str) -> LLVMCodeString {
-    let tokens = match tokenizer::tokenize(input) {
-      Ok(tokens) =>  tokens,
-      Err(err) => {
-        let msg = format!("Tokenization error: {:?}\n", err.msg);
-        panic!("{}", msg);
-      }
-    };
-
-    let ast = match parser::parse(&tokens, &[]) {
-      Ok(ast) => ast,
-      Err(err) => {
-        let msg = format!("Parse error: {:?}\n", err.msg);
-        panic!("{}", msg);
-      }
-    };
-    compilation::compile_ast(ast)
-  }
-  */
 }

robo/src/lib.rs

@@ -4,7 +4,7 @@ extern crate itertools;
 extern crate schala_repl;
 
 use itertools::Itertools;
-use schala_repl::{ProgrammingLanguageInterface, EvalOptions, LanguageOutput};
+use schala_repl::{ProgrammingLanguageInterface, EvalOptions, FinishedComputation, UnfinishedComputation};
 
 pub struct Robo {
 }
@@ -155,18 +155,16 @@ impl ProgrammingLanguageInterface for Robo {
     format!("robo")
   }
 
-  fn evaluate_in_repl(&mut self, input: &str, _eval_options: &EvalOptions) -> LanguageOutput {
-    let mut output = LanguageOutput::default();
+  fn execute_pipeline(&mut self, input: &str, _eval_options: &EvalOptions) -> FinishedComputation {
+    let output = UnfinishedComputation::default();
     let tokens = match tokenize(input) {
       Ok(tokens) => tokens,
       Err(e) => {
-        output.add_output(format!("Tokenize error: {:?}", e));
-        return output;
+        return output.finish(Err(format!("Tokenize error: {:?}", e)));
       }
     };
 
-    output.add_output(format!("{:?}", tokens));
-    output
+    output.finish(Ok(format!("{:?}", tokens)))
   }
 }
 

rukka/src/lib.rs

@@ -4,7 +4,7 @@ extern crate itertools;
 extern crate schala_repl;
 
 use itertools::Itertools;
-use schala_repl::{ProgrammingLanguageInterface, EvalOptions, LanguageOutput};
+use schala_repl::{ProgrammingLanguageInterface, EvalOptions, UnfinishedComputation, FinishedComputation};
 use std::iter::Peekable;
 use std::vec::IntoIter;
 use std::str::Chars;
@@ -73,12 +73,11 @@ impl ProgrammingLanguageInterface for Rukka {
     format!("rukka")
   }
 
-  fn evaluate_in_repl(&mut self, input: &str, _eval_options: &EvalOptions) -> LanguageOutput {
-    let mut output = LanguageOutput::default();
+  fn execute_pipeline(&mut self, input: &str, _eval_options: &EvalOptions) -> FinishedComputation {
+    let output = UnfinishedComputation::default();
     let sexps = match read(input) {
       Err(err) => {
-        output.add_output(format!("Error: {}", err));
-        return output;
+        return output.finish(Err(format!("Error: {}", err)));
       },
       Ok(sexps) => sexps
     };
@@ -89,8 +88,7 @@ impl ProgrammingLanguageInterface for Rukka {
         Err(err) => format!("{} Error: {}", i, err),
       }
     }).intersperse(format!("\n")).collect();
-    output.add_output(output_str);
-    output
+    output.finish(Ok(output_str))
   }
 }
 

schala-codegen/Cargo.toml

@@ -1,12 +0,0 @@
-[package]
-name = "schala-codegen"
-version = "0.1.0"
-authors = ["greg <greg.shuflin@protonmail.com>"]
-
-[dependencies]
-quote = "0.5.2"
-syn = { version = "0.13.1", features = ["full", "extra-traits"] }
-
-
-[lib]
-proc-macro = true

schala-codegen/src/lib.rs

@@ -1,95 +0,0 @@
-#![feature(proc_macro)]
-extern crate proc_macro;
-#[macro_use]
-extern crate syn;
-#[macro_use]
-extern crate quote;
-
-use proc_macro::TokenStream;
-use syn::{Expr, Lit, ExprLit};
-use syn::punctuated::Punctuated;
-use syn::synom::Synom;
-
-
-fn get_string_args(input: Expr) -> Vec<String> {
-  let mut contained_strings = Vec::new();
-  match input {
-    Expr::Array(array) => {
-      for item in array.elems {
-        if let Expr::Lit(ExprLit { lit: Lit::Str(s), ..}) = item {
-          contained_strings.push(s.value());
-        } else {
-          panic!("Non-string-literal input to compiler_pass_sequence");
-        }
-      }
-    },
-    _ => panic!("Non-array input to compiler_pass_sequence"),
-  }
-  contained_strings
-}
-
-#[proc_macro]
-pub fn compiler_pass_sequence(input: TokenStream) -> TokenStream {
-  /*
-  for token_tree in input {
-    //println!("ITEM: {:?}", token_tree.kind);
-    match token_tree.kind {
-      TokenNode::Literal(l) => println!("{:?}", l),
-      _ => ()
-    }
-  }
-  */
-
-  let input: Expr = syn::parse(input).unwrap();
-  let stages = get_string_args(input);
-  let from_macro = format!("{:?}", stages);
-
-  let output = quote! {
-    fn new_execute(&mut self, input: &str, _options: &EvalOptions) -> FinishedComputation {
-      let evaluation = UnfinishedComputation::default();
-      evaluation.output(Err(#from_macro.to_string()))
-    }
-  };
-  output.into()
-}
-
-/* #[compiler_pass(<name of pass>*/
-#[proc_macro_attribute]
-pub fn compiler_pass(metadata: TokenStream, function: TokenStream) -> TokenStream {
-  //println!("FROM MACRO: {}", function);
-  println!("Compiler pass metadata: {}", metadata);
-  function
-}
-
-#[cfg(test)]
-mod tests {
-    #[test]
-    fn it_works() {
-        assert_eq!(2 + 2, 4);
-    }
-}
-
-
-/* in Rocket
- *
-
- #[get("/")]
- fn hi() -> &'static str {
- "hello"
- }
-
- GETS MAPPED TO:
-
- static hi_info = RouteInfo {
-  name: "hi",
-  method: Method::Get,
-  path: "/",
-  handler: hi_route,
-  }
-
-  fn hi_route(req: &Request) -> Outcome {
-  let responder = hi();
-  Outcome::from(req, responder);
-  }
-
- */

schala-lang/codegen/Cargo.toml

@@ -0,0 +1,12 @@
+[package]
+name = "schala-lang-codegen"
+version = "0.1.0"
+authors = ["greg <greg.shuflin@protonmail.com>"]
+edition = "2018"
+
+[lib]
+proc-macro = true
+
+[dependencies]
+syn = { version = "0.15.12", features = ["full", "extra-traits", "fold"] }
+quote = "0.6.8"

schala-lang/codegen/src/lib.rs

@@ -0,0 +1,50 @@
+#![feature(box_patterns)]
+#![recursion_limit="128"]
+extern crate proc_macro;
+#[macro_use]
+extern crate quote;
+#[macro_use]
+extern crate syn;
+
+use self::proc_macro::TokenStream;
+use self::syn::fold::Fold;
+
+struct RecursiveDescentFn {
+}
+
+impl Fold for RecursiveDescentFn {
+  fn fold_item_fn(&mut self, mut i: syn::ItemFn) -> syn::ItemFn {
+    let box block = i.block;
+    let ref ident = i.ident;
+
+    let new_block: syn::Block = parse_quote! {
+      {
+        let next_token_before_parse = self.token_handler.peek();
+        let record = ParseRecord {
+          production_name: stringify!(#ident).to_string(),
+          next_token: format!("{}", next_token_before_parse.to_string_with_metadata()),
+          level: self.parse_level,
+        };
+        self.parse_level += 1;
+        self.parse_record.push(record);
+        let result = { #block };
+
+        if self.parse_level != 0 {
+          self.parse_level -= 1;
+        }
+        result
+      }
+    };
+    i.block = Box::new(new_block);
+    i
+  }
+}
+
+#[proc_macro_attribute]
+pub fn recursive_descent_method(_attr: TokenStream, item: TokenStream) -> TokenStream {
+
+  let input: syn::ItemFn = parse_macro_input!(item as syn::ItemFn);
+  let mut folder = RecursiveDescentFn {};
+  let output = folder.fold_item_fn(input);
+  TokenStream::from(quote!(#output))
+}

schala-lang/language/Cargo.toml

@@ -2,12 +2,16 @@
 name = "schala-lang"
 version = "0.1.0"
 authors = ["greg <greg.shuflin@protonmail.com>"]
+edition = "2018"
 
 [dependencies]
 itertools = "0.5.8"
 take_mut = "0.1.3"
 maplit = "*"
 lazy_static = "0.2.8"
+failure = "0.1.2"
 
-schala-repl = { path = "../schala-repl" }
-schala-codegen = { path = "../schala-codegen" }
+
+schala-lang-codegen = { path = "../codegen" }
+schala-repl = { path = "../../schala-repl" }
+schala-repl-codegen = { path = "../../schala-repl-codegen" }

schala-lang/language/src/ast.rs

@@ -0,0 +1,212 @@
+use std::rc::Rc;
+use std::convert::From;
+
+use crate::builtin::{BinOp, PrefixOp};
+
+#[derive(Clone, Debug, PartialEq)]
+pub struct Node<T> {
+  n: T,
+  source_map: SourceMap
+}
+
+impl<T> Node<T> {
+  pub fn new(n: T) -> Node<T> {
+    Node { n, source_map: SourceMap::default() }
+  }
+
+  pub fn node(&self) -> &T {
+    &self.n
+  }
+}
+
+//TODO this PartialEq is here to make tests work - find a way to make it not necessary
+#[derive(Clone, Debug, Default, PartialEq)]
+struct SourceMap {
+}
+
+impl From<Expression> for Node<Expression> {
+  fn from(expr: Expression) -> Node<Expression> {
+    Node { n: expr, source_map: SourceMap::default() }
+  }
+}
+
+#[derive(Debug, PartialEq)]
+pub struct AST(pub Vec<Node<Statement>>);
+
+#[derive(Debug, PartialEq, Clone)]
+pub enum Statement {
+  ExpressionStatement(Node<Expression>),
+  Declaration(Declaration),
+}
+
+pub type Block = Vec<Node<Statement>>;
+pub type ParamName = Rc<String>;
+pub type FormalParam = (ParamName, Option<TypeIdentifier>);
+
+#[derive(Debug, PartialEq, Clone)]
+pub enum Declaration {
+  FuncSig(Signature),
+  FuncDecl(Signature, Block),
+  TypeDecl {
+    name: TypeSingletonName,
+    body: TypeBody,
+    mutable: bool
+  },
+  TypeAlias(Rc<String>, Rc<String>), //should have TypeSingletonName in it, or maybe just String, not sure
+  Binding {
+    name: Rc<String>,
+    constant: bool,
+    expr: Expression,
+  },
+  Impl {
+    type_name: TypeIdentifier,
+    interface_name: Option<TypeSingletonName>,
+    block: Vec<Declaration>,
+  },
+  Interface {
+    name: Rc<String>,
+    signatures: Vec<Signature>
+  }
+}
+
+#[derive(Debug, PartialEq, Clone)]
+pub struct Signature {
+  pub name: Rc<String>,
+  pub operator: bool,
+  pub params: Vec<FormalParam>,
+  pub type_anno: Option<TypeIdentifier>,
+}
+
+#[derive(Debug, PartialEq, Clone)]
+pub struct TypeBody(pub Vec<Variant>);
+
+#[derive(Debug, PartialEq, Clone)]
+pub enum Variant {
+  UnitStruct(Rc<String>),
+  TupleStruct(Rc<String>, Vec<TypeIdentifier>),
+  Record {
+    name: Rc<String>,
+    members: Vec<(Rc<String>, TypeIdentifier)>,
+  }
+}
+
+#[derive(Debug, PartialEq, Clone)]
+pub struct Expression(pub ExpressionType, pub Option<TypeIdentifier>);
+
+
+#[derive(Debug, PartialEq, Clone)]
+pub enum TypeIdentifier {
+  Tuple(Vec<TypeIdentifier>),
+  Singleton(TypeSingletonName)
+}
+
+#[derive(Debug, PartialEq, Clone)]
+pub struct TypeSingletonName {
+  pub name: Rc<String>,
+  pub params: Vec<TypeIdentifier>,
+}
+
+#[derive(Debug, PartialEq, Clone)]
+pub enum ExpressionType {
+  NatLiteral(u64),
+  FloatLiteral(f64),
+  StringLiteral(Rc<String>),
+  BoolLiteral(bool),
+  BinExp(BinOp, Box<Node<Expression>>, Box<Node<Expression>>),
+  PrefixExp(PrefixOp, Box<Node<Expression>>),
+  TupleLiteral(Vec<Node<Expression>>),
+  Value(Rc<String>),
+  NamedStruct {
+    name: Rc<String>,
+    fields: Vec<(Rc<String>, Expression)>,
+  },
+  Call {
+    f: Box<Expression>,
+    arguments: Vec<Node<Expression>>,
+  },
+  Index {
+    indexee: Box<Expression>,
+    indexers: Vec<Expression>,
+  },
+  IfExpression {
+    discriminator: Box<Discriminator>,
+    body: Box<IfExpressionBody>,
+  },
+  WhileExpression {
+    condition: Option<Box<Expression>>,
+    body: Block,
+  },
+  ForExpression {
+    enumerators: Vec<Enumerator>,
+    body: Box<ForBody>,
+  },
+  Lambda {
+    params: Vec<FormalParam>,
+    type_anno: Option<TypeIdentifier>,
+    body: Block,
+  },
+  ListLiteral(Vec<Expression>),
+}
+
+#[derive(Debug, PartialEq, Clone)]
+pub enum Discriminator {
+  Simple(Expression),
+  BinOp(Expression, BinOp)
+}
+
+#[derive(Debug, PartialEq, Clone)]
+pub enum IfExpressionBody {
+  SimpleConditional(Block, Option<Block>),
+  SimplePatternMatch(Pattern, Block, Option<Block>),
+  GuardList(Vec<GuardArm>)
+}
+
+#[derive(Debug, PartialEq, Clone)]
+pub struct GuardArm {
+  pub guard: Guard,
+  pub body: Block,
+}
+
+#[derive(Debug, PartialEq, Clone)]
+pub enum Guard {
+  Pat(Pattern),
+  HalfExpr(HalfExpr)
+}
+
+#[derive(Debug, PartialEq, Clone)]
+pub struct HalfExpr {
+  pub op: Option<BinOp>,
+  pub expr: ExpressionType,
+}
+
+#[derive(Debug, PartialEq, Clone)]
+pub enum Pattern {
+  Ignored,
+  TuplePattern(Vec<Pattern>),
+  Literal(PatternLiteral),
+  TupleStruct(Rc<String>, Vec<Pattern>),
+  Record(Rc<String>, Vec<(Rc<String>, Pattern)>),
+}
+
+#[derive(Debug, PartialEq, Clone)]
+pub enum PatternLiteral {
+  NumPattern {
+    neg: bool,
+    num: ExpressionType,
+  },
+  StringPattern(Rc<String>),
+  BoolPattern(bool),
+  VarPattern(Rc<String>)
+}
+
+#[derive(Debug, PartialEq, Clone)]
+pub struct Enumerator {
+  pub id: Rc<String>,
+  pub generator: Expression,
+}
+
+#[derive(Debug, PartialEq, Clone)]
+pub enum ForBody {
+  MonadicReturn(Expression),
+  StatementBlock(Block),
+}

schala-lang/language/src/builtin.rs

@@ -0,0 +1,145 @@
+use std::rc::Rc;
+use std::collections::HashMap;
+use std::fmt;
+
+use crate::tokenizing::TokenKind;
+use self::BuiltinTypeSpecifier::*;
+use self::BuiltinTConst::*;
+
+
+#[derive(Debug, PartialEq, Clone)]
+pub enum BuiltinTypeSpecifier {
+  Const(BuiltinTConst),
+  Func(Box<BuiltinTypeSpecifier>, Box<BuiltinTypeSpecifier>),
+}
+
+#[derive(Debug, PartialEq, Clone)]
+pub enum BuiltinTConst {
+  Nat,
+  Int,
+  Float,
+  StringT,
+  Bool,
+}
+
+impl fmt::Display for BuiltinTypeSpecifier {
+  fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
+    write!(f, "{:?}", self)
+  }
+}
+
+#[derive(Debug, PartialEq, Clone)]
+pub struct BinOp {
+  sigil: Rc<String>
+}
+
+impl BinOp {
+  pub fn from_sigil(sigil: &str) -> BinOp {
+    BinOp { sigil: Rc::new(sigil.to_string()) }
+  }
+  pub fn sigil(&self) -> &Rc<String> {
+    &self.sigil
+  }
+  pub fn from_sigil_token(tok: &TokenKind) -> Option<BinOp> {
+    use self::TokenKind::*;
+    let s = match tok {
+      Operator(op) => op,
+      Period => ".",
+      Pipe => "|",
+      Slash => "/",
+      LAngleBracket => "<",
+      RAngleBracket => ">",
+      _ => return None
+    };
+    Some(BinOp::from_sigil(s))
+  }
+  /*
+  pub fn get_type(&self) -> Result<Type, String> {
+    let s = self.sigil.as_str();
+    BINOPS.get(s).map(|x| x.0.clone()).ok_or(format!("Binop {} not found", s))
+  }
+  */
+  pub fn min_precedence() -> i32 {
+    i32::min_value()
+  }
+  pub fn get_precedence_from_token(op: &TokenKind) -> Option<i32> {
+    use self::TokenKind::*;
+    let s = match op {
+      Operator(op) => op,
+      Period => ".",
+      Pipe => "|",
+      Slash => "/",
+      LAngleBracket => "<",
+      RAngleBracket => ">",
+      _ => return None
+    };
+    let default = 10_000_000;
+    Some(BINOPS.get(s).map(|x| x.2.clone()).unwrap_or_else(|| {
+      default
+    }))
+  }
+
+  pub fn get_precedence(&self) -> i32 {
+    let s: &str = &self.sigil;
+    let default = 10_000_000;
+    BINOPS.get(s).map(|x| x.2.clone()).unwrap_or_else(|| {
+      default
+    })
+  }
+}
+
+#[derive(Debug, PartialEq, Clone)]
+pub struct PrefixOp {
+  sigil: Rc<String>
+}
+
+impl PrefixOp {
+  pub fn from_sigil(sigil: &str) -> PrefixOp {
+    PrefixOp { sigil: Rc::new(sigil.to_string()) }
+  }
+  pub fn sigil(&self) -> &Rc<String> {
+    &self.sigil
+  }
+  pub fn is_prefix(op: &str) -> bool {
+    PREFIX_OPS.get(op).is_some()
+  }
+  /*
+  pub fn get_type(&self) -> Result<Type, String> {
+    let s = self.sigil.as_str();
+    PREFIX_OPS.get(s).map(|x| x.0.clone()).ok_or(format!("Prefix op {} not found", s))
+  }
+  */
+}
+lazy_static! {
+  static ref PREFIX_OPS: HashMap<&'static str, (BuiltinTypeSpecifier, ())> = 
+    hashmap! {
+      "+" => (Func(bx!(Const(Int)),  bx!(Const(Int))), ()),
+      "-" => (Func(bx!(Const(Int)),  bx!(Const(Int))), ()),
+      "!" => (Func(bx!(Const(Bool)),  bx!(Const(Bool))), ()),
+    };
+}
+
+/* the second tuple member is a placeholder for when I want to make evaluation rules tied to the
+ * binop definition */
+lazy_static! {
+  static ref BINOPS: HashMap<&'static str, (BuiltinTypeSpecifier, (), i32)> =
+    hashmap! {
+      "+" => (Func(bx!(Const(Nat)), bx!(Func(bx!(Const(Nat)), bx!(Const(Nat))))), (), 10),
+      "-" => (Func(bx!(Const(Nat)), bx!(Func(bx!(Const(Nat)), bx!(Const(Nat))))), (), 10),
+      "*" => (Func(bx!(Const(Nat)), bx!(Func(bx!(Const(Nat)), bx!(Const(Nat))))), (), 20),
+      "/" => (Func(bx!(Const(Nat)), bx!(Func(bx!(Const(Nat)), bx!(Const(Float))))), (), 20),
+      "quot" => (Func(bx!(Const(Nat)), bx!(Func(bx!(Const(Nat)), bx!(Const(Nat))))), (), 20),
+      "%" => (Func(bx!(Const(Nat)), bx!(Func(bx!(Const(Nat)), bx!(Const(Nat))))), (), 20),
+      "++" => (Func(bx!(Const(StringT)), bx!(Func(bx!(Const(StringT)), bx!(Const(StringT))))), (), 30),
+      "^" => (Func(bx!(Const(Nat)), bx!(Func(bx!(Const(Nat)), bx!(Const(Nat))))), (), 20),
+      "&" => (Func(bx!(Const(Nat)), bx!(Func(bx!(Const(Nat)), bx!(Const(Nat))))), (), 20),
+      "|" => (Func(bx!(Const(Nat)), bx!(Func(bx!(Const(Nat)), bx!(Const(Nat))))), (), 20),
+      ">" => (Func(bx!(Const(Nat)), bx!(Func(bx!(Const(Nat)), bx!(Const(Nat))))), (), 20),
+      ">=" => (Func(bx!(Const(Nat)), bx!(Func(bx!(Const(Nat)), bx!(Const(Nat))))), (), 20),
+      "<" => (Func(bx!(Const(Nat)), bx!(Func(bx!(Const(Nat)), bx!(Const(Nat))))), (), 20),
+      "<=" => (Func(bx!(Const(Nat)), bx!(Func(bx!(Const(Nat)), bx!(Const(Nat))))), (), 20),
+      "==" => (Func(bx!(Const(Nat)), bx!(Func(bx!(Const(Nat)), bx!(Const(Nat))))), (), 20),
+      "=" => (Func(bx!(Const(Nat)), bx!(Func(bx!(Const(Nat)), bx!(Const(Nat))))), (), 20),
+      "<=>" => (Func(bx!(Const(Nat)), bx!(Func(bx!(Const(Nat)), bx!(Const(Nat))))), (), 20),
+    };
+}

schala-lang/language/src/eval.rs

@@ -0,0 +1,748 @@
+
+use std::cell::RefCell;
+use std::rc::Rc;
+use std::fmt::Write;
+use std::io;
+
+use itertools::Itertools;
+
+use crate::util::ScopeStack;
+use crate::reduced_ast::{BoundVars, ReducedAST, Stmt, Expr, Lit, Func, Alternative, Subpattern};
+use crate::symbol_table::{SymbolSpec, Symbol, SymbolTable};
+
+pub struct State<'a> {
+  values: ScopeStack<'a, Rc<String>, ValueEntry>,
+  symbol_table_handle: Rc<RefCell<SymbolTable>>,
+}
+
+macro_rules! builtin_binding {
+  ($name:expr, $values:expr) => {
+    $values.insert(Rc::new(format!($name)), ValueEntry::Binding { constant: true, val: Node::Expr(Expr::Func(Func::BuiltIn(Rc::new(format!($name))))) });
+  }
+}
+
+impl<'a> State<'a> {
+  pub fn new(symbol_table_handle: Rc<RefCell<SymbolTable>>) -> State<'a> {
+    let mut values = ScopeStack::new(Some(format!("global")));
+    builtin_binding!("print", values);
+    builtin_binding!("println", values);
+    builtin_binding!("getline", values);
+    State { values, symbol_table_handle }
+  }
+
+  pub fn debug_print(&self) -> String {
+    format!("Values: {:?}", self.values)
+  }
+
+  fn new_frame(&'a self, items: &'a Vec<Node>, bound_vars: &BoundVars) -> State<'a> {
+    let mut inner_state = State {
+      values: self.values.new_scope(None),
+      symbol_table_handle: self.symbol_table_handle.clone(),
+    };
+    for (bound_var, val) in bound_vars.iter().zip(items.iter()) {
+      if let Some(bv) = bound_var.as_ref() {
+        inner_state.values.insert(bv.clone(), ValueEntry::Binding { constant: true, val: val.clone() });
+      }
+    }
+    inner_state
+  }
+}
+
+#[derive(Debug, Clone)]
+enum Node {
+  Expr(Expr),
+  PrimObject {
+    name: Rc<String>,
+    tag: usize,
+    items: Vec<Node>,
+  },
+  PrimTuple {
+    items: Vec<Node>
+  }
+}
+
+fn paren_wrapped_vec(terms: impl Iterator<Item=String>) -> String {
+  let mut buf = String::new();
+  write!(buf, "(").unwrap();
+  for term in terms.map(|e| Some(e)).intersperse(None) {
+    match term {
+      Some(e) => write!(buf, "{}", e).unwrap(),
+      None => write!(buf, ", ").unwrap(),
+    };
+  }
+  write!(buf, ")").unwrap();
+  buf
+}
+
+
+impl Node {
+  fn to_repl(&self) -> String {
+    match self {
+      Node::Expr(e) => e.to_repl(),
+      Node::PrimObject { name, items, .. } if items.len() == 0 => format!("{}", name),
+      Node::PrimObject { name, items, .. } => format!("{}{}", name, paren_wrapped_vec(items.iter().map(|x| x.to_repl()))),
+      Node::PrimTuple { items } => format!("{}", paren_wrapped_vec(items.iter().map(|x| x.to_repl()))),
+    }
+  }
+  fn is_true(&self) -> bool {
+    match self {
+      Node::Expr(Expr::Lit(crate::reduced_ast::Lit::Bool(true))) => true,
+      _ => false,
+    }
+  }
+}
+
+#[derive(Debug)]
+enum ValueEntry {
+  Binding {
+    constant: bool,
+    val: /*FullyEvaluatedExpr*/ Node, //TODO make this use a subtype to represent fully evaluatedness
+  }
+}
+
+type EvalResult<T> = Result<T, String>;
+
+impl Expr {
+  fn to_node(self) -> Node {
+    Node::Expr(self)
+  }
+  fn to_repl(&self) -> String {
+    use self::Lit::*;
+    use self::Func::*;
+
+    match self {
+      Expr::Lit(ref l) => match l {
+        Nat(n) => format!("{}", n),
+        Int(i) => format!("{}", i),
+        Float(f) => format!("{}", f),
+        Bool(b) => format!("{}", b),
+        StringLit(s) => format!("\"{}\"", s),
+      },
+      Expr::Func(f) => match f {
+        BuiltIn(name) => format!("<built-in function '{}'>", name),
+        UserDefined { name: None, .. } => format!("<function>"),
+        UserDefined { name: Some(name), .. } => format!("<function '{}'>", name),
+      },
+      Expr::Constructor { 
+        type_name: _, name, arity, ..
+      } => if *arity == 0 {
+        format!("{}", name)
+      } else {
+        format!("<data constructor '{}'>", name)
+      },
+      Expr::Tuple(exprs) => paren_wrapped_vec(exprs.iter().map(|x| x.to_repl())),
+      _ => format!("{:?}", self),
+    }
+  }
+
+  fn replace_conditional_target_sigil(self, replacement: &Expr) -> Expr {
+    use self::Expr::*;
+
+    match self {
+      ConditionalTargetSigilValue => replacement.clone(),
+      Unit | Lit(_) | Func(_) | Val(_) | Constructor { .. } |
+       CaseMatch { .. } | UnimplementedSigilValue => self,
+      Tuple(exprs) => Tuple(exprs.into_iter().map(|e| e.replace_conditional_target_sigil(replacement)).collect()),
+      Call { f, args } => {
+        let new_args = args.into_iter().map(|e| e.replace_conditional_target_sigil(replacement)).collect();
+        Call { f, args: new_args }
+      },
+      Conditional { .. } => panic!("Dunno if I need this, but if so implement"),
+      Assign { .. } => panic!("I'm pretty sure I don't need this"),
+    }
+  }
+}
+
+impl<'a> State<'a> {
+  pub fn evaluate(&mut self, ast: ReducedAST, repl: bool) -> Vec<Result<String, String>> {
+    let mut acc = vec![];
+
+    // handle prebindings
+    for statement in ast.0.iter() {
+      self.prebinding(statement);
+    }
+
+    for statement in ast.0 {
+      match self.statement(statement) {
+        Ok(Some(ref output)) if repl => acc.push(Ok(output.to_repl())),
+        Ok(_) => (),
+        Err(error) => {
+          acc.push(Err(format!("Runtime error: {}", error)));
+          return acc;
+        },
+      }
+    }
+    acc
+  }
+
+  fn prebinding(&mut self, stmt: &Stmt) {
+    match stmt {
+      Stmt::PreBinding { name, func } => {
+        let v_entry = ValueEntry::Binding { constant: true, val: Node::Expr(Expr::Func(func.clone())) };
+        self.values.insert(name.clone(), v_entry);
+      },
+      Stmt::Expr(_expr) => {
+        //TODO have this support things like nested function defs
+
+      },
+      _ => ()
+    }
+  }
+
+  fn statement(&mut self, stmt: Stmt) -> EvalResult<Option<Node>> {
+    match stmt {
+      Stmt::Binding { name, constant, expr } => {
+        let val = self.expression(Node::Expr(expr))?;
+        self.values.insert(name.clone(), ValueEntry::Binding { constant, val });
+        Ok(None)
+      },
+      Stmt::Expr(expr) => Ok(Some(self.expression(expr.to_node())?)),
+      Stmt::PreBinding {..} | Stmt::Noop => Ok(None),
+    }
+  }
+
+  fn block(&mut self, stmts: Vec<Stmt>) -> EvalResult<Node> {
+    let mut ret = None;
+    for stmt in stmts {
+      ret = self.statement(stmt)?;
+    }
+    Ok(ret.unwrap_or(Node::Expr(Expr::Unit)))
+  }
+
+  fn expression(&mut self, node: Node) -> EvalResult<Node> {
+    use self::Expr::*;
+    match node {
+      t @ Node::PrimTuple { .. } => Ok(t),
+      obj @ Node::PrimObject { .. } =>  Ok(obj),
+      Node::Expr(expr) => match expr {
+        literal @ Lit(_) => Ok(Node::Expr(literal)),
+        Call { box f, args } => self.call_expression(f, args),
+        Val(v) => self.value(v),
+        Constructor { arity, ref name, tag, .. } if arity == 0 => Ok(Node::PrimObject { name: name.clone(), tag, items: vec![] }),
+        constructor @ Constructor { .. } => Ok(Node::Expr(constructor)),
+        func @ Func(_) => Ok(Node::Expr(func)),
+        Tuple(exprs) => {
+          let nodes = exprs.into_iter().map(|expr| self.expression(Node::Expr(expr))).collect::<Result<Vec<Node>,_>>()?;
+          Ok(Node::PrimTuple { items: nodes })
+        },
+        Conditional { box cond, then_clause, else_clause } => self.conditional(cond, then_clause, else_clause),
+        Assign { box val, box expr } => self.assign_expression(val, expr),
+        Unit => Ok(Node::Expr(Unit)),
+        CaseMatch { box cond, alternatives } => self.case_match_expression(cond, alternatives),
+        ConditionalTargetSigilValue => Ok(Node::Expr(ConditionalTargetSigilValue)),
+        UnimplementedSigilValue => Err(format!("Sigil value eval not implemented")),
+      }
+    }
+  }
+
+  fn call_expression(&mut self, f: Expr, args: Vec<Expr>) -> EvalResult<Node> {
+    use self::Expr::*;
+    match self.expression(Node::Expr(f))? {
+      Node::Expr(Constructor { type_name, name, tag, arity }) => self.apply_data_constructor(type_name, name, tag, arity, args),
+      Node::Expr(Func(f)) => self.apply_function(f, args),
+      other => return Err(format!("Tried to call {:?} which is not a function or data constructor", other)),
+    }
+  }
+
+  fn apply_data_constructor(&mut self, _type_name: Rc<String>, name: Rc<String>, tag: usize, arity: usize, args: Vec<Expr>) -> EvalResult<Node> {
+    if arity != args.len() {
+      return Err(format!("Data constructor {} requires {} args", name, arity));
+    }
+
+    let evaled_args = args.into_iter().map(|expr| self.expression(Node::Expr(expr))).collect::<Result<Vec<Node>,_>>()?;
+    //let evaled_args = vec![];
+    Ok(Node::PrimObject {
+      name: name.clone(),
+      items: evaled_args,
+      tag 
+    })
+  }
+
+  fn apply_function(&mut self, f: Func, args: Vec<Expr>) -> EvalResult<Node> {
+    match f {
+      Func::BuiltIn(sigil) => Ok(Node::Expr(self.apply_builtin(sigil, args)?)),
+      Func::UserDefined { params, body, name } => {
+
+        if params.len() != args.len() {
+          return Err(format!("calling a {}-argument function with {} args", params.len(), args.len()))
+        }
+        let mut func_state = State {
+          values: self.values.new_scope(name.map(|n| format!("{}", n))),
+          symbol_table_handle: self.symbol_table_handle.clone(),
+        };
+        for (param, val) in params.into_iter().zip(args.into_iter()) {
+          let val = func_state.expression(Node::Expr(val))?;
+          func_state.values.insert(param, ValueEntry::Binding { constant: true, val });
+        }
+        // TODO figure out function return semantics
+        func_state.block(body)
+      }
+    }
+  }
+
+  fn apply_builtin(&mut self, name: Rc<String>, args: Vec<Expr>) -> EvalResult<Expr> {
+    use self::Expr::*;
+    use self::Lit::*;
+    let evaled_args: Result<Vec<Expr>, String> = args.into_iter().map(|arg| {
+      match self.expression(Node::Expr(arg)) {
+        Ok(Node::Expr(e)) => Ok(e),
+        Ok(Node::PrimTuple { .. }) => Err(format!("Trying to apply a builtin to a tuple")),
+        Ok(Node::PrimObject { .. }) => Err(format!("Trying to apply a builtin to a primitive object")),
+        Err(e) => Err(e)
+      }
+    }).collect();
+    let evaled_args = evaled_args?;
+
+    Ok(match (name.as_str(), evaled_args.as_slice()) {
+      /* binops */
+      ("+", &[Lit(Nat(l)), Lit(Nat(r))]) => Lit(Nat(l + r)),
+      ("++", &[Lit(StringLit(ref s1)), Lit(StringLit(ref s2))]) => Lit(StringLit(Rc::new(format!("{}{}", s1, s2)))),
+      ("-", &[Lit(Nat(l)), Lit(Nat(r))]) => Lit(Nat(l - r)),
+      ("*", &[Lit(Nat(l)), Lit(Nat(r))]) => Lit(Nat(l * r)),
+      ("/", &[Lit(Nat(l)), Lit(Nat(r))]) => Lit(Float((l as f64)/ (r as f64))),
+      ("quot", &[Lit(Nat(l)), Lit(Nat(r))]) => if r == 0 {
+        return Err(format!("divide by zero"));
+      } else {
+        Lit(Nat(l / r))
+      },
+      ("%", &[Lit(Nat(l)), Lit(Nat(r))]) => Lit(Nat(l % r)),
+      ("^", &[Lit(Nat(l)), Lit(Nat(r))]) => Lit(Nat(l ^ r)),
+      ("&", &[Lit(Nat(l)), Lit(Nat(r))]) => Lit(Nat(l & r)),
+      ("|", &[Lit(Nat(l)), Lit(Nat(r))]) => Lit(Nat(l | r)),
+
+      /* comparisons */
+      ("==", &[Lit(Nat(l)), Lit(Nat(r))]) => Lit(Bool(l == r)),
+      ("==", &[Lit(Int(l)), Lit(Int(r))]) => Lit(Bool(l == r)),
+      ("==", &[Lit(Float(l)), Lit(Float(r))]) => Lit(Bool(l == r)),
+      ("==", &[Lit(Bool(l)), Lit(Bool(r))]) => Lit(Bool(l == r)),
+      ("==", &[Lit(StringLit(ref l)), Lit(StringLit(ref r))]) => Lit(Bool(l == r)),
+
+      ("<", &[Lit(Nat(l)), Lit(Nat(r))]) => Lit(Bool(l < r)),
+      ("<", &[Lit(Int(l)), Lit(Int(r))]) => Lit(Bool(l < r)),
+      ("<", &[Lit(Float(l)), Lit(Float(r))]) => Lit(Bool(l < r)),
+
+      ("<=", &[Lit(Nat(l)), Lit(Nat(r))]) => Lit(Bool(l <= r)),
+      ("<=", &[Lit(Int(l)), Lit(Int(r))]) => Lit(Bool(l <= r)),
+      ("<=", &[Lit(Float(l)), Lit(Float(r))]) => Lit(Bool(l <= r)),
+
+      (">", &[Lit(Nat(l)), Lit(Nat(r))]) => Lit(Bool(l > r)),
+      (">", &[Lit(Int(l)), Lit(Int(r))]) => Lit(Bool(l > r)),
+      (">", &[Lit(Float(l)), Lit(Float(r))]) => Lit(Bool(l > r)),
+
+      (">=", &[Lit(Nat(l)), Lit(Nat(r))]) => Lit(Bool(l >= r)),
+      (">=", &[Lit(Int(l)), Lit(Int(r))]) => Lit(Bool(l >= r)),
+      (">=", &[Lit(Float(l)), Lit(Float(r))]) => Lit(Bool(l >= r)),
+
+      /* prefix ops */
+      ("!", &[Lit(Bool(true))]) => Lit(Bool(false)),
+      ("!", &[Lit(Bool(false))]) => Lit(Bool(true)),
+      ("-", &[Lit(Nat(n))]) => Lit(Int(-1*(n as i64))),
+      ("-", &[Lit(Int(n))]) => Lit(Int(-1*(n as i64))),
+      ("+", &[Lit(Int(n))]) => Lit(Int(n)),
+      ("+", &[Lit(Nat(n))]) => Lit(Nat(n)),
+
+
+      /* builtin functions */
+      ("print", &[ref anything]) => {
+        print!("{}", anything.to_repl());
+        Expr::Unit
+      },
+      ("println", &[ref anything]) => {
+        println!("{}", anything.to_repl());
+        Expr::Unit
+      },
+      ("getline", &[]) => {
+        let mut buf = String::new();
+        io::stdin().read_line(&mut buf).expect("Error readling line in 'getline'");
+        Lit(StringLit(Rc::new(buf.trim().to_string())))
+      },
+      (x, args) => return Err(format!("bad or unimplemented builtin {:?} | {:?}", x, args)),
+    })
+  }
+
+  fn conditional(&mut self, cond: Expr, then_clause: Vec<Stmt>, else_clause: Vec<Stmt>) -> EvalResult<Node> {
+    let cond = self.expression(Node::Expr(cond))?;
+    Ok(match cond {
+      Node::Expr(Expr::Lit(Lit::Bool(true))) =>  self.block(then_clause)?,
+      Node::Expr(Expr::Lit(Lit::Bool(false))) => self.block(else_clause)?,
+      _ => return Err(format!("Conditional with non-boolean condition"))
+    })
+  }
+
+  fn assign_expression(&mut self, val: Expr, expr: Expr) -> EvalResult<Node> {
+    let name = match val  {
+      Expr::Val(name) => name,
+      _ => return Err(format!("Trying to assign to a non-value")),
+    };
+
+    let constant = match self.values.lookup(&name) {
+      None => return Err(format!("Constant {} is undefined", name)),
+      Some(ValueEntry::Binding { constant, .. }) => constant.clone(),
+    };
+    if constant {
+      return Err(format!("trying to update {}, a non-mutable binding", name));
+    }
+    let val = self.expression(Node::Expr(expr))?;
+    self.values.insert(name.clone(), ValueEntry::Binding { constant: false, val });
+    Ok(Node::Expr(Expr::Unit))
+  }
+
+  fn guard_passes(&mut self, guard: &Option<Expr>, cond: &Node) -> EvalResult<bool> {
+    if let Some(ref guard_expr) = guard {
+      let guard_expr = match cond {
+        Node::Expr(ref e) => guard_expr.clone().replace_conditional_target_sigil(e),
+        _ => guard_expr.clone()
+      };
+      Ok(self.expression(guard_expr.to_node())?.is_true())
+    } else {
+      Ok(true)
+    }
+  }
+
+  fn case_match_expression(&mut self, cond: Expr, alternatives: Vec<Alternative>) -> EvalResult<Node> {
+
+    //TODO need to handle recursive subpatterns
+    let all_subpatterns_pass = |state: &mut State, subpatterns: &Vec<Option<Subpattern>>, items: &Vec<Node>| -> EvalResult<bool> {
+
+      if subpatterns.len() == 0 {
+        return Ok(true)
+      }
+
+      if items.len() != subpatterns.len() {
+        return Err(format!("Subpattern length isn't correct items {} subpatterns {}", items.len(), subpatterns.len()));
+      }
+
+      for (maybe_subp, cond) in subpatterns.iter().zip(items.iter()) {
+        if let Some(subp) = maybe_subp {
+          if !state.guard_passes(&subp.guard, &cond)? {
+            return Ok(false)
+          }
+        }
+      }
+      Ok(true)
+    };
+
+    let cond = self.expression(Node::Expr(cond))?;
+    for alt in alternatives {
+      // no matter what type of condition we have, ignore alternative if the guard evaluates false
+      if !self.guard_passes(&alt.guard, &cond)? {
+        continue;
+      }
+
+      match cond {
+        Node::PrimObject { ref tag, ref items, .. } => {
+          if alt.tag.map(|t| t == *tag).unwrap_or(true) {
+            let mut inner_state = self.new_frame(items, &alt.bound_vars);
+            if all_subpatterns_pass(&mut inner_state, &alt.subpatterns, items)? {
+              return inner_state.block(alt.item);
+            } else {
+              continue;
+            }
+          }
+        },
+        Node::PrimTuple { ref items } =>  {
+          let mut inner_state = self.new_frame(items, &alt.bound_vars);
+          if all_subpatterns_pass(&mut inner_state, &alt.subpatterns, items)? {
+            return inner_state.block(alt.item);
+          } else {
+            continue;
+          }
+        },
+        Node::Expr(ref _e) => {
+          if let None = alt.tag {
+            return self.block(alt.item)
+          }
+        }
+      }
+    }
+    Err(format!("{:?} failed pattern match", cond))
+  }
+
+  fn value(&mut self, name: Rc<String>) -> EvalResult<Node> {
+    use self::ValueEntry::*;
+    use self::Func::*;
+    //TODO add a layer of indirection here to talk to the symbol table first, and only then look up
+    //in the values table
+
+    let symbol_table = self.symbol_table_handle.borrow();
+    let value = symbol_table.lookup_by_name(&name);
+    Ok(match value {
+      Some(Symbol { name, spec }) => match spec {
+        //TODO I'll need this type_name later to do a table lookup
+        SymbolSpec::DataConstructor { type_name: _type_name, type_args, .. } => {
+          if type_args.len() == 0 {
+            Node::PrimObject { name: name.clone(), tag: 0, items: vec![] }
+          } else {
+            return Err(format!("This data constructor thing not done"))
+          }
+        },
+        SymbolSpec::Func(_) => match self.values.lookup(&name) {
+          Some(Binding { val: Node::Expr(Expr::Func(UserDefined { name, params, body })), .. }) => {
+            Node::Expr(Expr::Func(UserDefined { name: name.clone(), params: params.clone(), body: body.clone() }))
+          },
+          _ => unreachable!(),
+        },
+        SymbolSpec::RecordConstructor { .. } => return Err(format!("This shouldn't be a record!")),
+      },
+      /* see if it's an ordinary variable TODO make variables go in symbol table */
+      None => match self.values.lookup(&name) {
+        Some(Binding { val, .. }) => val.clone(),
+        None => return Err(format!("Couldn't find value {}", name)),
+      }
+    })
+  }
+}
+
+#[cfg(test)]
+mod eval_tests {
+  use std::cell::RefCell;
+  use std::rc::Rc;
+
+  use crate::tokenizing::{Token, tokenize};
+  use crate::parsing::ParseResult;
+  use crate::ast::AST;
+  use crate::symbol_table::SymbolTable;
+  use crate::eval::State;
+
+  fn parse(tokens: Vec<Token>) -> ParseResult<AST> {
+    let mut parser = crate::parsing::Parser::new(tokens);
+    parser.parse()
+  }
+
+  fn evaluate_all_outputs(input: &str) -> Vec<Result<String, String>> {
+    let symbol_table = Rc::new(RefCell::new(SymbolTable::new()));
+    let mut state = State::new(symbol_table);
+    let ast = parse(tokenize(input)).unwrap();
+    state.symbol_table_handle.borrow_mut().add_top_level_symbols(&ast).unwrap();
+    let reduced = ast.reduce(&state.symbol_table_handle.borrow());
+    let all_output = state.evaluate(reduced, true);
+    all_output
+  }
+
+  macro_rules! test_in_fresh_env {
+    ($string:expr, $correct:expr) => {
+      {
+        let all_output = evaluate_all_outputs($string);
+        let ref output = all_output.last().unwrap();
+        assert_eq!(**output, Ok($correct.to_string()));
+      }
+    }
+  }
+
+  #[test]
+  fn test_basic_eval() {
+    test_in_fresh_env!("1 + 2", "3");
+    test_in_fresh_env!("let mut a = 1; a = 2", "Unit");
+    test_in_fresh_env!("let mut a = 1; a = 2; a", "2");
+    test_in_fresh_env!(r#"("a", 1 + 2)"#, r#"("a", 3)"#);
+  }
+
+  #[test]
+  fn function_eval() {
+    test_in_fresh_env!("fn oi(x) { x + 1 }; oi(4)", "5");
+    test_in_fresh_env!("fn oi(x) { x + 1 }; oi(1+2)", "4");
+  }
+
+  #[test]
+  fn scopes() {
+    let scope_ok = r#"
+    let a = 20
+    fn haha() {
+      let a = 10
+      a
+    }
+    haha()
+    "#;
+    test_in_fresh_env!(scope_ok, "10");
+    let scope_ok = r#"
+    let a = 20
+    fn haha() {
+      let a = 10
+      a
+    }
+    a
+    "#;
+    test_in_fresh_env!(scope_ok, "20");
+  }
+
+  #[test]
+  fn if_is_patterns() {
+    let source = r#"
+type Option<T> = Some(T) | None
+let x = Some(9); if x is Some(q) then { q } else { 0 }"#;
+    test_in_fresh_env!(source, "9");
+
+    let source = r#"
+type Option<T> = Some(T) | None
+let x = None; if x is Some(q) then { q } else { 0 }"#;
+    test_in_fresh_env!(source, "0");
+  }
+
+  #[test]
+  fn full_if_matching() {
+    let source = r#"
+type Option<T> = Some(T) | None
+let a = None
+if a { is None -> 4, is Some(x) -> x }
+"#;
+  test_in_fresh_env!(source, "4");
+
+    let source = r#"
+type Option<T> = Some(T) | None
+let a = Some(99)
+if a { is None -> 4, is Some(x) -> x }
+"#;
+  test_in_fresh_env!(source, "99");
+
+  let source = r#"
+let a = 10
+if a { is 10 -> "x", is 4 -> "y" }
+"#;
+  test_in_fresh_env!(source, "\"x\"");
+
+  let source = r#"
+let a = 10
+if a { is 15 -> "x", is 10 -> "y" }
+"#;
+  test_in_fresh_env!(source, "\"y\"");
+  }
+
+  #[test]
+  fn string_pattern() {
+    let source = r#"
+let a = "foo"
+if a { is "foo" -> "x", is _ -> "y" }
+"#;
+    test_in_fresh_env!(source, "\"x\"");
+  }
+
+  #[test]
+  fn boolean_pattern() {
+    let source = r#"
+let a = true
+if a { 
+  is true -> "x",
+  is false -> "y"
+}
+"#;
+    test_in_fresh_env!(source, "\"x\"");
+  }
+
+  #[test]
+  fn boolean_pattern_2() {
+    let source = r#"
+let a = false
+if a { is true -> "x", is false -> "y" }
+"#;
+    test_in_fresh_env!(source, "\"y\"");
+  }
+
+  #[test]
+  fn ignore_pattern() {
+    let source = r#"
+type Option<T> = Some(T) | None
+if Some(10) {
+  is _ -> "hella"
+}
+"#;
+    test_in_fresh_env!(source, "\"hella\"");
+  }
+
+  #[test]
+  fn tuple_pattern() {
+    let source = r#"
+if (1, 2) {
+  is (1, x) -> x,
+  is _ -> 99
+}
+"#;
+    test_in_fresh_env!(source, 2);
+  }
+
+
+  #[test]
+  fn tuple_pattern_2() {
+    let source = r#"
+if (1, 2) {
+  is (10, x) -> x,
+  is (y, x) -> x + y
+}
+"#;
+    test_in_fresh_env!(source, 3);
+  }
+
+  #[test]
+  fn tuple_pattern_3() {
+    let source = r#"
+if (1, 5) {
+  is (10, x) -> x,
+  is (1, x) -> x
+}
+"#;
+    test_in_fresh_env!(source, 5);
+  }
+
+  #[test]
+  fn tuple_pattern_4() {
+    let source = r#"
+if (1, 5) {
+  is (10, x) -> x,
+  is (1, x) -> x,
+}
+"#;
+    test_in_fresh_env!(source, 5);
+  }
+
+  #[test]
+  fn  prim_obj_pattern() {
+    let source = r#"
+type Stuff = Mulch(Nat) | Jugs(Nat, String) | Mardok
+let a = Mulch(20)
+let b = Jugs(1, "haha")
+let c = Mardok
+
+let x = if a {
+  is Mulch(20) -> "x",
+  is _ -> "ERR"
+}
+
+let y = if b {
+  is Mulch(n) -> "ERR",
+  is Jugs(2, _) -> "ERR",
+  is Jugs(1, s) -> s,
+  is _ -> "ERR",
+}
+
+let z = if c {
+  is Jugs(_, _) -> "ERR",
+  is Mardok -> "NIGH",
+  is _ -> "ERR",
+}
+
+(x, y, z)
+"#;
+  test_in_fresh_env!(source, r#"("x", "haha", "NIGH")"#);
+  }
+
+  #[test]
+  fn basic_lambda_syntax() {
+    let source = r#"
+let q = \(x, y) { x * y }
+let x = q(5,2)
+let y = \(m, n, o) { m + n + o }(1,2,3)
+(x, y)
+  "#;
+  test_in_fresh_env!(source, r"(10, 6)");
+  }
+
+  #[test]
+  fn lambda_syntax_2() {
+    let source = r#"
+fn milta() {
+  \(x) { x + 33 }
+}
+milta()(10)
+  "#;
+    test_in_fresh_env!(source, "43");
+  }
+}

schala-lang/language/src/lib.rs

@@ -0,0 +1,213 @@
+#![feature(trace_macros)]
+#![feature(custom_attribute)]
+#![feature(unrestricted_attribute_tokens)]
+#![feature(slice_patterns, box_patterns, box_syntax)]
+
+//! `schala-lang` is where the Schala programming language is actually implemented. 
+//! It defines the `Schala` type, which contains the state for a Schala REPL, and implements
+//! `ProgrammingLanguageInterface` and the chain of compiler passes for it.
+
+extern crate itertools;
+#[macro_use]
+extern crate lazy_static;
+#[macro_use]
+extern crate maplit;
+extern crate schala_repl;
+#[macro_use]
+extern crate schala_repl_codegen;
+#[macro_use]
+extern crate schala_lang_codegen;
+
+use std::cell::RefCell;
+use std::rc::Rc;
+
+use itertools::Itertools;
+use schala_repl::{ProgrammingLanguageInterface, EvalOptions, TraceArtifact, UnfinishedComputation, FinishedComputation};
+
+macro_rules! bx {
+  ($e:expr) => { Box::new($e) }
+}
+
+mod util;
+mod builtin;
+mod tokenizing;
+mod ast;
+mod parsing;
+mod symbol_table;
+mod typechecking;
+mod reduced_ast;
+mod eval;
+
+//trace_macros!(true);
+#[derive(ProgrammingLanguageInterface)]
+#[LanguageName = "Schala"]
+#[SourceFileExtension = "schala"]
+#[PipelineSteps(load_source, tokenizing, parsing(compact,expanded,trace), symbol_table, typechecking, ast_reducing, eval)]
+#[DocMethod = get_doc]
+#[HandleCustomInterpreterDirectives = handle_custom_interpreter_directives]
+/// All bits of state necessary to parse and execute a Schala program are stored in this struct.
+/// `state` represents the execution state for the AST-walking interpreter, the other fields
+/// should be self-explanatory.
+pub struct Schala {
+  source_reference: SourceReference,
+  state: eval::State<'static>,
+  symbol_table: Rc<RefCell<symbol_table::SymbolTable>>,
+  type_context: typechecking::TypeContext<'static>,
+  active_parser: Option<parsing::Parser>,
+}
+
+impl Schala {
+  fn get_doc(&self, commands: &Vec<&str>) -> Option<String> {
+    Some(format!("Documentation on commands: {:?}", commands))
+  }
+
+  fn handle_custom_interpreter_directives(&mut self, commands: &Vec<&str>) -> Option<String> {
+    Some(format!("Schala-lang command: {:?} not supported", commands.get(0)))
+  }
+}
+
+impl Schala {
+  /// Creates a new Schala environment *without* any prelude.
+  fn new_blank_env() -> Schala {
+    let symbols = Rc::new(RefCell::new(symbol_table::SymbolTable::new()));
+    Schala {
+      source_reference: SourceReference::new(),
+      symbol_table: symbols.clone(),
+      state: eval::State::new(symbols),
+      type_context: typechecking::TypeContext::new(),
+      active_parser: None,
+    }
+  }
+
+  /// Creates a new Schala environment with the standard prelude, which is defined as ordinary
+  /// Schala code in the file `prelude.schala`
+  pub fn new() -> Schala {
+    let prelude = include_str!("prelude.schala");
+    let mut s = Schala::new_blank_env();
+    s.execute_pipeline(prelude, &EvalOptions::default());
+    s
+  }
+}
+
+fn load_source<'a>(input: &'a str, handle: &mut Schala, _comp: Option<&mut UnfinishedComputation>) -> Result<&'a str, String> {
+  handle.source_reference.load_new_source(input);
+  Ok(input)
+}
+
+fn tokenizing(input: &str, _handle: &mut Schala, comp: Option<&mut UnfinishedComputation>) -> Result<Vec<tokenizing::Token>, String> {
+  let tokens = tokenizing::tokenize(input);
+  comp.map(|comp| {
+    let token_string = tokens.iter().map(|t| t.to_string_with_metadata()).join(", ");
+    comp.add_artifact(TraceArtifact::new("tokens", token_string));
+  });
+
+  let errors: Vec<String> = tokens.iter().filter_map(|t| t.get_error()).collect();
+  if errors.len() == 0 {
+    Ok(tokens)
+  } else {
+    Err(format!("{:?}", errors))
+  }
+}
+
+fn parsing(input: Vec<tokenizing::Token>, handle: &mut Schala, comp: Option<&mut UnfinishedComputation>) -> Result<ast::AST, String> {
+  use crate::parsing::Parser;
+
+  let mut parser = match handle.active_parser.take() {
+    None => Parser::new(input),
+    Some(parser) => parser
+  };
+
+  let ast = parser.parse();
+  let trace = parser.format_parse_trace();
+
+  comp.map(|comp| {
+    //TODO need to control which of these debug stages get added
+    let opt = comp.cur_debug_options.get(0).map(|s| s.clone());
+    match opt {
+      None => comp.add_artifact(TraceArtifact::new("ast", format!("{:?}", ast))),
+      Some(ref s) if s == "compact" => comp.add_artifact(TraceArtifact::new("ast", format!("{:?}", ast))),
+      Some(ref s) if s == "expanded" => comp.add_artifact(TraceArtifact::new("ast", format!("{:#?}", ast))),
+      Some(ref s) if s == "trace" => comp.add_artifact(TraceArtifact::new_parse_trace(trace)),
+      Some(ref x) => println!("Bad parsing debug option: {}", x),
+    };
+  });
+  ast.map_err(|err| format_parse_error(err, handle))
+}
+
+fn format_parse_error(error: parsing::ParseError, handle: &mut Schala) -> String {
+  let line_num = error.token.line_num;
+  let ch = error.token.char_num;
+  let line_from_program = handle.source_reference.get_line(line_num);
+  let location_pointer = format!("{}^", " ".repeat(ch));
+
+  let line_num_digits = format!("{}", line_num).chars().count();
+  let space_padding = " ".repeat(line_num_digits);
+
+  format!(r#"
+{error_msg}
+{space_padding} |
+{line_num} | {}
+{space_padding} | {}
+"#, line_from_program, location_pointer, error_msg=error.msg, space_padding=space_padding, line_num=line_num)
+}
+
+fn symbol_table(input: ast::AST, handle: &mut Schala, comp: Option<&mut UnfinishedComputation>) -> Result<ast::AST, String> {
+  let add = handle.symbol_table.borrow_mut().add_top_level_symbols(&input);
+  match add {
+    Ok(()) => {
+      let artifact = TraceArtifact::new("symbol_table", handle.symbol_table.borrow().debug_symbol_table());
+      comp.map(|comp| comp.add_artifact(artifact));
+      Ok(input)
+    },
+    Err(msg) => Err(msg)
+  }
+}
+
+fn typechecking(input: ast::AST, handle: &mut Schala, comp: Option<&mut UnfinishedComputation>) -> Result<ast::AST, String> {
+  let result = handle.type_context.typecheck(&input);
+
+  comp.map(|comp| {
+    let artifact = TraceArtifact::new("type", format!("{:?}", result));
+    comp.add_artifact(artifact);
+  });
+
+  Ok(input)
+}
+
+fn ast_reducing(input: ast::AST, handle: &mut Schala, comp: Option<&mut UnfinishedComputation>) -> Result<reduced_ast::ReducedAST, String> {
+  let ref symbol_table = handle.symbol_table.borrow();
+  let output = input.reduce(symbol_table);
+  comp.map(|comp| comp.add_artifact(TraceArtifact::new("ast_reducing", format!("{:?}", output))));
+  Ok(output)
+}
+
+fn eval(input: reduced_ast::ReducedAST, handle: &mut Schala, comp: Option<&mut UnfinishedComputation>) -> Result<String, String> {
+  comp.map(|comp| comp.add_artifact(TraceArtifact::new("value_state", handle.state.debug_print())));
+  let evaluation_outputs = handle.state.evaluate(input, true);
+  let text_output: Result<Vec<String>, String> = evaluation_outputs
+    .into_iter()
+    .collect();
+
+  let eval_output: Result<String, String> = text_output
+    .map(|v| { v.into_iter().intersperse(format!("\n")).collect() });
+  eval_output
+}
+
+/// Represents lines of source code
+struct SourceReference {
+  lines: Option<Vec<String>>
+}
+
+impl SourceReference {
+  fn new() -> SourceReference {
+    SourceReference { lines: None }
+  }
+
+  fn load_new_source(&mut self, source: &str) {
+    //TODO this is a lot of heap allocations - maybe there's a way to make it more efficient?
+    self.lines = Some(source.lines().map(|s| s.to_string()).collect()); }
+
+  fn get_line(&self, line: usize) -> String {
+    self.lines.as_ref().and_then(|x| x.get(line).map(|s| s.to_string())).unwrap_or(format!("NO LINE FOUND"))
+  }
+}

schala-lang/language/src/prelude.schala

@@ -0,0 +1,13 @@
+
+type Option<T> = Some(T) | None
+type Color = Red | Green | Blue
+type Ord = LT | EQ | GT
+
+
+fn map(input: Option<T>, func: Func): Option<T> {
+  if input {
+    is Some(x) -> Some(func(x)),
+    is None -> None,
+  }
+}
+  

schala-lang/language/src/reduced_ast.rs

@@ -0,0 +1,398 @@
+use std::rc::Rc;
+
+use crate::ast::*;
+use crate::symbol_table::{Symbol, SymbolSpec, SymbolTable};
+use crate::builtin::{BinOp, PrefixOp};
+
+#[derive(Debug)]
+pub struct ReducedAST(pub Vec<Stmt>);
+
+#[derive(Debug, Clone)]
+pub enum Stmt {
+  PreBinding {
+    name: Rc<String>,
+    func: Func,
+  },
+  Binding {
+    name: Rc<String>,
+    constant: bool,
+    expr: Expr,
+  },
+  Expr(Expr),
+  Noop,
+}
+
+#[derive(Debug, Clone)]
+pub enum Expr {
+  Unit,
+  Lit(Lit),
+  Tuple(Vec<Expr>),
+  Func(Func),
+  Val(Rc<String>),
+  Constructor {
+    type_name: Rc<String>,
+    name: Rc<String>,
+    tag: usize,
+    arity: usize,
+  },
+  Call {
+    f: Box<Expr>,
+    args: Vec<Expr>,
+  },
+  Assign {
+    val: Box<Expr>,
+    expr: Box<Expr>,
+  },
+  Conditional {
+    cond: Box<Expr>,
+    then_clause: Vec<Stmt>,
+    else_clause: Vec<Stmt>,
+  },
+  ConditionalTargetSigilValue,
+  CaseMatch {
+    cond: Box<Expr>,
+    alternatives: Vec<Alternative>
+  },
+  UnimplementedSigilValue
+}
+
+pub type BoundVars = Vec<Option<Rc<String>>>; //remember that order matters here
+
+#[derive(Debug, Clone)]
+pub struct Alternative {
+  pub tag: Option<usize>,
+  pub subpatterns: Vec<Option<Subpattern>>,
+  pub guard: Option<Expr>,
+  pub bound_vars: BoundVars,
+  pub item: Vec<Stmt>,
+}
+
+#[derive(Debug, Clone)]
+pub struct Subpattern {
+  pub tag: Option<usize>,
+  pub subpatterns: Vec<Option<Subpattern>>,
+  pub bound_vars: BoundVars,
+  pub guard: Option<Expr>,
+}
+
+#[derive(Debug, Clone)]
+pub enum Lit {
+  Nat(u64),
+  Int(i64),
+  Float(f64),
+  Bool(bool),
+  StringLit(Rc<String>),
+}
+
+#[derive(Debug, Clone)]
+pub enum Func {
+  BuiltIn(Rc<String>),
+  UserDefined {
+    name: Option<Rc<String>>,
+    params: Vec<Rc<String>>,
+    body: Vec<Stmt>,
+  }
+}
+
+impl AST {
+  pub fn reduce(&self, symbol_table: &SymbolTable) -> ReducedAST {
+    let mut output = vec![];
+    for statement in self.0.iter() {
+      output.push(statement.node().reduce(symbol_table));
+    }
+    ReducedAST(output)
+  }
+}
+
+impl Statement {
+  fn reduce(&self, symbol_table: &SymbolTable) -> Stmt { 
+    use crate::ast::Statement::*;
+    match self {
+      ExpressionStatement(expr) => Stmt::Expr(expr.node().reduce(symbol_table)),
+      Declaration(decl) => decl.reduce(symbol_table),
+    }
+  }
+}
+
+fn reduce_block(block: &Block, symbol_table: &SymbolTable) -> Vec<Stmt> {
+  block.iter().map(|stmt| stmt.node().reduce(symbol_table)).collect()
+}
+
+impl Expression {
+  fn reduce(&self, symbol_table: &SymbolTable) -> Expr {
+    use crate::ast::ExpressionType::*;
+    let ref input = self.0;
+    match input {
+      NatLiteral(n) => Expr::Lit(Lit::Nat(*n)),
+      FloatLiteral(f) => Expr::Lit(Lit::Float(*f)),
+      StringLiteral(s) => Expr::Lit(Lit::StringLit(s.clone())),
+      BoolLiteral(b) => Expr::Lit(Lit::Bool(*b)),
+      BinExp(binop, lhs, rhs) => binop.reduce(symbol_table, lhs, rhs),
+      PrefixExp(op, arg) => op.reduce(symbol_table, arg),
+      Value(name) => match symbol_table.lookup_by_name(name) {
+        Some(Symbol { spec: SymbolSpec::DataConstructor { index, type_args, type_name}, .. }) => Expr::Constructor {
+          type_name: type_name.clone(),
+          name: name.clone(),
+          tag: index.clone(),
+          arity: type_args.len(),
+        },
+        _ => Expr::Val(name.clone()),
+      },
+      Call { f, arguments } => Expr::Call {
+        f: Box::new(f.reduce(symbol_table)),
+        args: arguments.iter().map(|arg| arg.node().reduce(symbol_table)).collect(),
+      },
+      TupleLiteral(exprs) => Expr::Tuple(exprs.iter().map(|e| e.node().reduce(symbol_table)).collect()),
+      IfExpression { discriminator, body } => reduce_if_expression(discriminator, body, symbol_table),
+      Lambda { params, body, .. } => reduce_lambda(params, body, symbol_table),
+      NamedStruct { .. } => Expr::UnimplementedSigilValue,
+      Index { .. } => Expr::UnimplementedSigilValue,
+      WhileExpression { .. } => Expr::UnimplementedSigilValue,
+      ForExpression { .. } => Expr::UnimplementedSigilValue,
+      ListLiteral { .. } => Expr::UnimplementedSigilValue,
+    }
+  }
+}
+
+fn reduce_lambda(params: &Vec<FormalParam>, body: &Block, symbol_table: &SymbolTable) -> Expr {
+  Expr::Func(Func::UserDefined {
+    name: None,
+    params: params.iter().map(|param| param.0.clone()).collect(),
+    body: reduce_block(body, symbol_table),
+  })
+}
+
+fn reduce_if_expression(discriminator: &Discriminator, body: &IfExpressionBody, symbol_table: &SymbolTable) -> Expr {
+  let cond = Box::new(match *discriminator {
+    Discriminator::Simple(ref expr) => expr.reduce(symbol_table),
+    Discriminator::BinOp(ref _expr, ref _binop) => panic!("Can't yet handle binop discriminators")
+  });
+  match *body {
+    IfExpressionBody::SimpleConditional(ref then_clause, ref else_clause) => {
+      let then_clause = reduce_block(then_clause, symbol_table);
+      let else_clause = match else_clause {
+        None => vec![],
+        Some(stmts) => reduce_block(stmts, symbol_table),
+      };
+      Expr::Conditional { cond, then_clause, else_clause }
+    },
+    IfExpressionBody::SimplePatternMatch(ref pat, ref then_clause, ref else_clause) => {
+      let then_clause = reduce_block(then_clause, symbol_table);
+      let else_clause = match else_clause {
+        None => vec![],
+        Some(stmts) => reduce_block(stmts, symbol_table),
+      };
+
+      let alternatives = vec![
+        pat.to_alternative(then_clause, symbol_table),
+        Alternative {
+          tag: None,
+          subpatterns: vec![],
+          bound_vars: vec![],
+          guard: None,
+          item: else_clause
+        },
+      ];
+
+      Expr::CaseMatch {
+        cond,
+        alternatives,
+      }
+    },
+    IfExpressionBody::GuardList(ref guard_arms) => {
+      let mut alternatives = vec![];
+      for arm in guard_arms {
+        match arm.guard {
+          Guard::Pat(ref p) =>  {
+            let item = reduce_block(&arm.body, symbol_table);
+            let alt = p.to_alternative(item, symbol_table);
+            alternatives.push(alt);
+          },
+          Guard::HalfExpr(HalfExpr { op: _, expr: _ }) => {
+            return Expr::UnimplementedSigilValue
+          }
+        }
+      }
+      Expr::CaseMatch { cond, alternatives }
+    }
+  }
+}
+/*                     ig var   pat
+ * x is SomeBigOldEnum(_, x, Some(t))
+ */
+
+fn handle_symbol(symbol: Option<&Symbol>, inner_patterns: &Vec<Pattern>, symbol_table: &SymbolTable) -> Subpattern {
+  use self::Pattern::*;
+  let tag = symbol.map(|symbol| match symbol.spec {
+    SymbolSpec::DataConstructor { index, .. } => index.clone(),
+    _ => panic!("Symbol is not a data constructor - this should've been caught in type-checking"),
+  });
+  let bound_vars = inner_patterns.iter().map(|p| match p {
+    Literal(PatternLiteral::VarPattern(var)) => Some(var.clone()),
+    _ => None,
+  }).collect();
+
+  let subpatterns = inner_patterns.iter().map(|p| match p {
+    Ignored => None,
+    Literal(PatternLiteral::VarPattern(_)) => None,
+    Literal(other) => Some(other.to_subpattern(symbol_table)),
+    tp @ TuplePattern(_) => Some(tp.to_subpattern(symbol_table)),
+    ts @ TupleStruct(_, _) => Some(ts.to_subpattern(symbol_table)),
+    Record(..) => unimplemented!(),
+  }).collect();
+
+  let guard = None;
+  /*
+     let guard_equality_exprs: Vec<Expr> = subpatterns.iter().map(|p| match p {
+     Literal(lit) => match lit {
+     _ => unimplemented!()
+     },
+     _ => unimplemented!()
+     }).collect();
+     */
+
+  Subpattern {
+    tag,
+    subpatterns,
+    guard,
+    bound_vars,
+  }
+}
+
+impl Pattern {
+  fn to_alternative(&self, item: Vec<Stmt>, symbol_table: &SymbolTable) -> Alternative {
+    let s = self.to_subpattern(symbol_table);
+    Alternative {
+      tag: s.tag,
+      subpatterns: s.subpatterns,
+      bound_vars: s.bound_vars,
+      guard: s.guard,
+      item
+    }
+  }
+
+  fn to_subpattern(&self, symbol_table: &SymbolTable) -> Subpattern {
+    use self::Pattern::*;
+    match self {
+      TupleStruct(name, inner_patterns) => {
+        let symbol = symbol_table.lookup_by_name(name).expect(&format!("Symbol {} not found", name));
+        handle_symbol(Some(symbol), inner_patterns, symbol_table)
+      },
+      TuplePattern(inner_patterns) => handle_symbol(None, inner_patterns, symbol_table),
+      Record(_name, _pairs) => {
+        unimplemented!()
+      },
+      Ignored => Subpattern { tag: None, subpatterns: vec![], guard: None, bound_vars: vec![] },
+      Literal(lit) => lit.to_subpattern(symbol_table),
+    }
+  }
+}
+
+impl PatternLiteral {
+  fn to_subpattern(&self, symbol_table: &SymbolTable) -> Subpattern {
+    use self::PatternLiteral::*;
+    match self {
+      NumPattern { neg, num } => {
+        let comparison = Expr::Lit(match (neg, num) {
+          (false, ExpressionType::NatLiteral(n)) => Lit::Nat(*n),
+          (false, ExpressionType::FloatLiteral(f)) => Lit::Float(*f),
+          (true, ExpressionType::NatLiteral(n)) => Lit::Int(-1*(*n as i64)),
+          (true, ExpressionType::FloatLiteral(f)) => Lit::Float(-1.0*f),
+          _ => panic!("This should never happen")
+        });
+        let guard = Some(Expr::Call {
+          f: Box::new(Expr::Func(Func::BuiltIn(Rc::new("==".to_string())))),
+          args: vec![comparison, Expr::ConditionalTargetSigilValue],
+        });
+        Subpattern {
+          tag: None,
+          subpatterns: vec![],
+          guard,
+          bound_vars: vec![],
+        }
+      },
+      StringPattern(s) => {
+        let guard = Some(Expr::Call {
+          f: Box::new(Expr::Func(Func::BuiltIn(Rc::new("==".to_string())))),
+          args: vec![Expr::Lit(Lit::StringLit(s.clone())), Expr::ConditionalTargetSigilValue]
+        });
+
+        Subpattern {
+          tag: None,
+          subpatterns: vec![],
+          guard,
+          bound_vars: vec![],
+        }
+      },
+      BoolPattern(b) =>  {
+        let guard = Some(if *b {
+          Expr::ConditionalTargetSigilValue
+        } else {
+          Expr::Call {
+            f: Box::new(Expr::Func(Func::BuiltIn(Rc::new("!".to_string())))),
+            args: vec![Expr::ConditionalTargetSigilValue]
+          }
+        });
+        Subpattern {
+          tag: None,
+          subpatterns: vec![],
+          guard,
+          bound_vars: vec![],
+        }
+      },
+      VarPattern(var) => match symbol_table.lookup_by_name(var) {
+        Some(symbol) => handle_symbol(Some(symbol), &vec![], symbol_table),
+        None => Subpattern {
+          tag: None,
+          subpatterns: vec![],
+          guard: None,
+          bound_vars: vec![Some(var.clone())],
+        }
+      }
+    }
+  }
+}
+
+impl Declaration {
+  fn reduce(&self, symbol_table: &SymbolTable) -> Stmt {
+    use self::Declaration::*;
+    use crate::ast::Signature;
+    match self {
+      Binding {name, constant, expr } => Stmt::Binding { name: name.clone(), constant: *constant, expr: expr.reduce(symbol_table) },
+      FuncDecl(Signature { name, params, .. }, statements) => Stmt::PreBinding {
+        name: name.clone(),
+        func: Func::UserDefined {
+          name: Some(name.clone()),
+          params: params.iter().map(|param| param.0.clone()).collect(),
+          body: reduce_block(&statements, symbol_table),
+        }
+      },
+      TypeDecl { .. } => Stmt::Noop,
+      TypeAlias(_, _) => Stmt::Noop,
+      Interface { .. } => Stmt::Noop,
+      Impl { .. } => Stmt::Expr(Expr::UnimplementedSigilValue),
+      _ => Stmt::Expr(Expr::UnimplementedSigilValue)
+    }
+  }
+}
+
+impl BinOp {
+  fn reduce(&self, symbol_table: &SymbolTable, lhs: &Box<Node<Expression>>, rhs: &Box<Node<Expression>>) -> Expr {
+    if **self.sigil() == "=" {
+      Expr::Assign {
+        val: Box::new(lhs.node().reduce(symbol_table)),
+        expr: Box::new(rhs.node().reduce(symbol_table)),
+      }
+    } else {
+      let f = Box::new(Expr::Func(Func::BuiltIn(self.sigil().clone())));
+      Expr::Call { f, args: vec![lhs.node().reduce(symbol_table), rhs.node().reduce(symbol_table)]}
+    }
+  }
+}
+
+impl PrefixOp {
+  fn reduce(&self, symbol_table: &SymbolTable, arg: &Box<Node<Expression>>) -> Expr {
+    let f = Box::new(Expr::Func(Func::BuiltIn(self.sigil().clone())));
+    Expr::Call { f, args: vec![arg.node().reduce(symbol_table)]}
+  }
+}

schala-lang/language/src/symbol_table.rs

@@ -0,0 +1,158 @@
+use std::collections::HashMap;
+use std::rc::Rc;
+use std::fmt;
+use std::fmt::Write;
+
+use crate::ast;
+use crate::ast::{TypeBody, TypeSingletonName, Signature};
+use crate::typechecking::TypeName;
+
+//cf. p. 150 or so of Language Implementation Patterns
+pub struct SymbolTable {
+  pub values: HashMap<Rc<String>, Symbol> //TODO this will eventually have real type information
+}
+
+//TODO add various types of lookups here, maybe multiple hash tables internally? also make values
+//non-public
+impl SymbolTable {
+  pub fn new() -> SymbolTable {
+    SymbolTable { values: HashMap::new() }
+  }
+
+  pub fn lookup_by_name(&self, name: &Rc<String>) -> Option<&Symbol> {
+    self.values.get(name)
+  }
+}
+
+#[derive(Debug)]
+pub struct Symbol {
+  pub name: Rc<String>,
+  pub spec: SymbolSpec,
+}
+
+impl fmt::Display for Symbol {
+  fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
+    write!(f, "<Name: {}, Spec: {}>", self.name, self.spec)
+  }
+}
+
+#[derive(Debug)]
+pub enum SymbolSpec {
+  Func(Vec<TypeName>),
+  DataConstructor {
+    index: usize,
+    type_name: Rc<String>,
+    type_args: Vec<Rc<String>>,
+  },
+  RecordConstructor {
+    fields: HashMap<Rc<String>, Rc<String>>
+  }
+}
+
+impl fmt::Display for SymbolSpec {
+  fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
+    use self::SymbolSpec::*;
+    match self {
+      Func(type_names) => write!(f, "Func({:?})", type_names),
+      DataConstructor { index, type_name, type_args } => write!(f, "DataConstructor(idx: {})({:?} -> {})", index, type_args, type_name),
+      RecordConstructor { fields } => write!(f, "RecordConstructor( <fields> )"),
+    }
+  }
+}
+
+impl SymbolTable {
+  /* note: this adds names for *forward reference* but doesn't actually create any types. solve that problem
+   * later */
+  pub fn add_top_level_symbols(&mut self, ast: &ast::AST) -> Result<(), String> {
+    use self::ast::Statement;
+    use self::ast::Declaration::*;
+    for statement in ast.0.iter() {
+      let statement = statement.node();
+      if let Statement::Declaration(decl) = statement {
+        match decl {
+          FuncSig(signature) | FuncDecl(signature, _) => self.add_function_signature(signature)?,
+          TypeDecl { name, body, mutable } => self.add_type_decl(name, body, mutable)?,
+          _ => ()
+        }
+      }
+    }
+    Ok(())
+  }
+  pub fn debug_symbol_table(&self) -> String {
+    let mut output = format!("Symbol table\n");
+    for (name, sym) in &self.values {
+      write!(output, "{} -> {}\n", name, sym).unwrap();
+    }
+    output
+  }
+
+  fn add_function_signature(&mut self, signature: &Signature) -> Result<(), String> {
+    let mut local_type_context = LocalTypeContext::new();
+    let types = signature.params.iter().map(|param| match param {
+      (_, Some(type_identifier)) => Rc::new(format!("{:?}", type_identifier)),
+      (_, None) => local_type_context.new_universal_type()
+    }).collect();
+    let spec = SymbolSpec::Func(types);
+    self.values.insert(
+      signature.name.clone(),
+      Symbol { name: signature.name.clone(), spec }
+    );
+    Ok(())
+  }
+
+  fn add_type_decl(&mut self, type_name: &TypeSingletonName, body: &TypeBody, _mutable: &bool) -> Result<(), String> {
+    use crate::ast::{TypeIdentifier, Variant};
+    let TypeBody(variants) = body;
+    let TypeSingletonName { name, .. } = type_name;
+    //TODO figure out why _params isn't being used here
+    for (index, var) in variants.iter().enumerate() {
+      match var {
+        Variant::UnitStruct(variant_name) => {
+          let spec = SymbolSpec::DataConstructor {
+            index,
+            type_name: name.clone(),
+            type_args: vec![],
+          };
+          self.values.insert(variant_name.clone(), Symbol { name: variant_name.clone(), spec });
+        },
+        Variant::TupleStruct(variant_name, tuple_members) => {
+          let type_args = tuple_members.iter().map(|type_name| match type_name {
+            TypeIdentifier::Singleton(TypeSingletonName { name, ..}) => name.clone(),
+            TypeIdentifier::Tuple(_) => unimplemented!(),
+          }).collect();
+          let spec = SymbolSpec::DataConstructor {
+            index,
+            type_name: name.clone(),
+            type_args
+          };
+          let symbol = Symbol { name: variant_name.clone(), spec };
+          self.values.insert(variant_name.clone(), symbol);
+        },
+        //TODO if there is only one variant, and it is a record, it doesn't need to have an
+        //explicit name
+        Variant::Record { name, members } => {
+          let fields = HashMap::new();
+          let spec = SymbolSpec::RecordConstructor { fields };
+          let symbol = Symbol { name: name.clone(), spec };
+          self.values.insert(name.clone(), symbol);
+        },
+      }
+    }
+    Ok(())
+  }
+}
+
+struct LocalTypeContext {
+  state: u8
+}
+impl LocalTypeContext {
+  fn new() -> LocalTypeContext {
+    LocalTypeContext { state: 0 }
+  }
+
+  fn new_universal_type(&mut self) -> TypeName {
+    let n = self.state;
+    self.state += 1;
+    Rc::new(format!("{}", (('a' as u8) + n) as char))
+  }
+}

schala-lang/language/src/tokenizing.rs

@@ -3,17 +3,16 @@ use std::collections::HashMap;
 use std::rc::Rc;
 use std::iter::{Iterator, Peekable};
 use std::fmt;
-use ::schala_codegen;
 
 #[derive(Debug, PartialEq, Clone)]
-pub enum TokenType {
+pub enum TokenKind {
   Newline, Semicolon,
 
   LParen, RParen,
   LSquareBracket, RSquareBracket,
   LAngleBracket, RAngleBracket,
   LCurlyBrace, RCurlyBrace,
-  Pipe,
+  Pipe, Backslash,
 
   Comma, Period, Colon, Underscore,
   Slash,
@@ -28,9 +27,9 @@ pub enum TokenType {
 
   Error(String),
 }
-use self::TokenType::*;
+use self::TokenKind::*;
 
-impl fmt::Display for TokenType {
+impl fmt::Display for TokenKind {
   fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
     match self {
       &Operator(ref s) => write!(f, "Operator({})", **s),
@@ -46,11 +45,12 @@ impl fmt::Display for TokenType {
 
 #[derive(Debug, Clone, Copy, PartialEq)]
 pub enum Kw {
-  If, Else,
+  If, Then, Else,
+  Is,
   Func,
-  For,
-  Match,
-  Var, Const, Let, In,
+  For, While,
+  Const, Let, In,
+  Mut,
   Return,
   Alias, Type, SelfType, SelfIdent,
   Interface, Impl,
@@ -62,14 +62,16 @@ lazy_static! {
   static ref KEYWORDS: HashMap<&'static str, Kw> =
     hashmap! {
       "if" => Kw::If,
+      "then" => Kw::Then,
       "else" => Kw::Else,
+      "is" => Kw::Is,
       "fn" => Kw::Func,
       "for" => Kw::For,
-      "match" => Kw::Match,
-      "var" => Kw::Var,
+      "while" => Kw::While,
       "const" => Kw::Const,
       "let" => Kw::Let,
       "in" => Kw::In,
+      "mut" => Kw::Mut,
       "return" => Kw::Return,
       "alias" => Kw::Alias,
       "type" => Kw::Type,
@@ -85,19 +87,24 @@ lazy_static! {
 
 #[derive(Debug, Clone)]
 pub struct Token {
-  pub token_type: TokenType,
-  pub offset: (usize, usize),
+  pub kind: TokenKind,
+  pub line_num: usize,
+  pub char_num: usize
 }
 
 impl Token {
-  pub fn get_error(&self) -> Option<&String> {
-    match self.token_type {
-      TokenType::Error(ref s) => Some(s),
+  pub fn get_error(&self) -> Option<String> {
+    match self.kind {
+      TokenKind::Error(ref s) => Some(s.clone()),
       _ => None,
     }
   }
   pub fn to_string_with_metadata(&self) -> String {
-    format!("{}(L:{},c:{})", self.token_type, self.offset.0, self.offset.1)
+    format!("{}(L:{},c:{})", self.kind, self.line_num, self.char_num)
+  }
+
+  pub fn get_kind(&self) -> TokenKind {
+    self.kind.clone()
   }
 }
 
@@ -106,9 +113,8 @@ fn is_operator(c: &char) -> bool {
   OPERATOR_CHARS.iter().any(|x| x == c)
 }
 
-type CharIter<I: Iterator<Item=(usize,usize,char)>> = Peekable<I>;
+type CharData = (usize, usize, char);
 
-#[schala_codegen::compiler_pass = "tokenization"]
 pub fn tokenize(input: &str) -> Vec<Token> {
   let mut tokens: Vec<Token> = Vec::new();
 
@@ -119,8 +125,8 @@ pub fn tokenize(input: &str) -> Vec<Token> {
       })
       .peekable();
 
-  while let Some((line_idx, ch_idx, c)) = input.next() {
-    let cur_tok_type = match c {
+  while let Some((line_num, char_num, c)) = input.next() {
+    let cur_tok_kind = match c {
       '/' => match input.peek().map(|t| t.2) {
         Some('/') => {
           while let Some((_, _, c)) = input.next() {
@@ -156,17 +162,18 @@ pub fn tokenize(input: &str) -> Vec<Token> {
       '{' => LCurlyBrace, '}' => RCurlyBrace,
       '[' => LSquareBracket, ']' => RSquareBracket,
       '"' => handle_quote(&mut input),
+      '\\' => Backslash,
       c if c.is_digit(10) => handle_digit(c, &mut input),
-      c if c.is_alphabetic() || c == '_' => handle_alphabetic(c, &mut input), //TODO I'll probably have to rewrite this if I care about types being uppercase, also type parameterization
+      c if c.is_alphabetic() || c == '_' => handle_alphabetic(c, &mut input),
       c if is_operator(&c) => handle_operator(c, &mut input),
       unknown => Error(format!("Unexpected character: {}", unknown)),
     };
-    tokens.push(Token { token_type: cur_tok_type, offset: (line_idx, ch_idx) });
+    tokens.push(Token { kind: cur_tok_kind, line_num, char_num });
   }
   tokens
 }
 
-fn handle_digit<I: Iterator<Item=(usize,usize,char)>>(c: char, input: &mut CharIter<I>) -> TokenType {
+fn handle_digit(c: char, input: &mut Peekable<impl Iterator<Item=CharData>>) -> TokenKind {
   if c == '0' && input.peek().map_or(false, |&(_, _, c)| { c == 'x' }) {
     input.next();
     let rest: String = input.peeking_take_while(|&(_, _, ref c)| c.is_digit(16) || *c == '_').map(|(_, _, c)| { c }).collect();
@@ -181,7 +188,7 @@ fn handle_digit<I: Iterator<Item=(usize,usize,char)>>(c: char, input: &mut CharI
   }
 }
 
-fn handle_quote<I: Iterator<Item=(usize,usize,char)>>(input: &mut CharIter<I>) -> TokenType {
+fn handle_quote(input: &mut Peekable<impl Iterator<Item=CharData>>) -> TokenKind {
   let mut buf = String::new();
   loop {
     match input.next().map(|(_, _, c)| { c }) {
@@ -200,22 +207,22 @@ fn handle_quote<I: Iterator<Item=(usize,usize,char)>>(input: &mut CharIter<I>) -
         }
       },
       Some(c) => buf.push(c),
-      None => return TokenType::Error(format!("Unclosed string")),
+      None => return TokenKind::Error(format!("Unclosed string")),
     }
   }
-  TokenType::StrLiteral(Rc::new(buf))
+  TokenKind::StrLiteral(Rc::new(buf))
 }
 
-fn handle_alphabetic<I: Iterator<Item=(usize,usize,char)>>(c: char, input: &mut CharIter<I>) -> TokenType {
+fn handle_alphabetic(c: char, input: &mut Peekable<impl Iterator<Item=CharData>>) -> TokenKind {
   let mut buf = String::new();
   buf.push(c);
   if c == '_' && input.peek().map(|&(_, _, c)| { !c.is_alphabetic() }).unwrap_or(true) {
-    return TokenType::Underscore
+    return TokenKind::Underscore
   }
 
   loop {
     match input.peek().map(|&(_, _, c)| { c }) {
-      Some(c) if c.is_alphanumeric() => {
+      Some(c) if c.is_alphanumeric() || c == '_' => {
         input.next();
         buf.push(c);
       },
@@ -224,12 +231,12 @@ fn handle_alphabetic<I: Iterator<Item=(usize,usize,char)>>(c: char, input: &mut
   }
 
   match KEYWORDS.get(buf.as_str()) {
-    Some(kw) => TokenType::Keyword(*kw),
-    None => TokenType::Identifier(Rc::new(buf)),
+    Some(kw) => TokenKind::Keyword(*kw),
+    None => TokenKind::Identifier(Rc::new(buf)),
   }
 }
 
-fn handle_operator<I: Iterator<Item=(usize,usize,char)>>(c: char, input: &mut CharIter<I>) -> TokenType {
+fn handle_operator(c: char, input: &mut Peekable<impl Iterator<Item=CharData>>) -> TokenKind {
   match c {
     '<' | '>' | '|' | '.' => {
       let ref next = input.peek().map(|&(_, _, c)| { c });
@@ -274,7 +281,7 @@ fn handle_operator<I: Iterator<Item=(usize,usize,char)>>(c: char, input: &mut Ch
       }
     }
   }
-  TokenType::Operator(Rc::new(buf))
+  TokenKind::Operator(Rc::new(buf))
 }
 
 #[cfg(test)]
@@ -289,26 +296,29 @@ mod schala_tokenizer_tests {
   #[test]
   fn tokens() {
     let a = tokenize("let a: A<B> = c ++ d");
-    let token_types: Vec<TokenType> = a.into_iter().map(move |t| t.token_type).collect();
-    assert_eq!(token_types, vec![Keyword(Let), ident!("a"), Colon, ident!("A"),
+    let token_kinds: Vec<TokenKind> = a.into_iter().map(move |t| t.kind).collect();
+    assert_eq!(token_kinds, vec![Keyword(Let), ident!("a"), Colon, ident!("A"),
       LAngleBracket, ident!("B"), RAngleBracket, op!("="), ident!("c"), op!("++"), ident!("d")]);
   }
 
   #[test]
   fn underscores() {
-    let token_types: Vec<TokenType> = tokenize("4_8").into_iter().map(move |t| t.token_type).collect();
-    assert_eq!(token_types, vec![digit!("4"), Underscore, digit!("8")]);
+    let token_kinds: Vec<TokenKind> = tokenize("4_8").into_iter().map(move |t| t.kind).collect();
+    assert_eq!(token_kinds, vec![digit!("4"), Underscore, digit!("8")]);
+
+    let token_kinds2: Vec<TokenKind> = tokenize("aba_yo").into_iter().map(move |t| t.kind).collect();
+    assert_eq!(token_kinds2, vec![ident!("aba_yo")]);
   }
 
   #[test]
   fn comments() {
-    let token_types: Vec<TokenType> = tokenize("1  + /* hella /* bro */ */ 2").into_iter().map(move |t| t.token_type).collect();
-    assert_eq!(token_types, vec![digit!("1"), op!("+"), digit!("2")]);
+    let token_kinds: Vec<TokenKind> = tokenize("1  + /* hella /* bro */ */ 2").into_iter().map(move |t| t.kind).collect();
+    assert_eq!(token_kinds, vec![digit!("1"), op!("+"), digit!("2")]);
   }
 
   #[test]
   fn backtick_operators() {
-    let token_types: Vec<TokenType> = tokenize("1 `plus` 2").into_iter().map(move |t| t.token_type).collect();
-    assert_eq!(token_types, vec![digit!("1"), op!("plus"), digit!("2")]);
+    let token_kinds: Vec<TokenKind> = tokenize("1 `plus` 2").into_iter().map(move |t| t.kind).collect();
+    assert_eq!(token_kinds, vec![digit!("1"), op!("plus"), digit!("2")]);
   }
 }

schala-lang/language/src/typechecking.rs

@@ -0,0 +1,254 @@
+use std::rc::Rc;
+
+use crate::ast::*;
+use crate::util::ScopeStack;
+
+pub type TypeName = Rc<String>;
+
+pub struct TypeContext<'a> {
+  variable_map: ScopeStack<'a, Rc<String>, Type<TVar>>,
+  evar_count: u32
+}
+
+/// `InferResult` is the monad in which type inference takes place.
+type InferResult<T> = Result<T, TypeError>;
+
+#[derive(Debug, Clone)]
+struct TypeError { msg: String }
+
+impl TypeError {
+  fn new<A>(msg: &str) -> InferResult<A> {
+    Err(TypeError { msg: msg.to_string() })
+  }
+}
+
+/// `Type` is parameterized by whether the type variables can be just universal, or universal or
+/// existential.
+#[derive(Debug, Clone)]
+enum Type<A> {
+  Var(A),
+  Const(TConst),
+  Arrow(Box<Type<A>>, Box<Type<A>>),
+}
+
+#[derive(Debug, Clone)]
+enum TVar {
+  Univ(UVar),
+  Exist(ExistentialVar)
+}
+
+#[derive(Debug, Clone)]
+struct UVar(Rc<String>);
+
+#[derive(Debug, Clone)]
+struct ExistentialVar(u32);
+
+impl Type<UVar> {
+  fn to_tvar(&self) -> Type<TVar> {
+    match self {
+      Type::Var(UVar(name)) => Type::Var(TVar::Univ(UVar(name.clone()))),
+      Type::Const(ref c) => Type::Const(c.clone()),
+      Type::Arrow(a, b) => Type::Arrow(
+        Box::new(a.to_tvar()),
+        Box::new(b.to_tvar())
+      )
+    }
+  }
+}
+
+impl Type<TVar> {
+  fn skolemize(&self) -> Type<UVar> {
+    match self {
+      Type::Var(TVar::Univ(uvar)) => Type::Var(uvar.clone()),
+      Type::Var(TVar::Exist(_)) => Type::Var(UVar(Rc::new(format!("sk")))),
+      Type::Const(ref c) => Type::Const(c.clone()),
+      Type::Arrow(a, b) => Type::Arrow(
+        Box::new(a.skolemize()),
+        Box::new(b.skolemize())
+      )
+    }
+  }
+}
+
+impl TypeIdentifier {
+  fn to_monotype(&self) -> Type<UVar> {
+    match self {
+      TypeIdentifier::Tuple(_) => Type::Const(TConst::Nat),
+      TypeIdentifier::Singleton(TypeSingletonName { name, .. }) => {
+        match &name[..] {
+          "Nat" => Type::Const(TConst::Nat),
+          "Int" => Type::Const(TConst::Int),
+          "Float" => Type::Const(TConst::Float),
+          "Bool" => Type::Const(TConst::Bool),
+          "String" => Type::Const(TConst::StringT),
+          _ => Type::Const(TConst::Nat),
+        }
+      }
+    }
+  }
+}
+
+#[derive(Debug, Clone)]
+enum TConst {
+  User(Rc<String>),
+  Unit,
+  Nat,
+  Int,
+  Float,
+  StringT,
+  Bool,
+}
+
+impl TConst {
+  fn user(name: &str) -> TConst {
+    TConst::User(Rc::new(name.to_string()))
+  }
+}
+
+impl<'a> TypeContext<'a> {
+  pub fn new() -> TypeContext<'a> {
+    TypeContext { 
+      variable_map: ScopeStack::new(None),
+      evar_count: 0
+    }
+  }
+
+  pub fn typecheck(&mut self, ast: &AST) -> Result<String, String> {
+    match self.infer_ast(ast) {
+      Ok(t) => Ok(format!("{:?}", t)),
+      Err(err) => Err(format!("Type error: {:?}", err))
+    }
+  }
+}
+
+impl<'a> TypeContext<'a> {
+  fn infer_ast(&mut self, ast: &AST) -> InferResult<Type<UVar>> {
+    self.infer_block(&ast.0)
+  }
+
+  fn infer_statement(&mut self, stmt: &Statement) -> InferResult<Type<UVar>> {
+    match stmt {
+      Statement::ExpressionStatement(ref expr) => self.infer_expr(expr.node()),
+      Statement::Declaration(ref decl) => self.infer_decl(decl),
+    }
+  }
+
+  fn infer_expr(&mut self, expr: &Expression) -> InferResult<Type<UVar>> {
+    match expr {
+      Expression(expr_type, Some(type_anno)) => {
+        let tx = self.infer_expr_type(expr_type)?;
+        let ty = type_anno.to_monotype();
+        self.unify(&ty.to_tvar(), &tx.to_tvar()).map(|x| x.skolemize())
+      },
+      Expression(expr_type, None) => self.infer_expr_type(expr_type)
+    }
+  }
+
+  fn infer_decl(&mut self, _decl: &Declaration) -> InferResult<Type<UVar>> {
+    Ok(Type::Const(TConst::user("unimplemented")))
+  }
+
+  fn infer_expr_type(&mut self, expr_type: &ExpressionType) -> InferResult<Type<UVar>> {
+    use self::ExpressionType::*;
+    Ok(match expr_type {
+      NatLiteral(_) => Type::Const(TConst::Nat),
+      FloatLiteral(_) => Type::Const(TConst::Float),
+      StringLiteral(_) => Type::Const(TConst::StringT),
+      BoolLiteral(_) => Type::Const(TConst::Bool),
+      Value(name) => {
+        //TODO handle the distinction between 0-arg constructors and variables at some point
+        // need symbol table for that
+        match self.variable_map.lookup(name) {
+          Some(ty) => ty.clone().skolemize(),
+          None => return TypeError::new(&format!("Variable {} not found", name))
+        }
+      },
+      IfExpression { discriminator, body } => self.infer_if_expr(discriminator, body)?,
+      Call { f, arguments } => {
+        let tf = self.infer_expr(f)?; //has to be an Arrow Type
+        let targ = self.infer_expr(&arguments[0].node())?; // TODO make this work with functions with more than one arg
+        match tf {
+          Type::Arrow(t1, t2) => {
+            self.unify(&t1.to_tvar(), &targ.to_tvar())?;
+            *t2.clone()
+          },
+          _ => return TypeError::new("not a function")
+        }
+      },
+
+      Lambda { params, .. } => {
+
+        let _arg_type = match &params[0] {
+          (_, Some(type_anno)) => type_anno.to_monotype().to_tvar(),
+          (_, None) => self.allocate_existential(),
+        };
+        //let _result_type = unimplemented!();
+        return TypeError::new("Unimplemented");
+
+        //Type::Arrow(Box::new(arg_type), Box::new(result_type))
+      }
+      _ => Type::Const(TConst::user("unimplemented"))
+    })
+  }
+
+  fn infer_if_expr(&mut self, discriminator: &Discriminator, body: &IfExpressionBody) -> InferResult<Type<UVar>> {
+    let _test = match discriminator {
+      Discriminator::Simple(expr) => expr,
+      _ => return TypeError::new("Dame desu")
+    };
+
+    let (_then_clause, _maybe_else_clause) = match body {
+      IfExpressionBody::SimpleConditional(a, b) => (a, b),
+      _ => return TypeError::new("Dont work")
+    };
+
+    TypeError::new("Not implemented")
+  }
+
+  fn infer_block(&mut self, block: &Block) -> InferResult<Type<UVar>> {
+    let mut output = Type::Const(TConst::Unit);
+    for statement in block.iter() {
+      output = self.infer_statement(statement.node())?;
+    }
+    Ok(output)
+  }
+
+  fn unify(&mut self, _t1: &Type<TVar>, _t2: &Type<TVar>) -> InferResult<Type<TVar>> {
+    TypeError::new("not implemented")
+  }
+
+  fn allocate_existential(&mut self) -> Type<TVar> {
+    let n = self.evar_count;
+    self.evar_count += 1;
+    Type::Var(TVar::Exist(ExistentialVar(n)))
+  }
+}
+
+#[cfg(test)]
+mod tests {
+  use super::*;
+
+  fn parse(input: &str) -> AST {
+    let tokens: Vec<crate::tokenizing::Token> = crate::tokenizing::tokenize(input);
+    let mut parser = crate::parsing::Parser::new(tokens);
+    parser.parse().unwrap()
+  }
+
+  macro_rules! type_test {
+    ($input:expr, $correct:expr) => {
+      {
+      let mut tc = TypeContext::new();
+      let ast = parse($input);
+      tc.add_symbols(&ast);
+      assert_eq!($correct, tc.type_check(&ast).unwrap())
+      }
+    }
+  }
+
+
+
+  #[test]
+  fn basic_inference() {
+
+  }
+}

schala-lang/language/src/util.rs

@@ -0,0 +1,43 @@
+use std::collections::HashMap;
+use std::hash::Hash;
+use std::cmp::Eq;
+
+#[derive(Default, Debug)]
+pub struct ScopeStack<'a, T: 'a, V: 'a>  where T: Hash + Eq {
+  parent: Option<&'a ScopeStack<'a, T, V>>,
+  values: HashMap<T, V>,
+  scope_name: Option<String>
+}
+
+impl<'a, T, V> ScopeStack<'a, T, V> where T: Hash + Eq {
+  pub fn new(name: Option<String>) -> ScopeStack<'a, T, V> where T: Hash + Eq {
+    ScopeStack {
+      parent: None,
+      values: HashMap::new(),
+      scope_name: name
+    }
+  }
+  pub fn insert(&mut self, key: T, value: V) where T: Hash + Eq {
+    self.values.insert(key, value);
+  }
+  pub fn lookup(&self, key: &T) -> Option<&V> where T: Hash + Eq {
+    match (self.values.get(key), self.parent) {
+      (None, None) => None,
+      (None, Some(parent)) => parent.lookup(key),
+      (Some(value), _) => Some(value),
+    }
+  }
+
+  pub fn new_scope(&'a self, name: Option<String>) -> ScopeStack<'a, T, V> where T: Hash + Eq {
+    ScopeStack {
+      parent: Some(self),
+      values: HashMap::default(),
+      scope_name: name,
+    }
+  }
+  #[allow(dead_code)]
+  pub fn get_name(&self) -> Option<&String> {
+    self.scope_name.as_ref()
+  }
+}
+

schala-lang/src/builtin.rs

@@ -1,77 +0,0 @@
-use std::rc::Rc;
-use std::collections::HashMap;
-
-use typechecking::{Type, TypeResult, TConst};
-use self::Type::*; use self::TConst::*;
-
-#[derive(Debug, PartialEq, Clone)]
-pub struct BinOp {
-  sigil: Rc<String>
-}
-
-impl BinOp {
-  pub fn from_sigil(sigil: &str) -> BinOp {
-    BinOp { sigil: Rc::new(sigil.to_string()) }
-  }
-  pub fn sigil(&self) -> &Rc<String> {
-    &self.sigil
-  }
-  pub fn get_type(&self) -> TypeResult<Type> {
-    let s = self.sigil.as_str();
-    BINOPS.get(s).map(|x| x.0.clone()).ok_or(format!("Binop {} not found", s))
-  }
-  pub fn min_precedence() -> i32 {
-    i32::min_value()
-  }
-  pub fn get_precedence(op: &str) -> i32 {
-    let default = 10_000_000;
-    BINOPS.get(op).map(|x| x.2.clone()).unwrap_or(default)
-  }
-}
-
-#[derive(Debug, PartialEq, Clone)]
-pub struct PrefixOp {
-  sigil: Rc<String>
-}
-
-impl PrefixOp {
-  pub fn from_sigil(sigil: &str) -> PrefixOp {
-    PrefixOp { sigil: Rc::new(sigil.to_string()) }
-  }
-  pub fn sigil(&self) -> &Rc<String> {
-    &self.sigil
-  }
-  pub fn is_prefix(op: &str) -> bool {
-    PREFIX_OPS.get(op).is_some()
-  }
-  pub fn get_type(&self) -> TypeResult<Type> {
-    let s = self.sigil.as_str();
-    PREFIX_OPS.get(s).map(|x| x.0.clone()).ok_or(format!("Prefix op {} not found", s))
-  }
-}
-lazy_static! {
-  static ref PREFIX_OPS: HashMap<&'static str, (Type, ())> = 
-    hashmap! {
-      "+" => (Func(bx!(Const(Int)),  bx!(Const(Int))), ()),
-      "-" => (Func(bx!(Const(Int)),  bx!(Const(Int))), ()),
-      "!" => (Func(bx!(Const(Bool)),  bx!(Const(Bool))), ()),
-    };
-}
-
-/* the second tuple member is a placeholder for when I want to make evaluation rules tied to the
- * binop definition */
-lazy_static! {
-  static ref BINOPS: HashMap<&'static str, (Type, (), i32)> =
-    hashmap! {
-      "+" => (Func(bx!(Const(Int)), bx!(Func(bx!(Const(Int)), bx!(Const(Int))))), (), 10),
-      "-" => (Func(bx!(Const(Int)), bx!(Func(bx!(Const(Int)), bx!(Const(Int))))), (), 10),
-      "*" => (Func(bx!(Const(Int)), bx!(Func(bx!(Const(Int)), bx!(Const(Int))))), (), 20),
-      "/" => (Func(bx!(Const(Int)), bx!(Func(bx!(Const(Int)), bx!(Const(Float))))), (), 20),
-      "//" => (Func(bx!(Const(Int)), bx!(Func(bx!(Const(Int)), bx!(Const(Int))))), (), 20), //TODO change this to `quot`
-      "%" => (Func(bx!(Const(Int)), bx!(Func(bx!(Const(Int)), bx!(Const(Int))))), (), 20),
-      "++" => (Func(bx!(Const(StringT)), bx!(Func(bx!(Const(StringT)), bx!(Const(StringT))))), (), 30),
-      "^" => (Func(bx!(Const(Int)), bx!(Func(bx!(Const(Int)), bx!(Const(Int))))), (), 20),
-      "&" => (Func(bx!(Const(Int)), bx!(Func(bx!(Const(Int)), bx!(Const(Int))))), (), 20),
-      "|" => (Func(bx!(Const(Int)), bx!(Func(bx!(Const(Int)), bx!(Const(Int))))), (), 20),
-    };
-}

schala-lang/src/eval.rs

@@ -1,317 +0,0 @@
-use std::collections::HashMap;
-use std::rc::Rc;
-use std::fmt::Write;
-
-use itertools::Itertools;
-
-use parsing::{AST, Statement, Declaration, Expression, Variant, ExpressionType};
-use builtin::{BinOp, PrefixOp};
-
-pub struct State<'a> {
-  parent_frame: Option<&'a State<'a>>,
-  values: HashMap<Rc<String>, ValueEntry>,
-}
-
-impl<'a> State<'a> {
-
-  fn insert(&mut self, name: Rc<String>, value: ValueEntry) {
-    self.values.insert(name, value);
-  }
-  fn lookup(&self, name: &Rc<String>) -> Option<&ValueEntry> {
-    match (self.values.get(name), self.parent_frame) {
-      (None, None) => None,
-      (None, Some(parent)) => parent.lookup(name),
-      (Some(value), _) => Some(value),
-    }
-  }
-}
-
-#[derive(Debug)]
-enum ValueEntry {
-  Binding {
-    val: FullyEvaluatedExpr,
-  },
-  Function {
-    param_names: Vec<Rc<String>>,
-    body: Vec<Statement>,
-  }
-}
-
-type EvalResult<T> = Result<T, String>;
-
-#[derive(Debug, PartialEq, Clone)]
-enum FullyEvaluatedExpr {
-  UnsignedInt(u64),
-  SignedInt(i64),
-  Float(f64),
-  Str(String),
-  Bool(bool),
-  FuncLit(Rc<String>),
-  Custom {
-    string_rep: Rc<String>,
-  },
-  Tuple(Vec<FullyEvaluatedExpr>),
-  List(Vec<FullyEvaluatedExpr>)
-}
-
-impl FullyEvaluatedExpr {
-  fn to_string(&self) -> String {
-    use self::FullyEvaluatedExpr::*;
-    match self {
-      &UnsignedInt(ref n) => format!("{}", n),
-      &SignedInt(ref n) => format!("{}", n),
-      &Float(ref f) => format!("{}", f),
-      &Str(ref s) => format!("\"{}\"", s),
-      &Bool(ref b) => format!("{}", b),
-      &Custom { ref string_rep } => format!("{}", string_rep),
-      &Tuple(ref items) => {
-        let mut buf = String::new();
-        write!(buf, "(").unwrap();
-        for term in items.iter().map(|e| Some(e)).intersperse(None) {
-          match term {
-            Some(e) => write!(buf, "{}", e.to_string()).unwrap(),
-            None => write!(buf, ", ").unwrap(),
-          };
-        }
-        write!(buf, ")").unwrap();
-        buf
-      },
-      &FuncLit(ref name) => format!("<function {}>", name),
-      &List(ref items) => {
-        let mut buf = String::new();
-        write!(buf, "[").unwrap();
-        for term in items.iter().map(|e| Some(e)).intersperse(None) {
-          match term {
-            Some(e) => write!(buf, "{}", e.to_string()).unwrap(),
-            None => write!(buf, ", ").unwrap()
-          }
-        }
-        write!(buf, "]").unwrap();
-        buf
-      }
-    }
-  }
-}
-
-impl<'a> State<'a> {
-  pub fn new() -> State<'a> {
-    State { parent_frame: None, values: HashMap::new() }
-  }
-
-  pub fn new_with_parent(parent: &'a State<'a>) -> State<'a> {
-    State { parent_frame: Some(parent), values: HashMap::new() }
-  }
-
-  pub fn evaluate(&mut self, ast: AST) -> Vec<Result<String, String>> {
-    let mut acc = vec![];
-    for statement in ast.0 {
-      match self.eval_statement(statement) {
-        Ok(output) => {
-          if let Some(fully_evaluated) = output {
-            acc.push(Ok(fully_evaluated.to_string()));
-          }
-        },
-        Err(error) => {
-          acc.push(Err(format!("Eval error: {}", error)));
-          return acc;
-        },
-      }
-    }
-    acc
-  }
-}
-
-impl<'a> State<'a> {
-  fn eval_statement(&mut self, statement: Statement) -> EvalResult<Option<FullyEvaluatedExpr>> {
-    Ok(match statement {
-      Statement::ExpressionStatement(expr) => Some(self.eval_expr(expr)?),
-      Statement::Declaration(decl) => { self.eval_decl(decl)?; None }
-    })
-  }
-
-  fn eval_decl(&mut self, decl: Declaration) -> EvalResult<()> {
-    use self::Declaration::*;
-    use self::Variant::*;
-
-    match decl {
-      FuncDecl(signature, statements) => {
-        let name = signature.name;
-        let param_names: Vec<Rc<String>> = signature.params.iter().map(|fp| fp.0.clone()).collect();
-        self.insert(name, ValueEntry::Function { body: statements.clone(), param_names });
-      },
-      TypeDecl(_name, body) => {
-        for variant in body.0.iter() {
-          match variant {
-            &UnitStruct(ref name) => self.insert(name.clone(),
-              ValueEntry::Binding { val: FullyEvaluatedExpr::Custom { string_rep: name.clone() } }),
-            &TupleStruct(ref _name, ref _args) =>  unimplemented!(),
-            &Record(ref _name, ref _fields) => unimplemented!(),
-          };
-        }
-      },
-      Binding { name, expr, ..} => {
-        let val = self.eval_expr(expr)?;
-        self.insert(name.clone(), ValueEntry::Binding { val });
-      },
-      _ => return Err(format!("Declaration evaluation not yet implemented"))
-    }
-    Ok(())
-  }
-
-  fn eval_expr(&mut self, expr: Expression) -> EvalResult<FullyEvaluatedExpr> {
-    use self::ExpressionType::*;
-    use self::FullyEvaluatedExpr::*;
-
-    let expr_type = expr.0;
-    match expr_type {
-      IntLiteral(n) => Ok(UnsignedInt(n)),
-      FloatLiteral(f) => Ok(Float(f)),
-      StringLiteral(s) => Ok(Str(s.to_string())),
-      BoolLiteral(b) => Ok(Bool(b)),
-      PrefixExp(op, expr) => self.eval_prefix_exp(op, expr),
-      BinExp(op, lhs, rhs) => self.eval_binexp(op, lhs, rhs),
-      Value(name) => self.eval_value(name),
-      TupleLiteral(expressions) => {
-        let mut evals = Vec::new();
-        for expr in expressions {
-          match self.eval_expr(expr) {
-            Ok(fully_evaluated) => evals.push(fully_evaluated),
-            error => return error,
-          }
-        }
-        Ok(Tuple(evals))
-      }
-      Call { f, arguments } => {
-        let mut evaled_arguments = Vec::new();
-        for arg in arguments.into_iter() {
-          evaled_arguments.push(self.eval_expr(arg)?);
-        }
-        self.eval_application(*f, evaled_arguments)
-      },
-      Index { box indexee, indexers } => {
-        let evaled = self.eval_expr(indexee)?;
-        match evaled {
-          Tuple(mut exprs) => {
-            let len = indexers.len();
-            if len == 1 {
-              let idx = indexers.into_iter().nth(0).unwrap();
-              match self.eval_expr(idx)? {
-                UnsignedInt(n) if (n as usize) < exprs.len() => Ok(exprs.drain(n as usize..).next().unwrap()),
-                UnsignedInt(n) => Err(format!("Index {} out of range", n)),
-                other => Err(format!("{:?} is not an unsigned integer", other)),
-              }
-            } else {
-              Err(format!("Tuple index must be one integer"))
-            }
-          },
-          _ => Err(format!("Bad index expression"))
-        }
-      },
-      ListLiteral(items) => Ok(List(items.into_iter().map(|item| self.eval_expr(item)).collect::<Result<Vec<_>,_>>()?)),
-      x => Err(format!("Unimplemented thing {:?}", x)),
-    }
-  }
-
-  fn eval_application(&mut self, f: Expression, arguments: Vec<FullyEvaluatedExpr>) -> EvalResult<FullyEvaluatedExpr> {
-    use self::ExpressionType::*;
-    match f {
-      Expression(Value(ref identifier), _) if self.is_builtin(identifier) =>  self.eval_builtin(identifier, arguments),
-      Expression(Value(identifier), _) => {
-        match self.lookup(&identifier) {
-          Some(&ValueEntry::Function { ref body, ref param_names }) => {
-            if arguments.len() != param_names.len() {
-              return Err(format!("Wrong number of arguments for the function"));
-            }
-            let mut new_state = State::new_with_parent(self);
-            let sub_ast = body.clone();
-            for (param, val) in param_names.iter().zip(arguments.into_iter()) {
-              new_state.insert(param.clone(), ValueEntry::Binding { val });
-            }
-            let mut ret: Option<FullyEvaluatedExpr> = None;
-            for statement in sub_ast.into_iter() {
-              ret = new_state.eval_statement(statement)?;
-            }
-            Ok(ret.unwrap_or(FullyEvaluatedExpr::Custom { string_rep: Rc::new("()".to_string()) }))
-          },
-          _ => Err(format!("Function {} not found", identifier)),
-        }
-      },
-      x => Err(format!("Trying to apply {:?} which is not a function", x)),
-    }
-  }
-  fn is_builtin(&self, name: &Rc<String>) -> bool {
-    match &name.as_ref()[..] {
-      "print" | "println" => true,
-      _ => false
-    }
-  }
-  fn eval_builtin(&mut self, name: &Rc<String>, args: Vec<FullyEvaluatedExpr>) -> EvalResult<FullyEvaluatedExpr> {
-    use self::FullyEvaluatedExpr::*;
-    match &name.as_ref()[..] {
-      "print" => {
-        for arg in args {
-          print!("{}", arg.to_string());
-        }
-        Ok(Tuple(vec![]))
-      },
-      "println" => {
-        for arg in args {
-          println!("{}", arg.to_string());
-        }
-        Ok(Tuple(vec![]))
-      },
-      _ => unreachable!()
-    }
-  }
-  fn eval_value(&mut self, name: Rc<String>) -> EvalResult<FullyEvaluatedExpr> {
-    use self::ValueEntry::*;
-    match self.lookup(&name) {
-      None => return Err(format!("Value {} not found", *name)),
-      Some(lookup) => match lookup {
-        &Binding { ref val } => Ok(val.clone()),
-        &Function { .. } =>  Ok(FullyEvaluatedExpr::FuncLit(name.clone()))
-      }
-    }
-  }
-
-  fn eval_binexp(&mut self, op: BinOp, lhs: Box<Expression>, rhs: Box<Expression>) -> EvalResult<FullyEvaluatedExpr> {
-    use self::FullyEvaluatedExpr::*;
-    let evaled_lhs = self.eval_expr(*lhs)?;
-    let evaled_rhs = self.eval_expr(*rhs)?;
-    let sigil = op.sigil();
-    //let sigil: &str = op.sigil().as_ref().as_str();
-    Ok(match (sigil.as_str(), evaled_lhs, evaled_rhs) {
-      ("+", UnsignedInt(l), UnsignedInt(r)) => UnsignedInt(l + r),
-      ("++", Str(s1), Str(s2)) => Str(format!("{}{}", s1, s2)),
-      ("-", UnsignedInt(l), UnsignedInt(r)) => UnsignedInt(l - r),
-      ("*", UnsignedInt(l), UnsignedInt(r)) => UnsignedInt(l * r),
-      ("/", UnsignedInt(l), UnsignedInt(r)) => Float((l as f64)/ (r as f64)),
-      ("//", UnsignedInt(l), UnsignedInt(r)) => if r == 0 {
-        return Err(format!("Runtime error: divide by zero"));
-      } else {
-        UnsignedInt(l / r)
-      },
-      ("%", UnsignedInt(l), UnsignedInt(r)) => UnsignedInt(l % r),
-      ("^", UnsignedInt(l), UnsignedInt(r)) => UnsignedInt(l ^ r),
-      ("&", UnsignedInt(l), UnsignedInt(r)) => UnsignedInt(l & r),
-      ("|", UnsignedInt(l), UnsignedInt(r)) => UnsignedInt(l | r),
-      _ => return Err(format!("Runtime error: not yet implemented")),
-    })
-  }
-
-  fn eval_prefix_exp(&mut self, op: PrefixOp, expr: Box<Expression>) -> EvalResult<FullyEvaluatedExpr> {
-    use self::FullyEvaluatedExpr::*;
-    let evaled_expr = self.eval_expr(*expr)?;
-    let sigil = op.sigil();
-
-    Ok(match (sigil.as_str(), evaled_expr) {
-      ("!", Bool(true)) => Bool(false),
-      ("!", Bool(false)) => Bool(true),
-      ("-", UnsignedInt(n)) => SignedInt(-1*(n as i64)),
-      ("-", SignedInt(n)) => SignedInt(-1*(n as i64)),
-      ("+", SignedInt(n)) => SignedInt(n),
-      ("+", UnsignedInt(n)) => UnsignedInt(n),
-      _ => return Err(format!("Runtime error: not yet implemented")),
-    })
-  }
-}

schala-lang/src/lib.rs

@@ -1,127 +0,0 @@
-#![feature(slice_patterns, box_patterns, box_syntax)]
-#![feature(proc_macro)]
-extern crate itertools;
-#[macro_use]
-extern crate lazy_static;
-#[macro_use]
-extern crate maplit;
-
-extern crate schala_repl;
-extern crate schala_codegen;
-
-use std::collections::HashMap;
-use itertools::Itertools;
-use schala_repl::{ProgrammingLanguageInterface, EvalOptions, TraceArtifact, UnfinishedComputation, FinishedComputation};
-
-macro_rules! bx {
-  ($e:expr) => { Box::new($e) }
-}
-
-mod builtin;
-
-mod tokenizing;
-mod parsing;
-mod typechecking;
-mod eval;
-
-use self::typechecking::{TypeContext};
-
-/* TODO eventually custom-derive ProgrammingLanguageInterface with compiler passes as options */
-pub struct Schala {
-  state: eval::State<'static>,
-  type_context: TypeContext
-}
-
-impl Schala {
-  pub fn new() -> Schala {
-    Schala {
-      state: eval::State::new(),
-      type_context: TypeContext::new(),
-    }
-  }
-}
-
-impl ProgrammingLanguageInterface for Schala {
-
-  schala_codegen::compiler_pass_sequence!(["tokenize", "parse", "yolo"]);
-
-  fn get_language_name(&self) -> String {
-    "Schala".to_string()
-  }
-
-  fn get_source_file_suffix(&self) -> String {
-    format!("schala")
-  }
-
-  fn execute(&mut self, input: &str, options: &EvalOptions) -> FinishedComputation {
-
-    let mut evaluation = UnfinishedComputation::default();
-
-    //tokenzing
-    let tokens = tokenizing::tokenize(input);
-    if options.debug.tokens {
-      let token_string = tokens.iter().map(|t| format!("{:?}<L:{},C:{}>", t.token_type, t.offset.0, t.offset.1)).join(", ");
-      evaluation.add_artifact(TraceArtifact::new("tokens", token_string));
-    }
-
-    {
-      let token_errors: Vec<&String> = tokens.iter().filter_map(|t| t.get_error()).collect();
-      if token_errors.len() != 0 {
-        return evaluation.output(Err(format!("Tokenization error: {:?}\n", token_errors)));
-      }
-    }
-
-    // parsing
-    let ast = match parsing::parse(tokens) {
-      (Ok(ast), trace) => {
-        if options.debug.parse_tree {
-          evaluation.add_artifact(TraceArtifact::new_parse_trace(trace));
-        }
-        if options.debug.ast {
-          evaluation.add_artifact(TraceArtifact::new("ast", format!("{:#?}", ast)));
-        }
-        ast
-      },
-      (Err(err), trace) => {
-        if options.debug.parse_tree {
-          evaluation.add_artifact(TraceArtifact::new_parse_trace(trace));
-        }
-        return evaluation.output(Err(format!("Parse error: {:?}\n", err.msg)));
-      }
-    };
-
-    //symbol table
-    match self.type_context.add_top_level_types(&ast) {
-      Ok(()) => (),
-      Err(msg) => {
-        if options.debug.type_checking {
-          evaluation.add_artifact(TraceArtifact::new("type_check", msg));
-        }
-      }
-    };
-
-    //typechecking
-    match self.type_context.type_check_ast(&ast) {
-      Ok(ty) => {
-        if options.debug.type_checking {
-          evaluation.add_artifact(TraceArtifact::new("type_check", format!("{:?}", ty)));
-        }
-      },
-      Err(msg) => evaluation.add_artifact(TraceArtifact::new("type_check", msg)),
-    };
-
-    let text = self.type_context.debug_symbol_table();
-    if options.debug.symbol_table {
-      evaluation.add_artifact(TraceArtifact::new("symbol_table", text));
-    }
-
-    let evaluation_outputs = self.state.evaluate(ast);
-    let text_output: Result<Vec<String>, String> = evaluation_outputs
-      .into_iter()
-      .collect();
-
-    let eval_output = text_output
-      .map(|v| { v.into_iter().intersperse(format!("\n")).collect() });
-    evaluation.output(eval_output)
-  }
-}

schala-lang/src/typechecking.rs

@@ -1,254 +0,0 @@
-use std::rc::Rc;
-use std::collections::HashMap;
-use std::char;
-use std::fmt;
-use std::fmt::Write;
-
-use itertools::Itertools;
-
-use parsing;
-
-pub struct TypeContext { 
-  type_var_count: u64,
-  bindings: HashMap<Rc<String>, Type>,
-}
-
-#[derive(Debug, PartialEq, Clone)]
-pub enum Type {
-  Const(TConst),
-  Sum(Vec<Type>),
-  Func(Box<Type>, Box<Type>),
-  UVar(String),
-  EVar(u64),
-  Void
-}
-
-impl fmt::Display for Type {
-  fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
-    use self::Type::*;
-    match self {
-      &Const(ref c) => write!(f, "{:?}", c),
-      &Sum(ref types) => {
-        write!(f, "(")?;
-        for item in types.iter().map(|ty| Some(ty)).intersperse(None) {
-          match item {
-            Some(ty) => write!(f, "{}", ty)?,
-            None => write!(f, ",")?,
-          };
-        }
-        write!(f, ")")
-      },
-      &Func(ref a, ref b) => write!(f, "{} -> {}", a, b),
-      &UVar(ref s) => write!(f, "{}_u", s),
-      &EVar(ref n) => write!(f, "{}_e", n),
-      &Void => write!(f, "Void")
-    }
-  }
-}
-
-#[derive(Default)]
-struct UVarGenerator {
-  n: u32,
-}
-impl UVarGenerator {
-  fn new() -> UVarGenerator {
-    UVarGenerator::default()
-  }
-  fn next(&mut self) -> Type {
-    //TODO handle this in the case where someone wants to make a function with more than 26 variables
-    let s = format!("{}", unsafe { char::from_u32_unchecked(self.n + ('a' as u32)) });
-    self.n += 1;
-    Type::UVar(s)
-  }
-}
-
-#[derive(Debug, PartialEq, Clone)]
-pub enum TConst {
-  Unit,
-  Int,
-  Float,
-  StringT,
-  Bool,
-  Custom(String),
-}
-
-impl parsing::TypeName {
-  fn to_type(&self) -> TypeResult<Type> {
-    use self::parsing::TypeSingletonName;
-    use self::parsing::TypeName::*;
-    use self::Type::*; use self::TConst::*;
-    Ok(match self {
-      &Tuple(_) => return Err(format!("Tuples not yet implemented")),
-      &Singleton(ref name) => match name {
-        &TypeSingletonName { ref name, .. } => match &name[..] {
-          "Int" => Const(Int),
-          "Float" => Const(Float),
-          "Bool" => Const(Bool),
-          "String" => Const(StringT),
-          n => Const(Custom(n.to_string()))
-        }
-      }
-    })
-  }
-}
-
-pub type TypeResult<T> = Result<T, String>;
-
-impl TypeContext {
-  pub fn new() -> TypeContext {
-    TypeContext { bindings: HashMap::new(), type_var_count: 0 }
-  }
-  pub fn fresh(&mut self) -> Type {
-    let ret = self.type_var_count;
-    self.type_var_count += 1;
-    Type::EVar(ret)
-  }
-}
-
-impl TypeContext {
-  pub fn add_top_level_types(&mut self, ast: &parsing::AST) -> TypeResult<()> {
-    use self::parsing::TypeName;
-    use self::parsing::Declaration::*;
-    use self::Type::*;
-    for statement in ast.0.iter() {
-      if let &self::parsing::Statement::Declaration(ref decl) = statement {
-        match decl {
-          &FuncSig(ref signature) | &FuncDecl(ref signature, _) => {
-            let mut uvar_gen = UVarGenerator::new();
-            let mut ty: Type = signature.type_anno.as_ref().map(|name: &TypeName| name.to_type()).unwrap_or_else(|| {Ok(uvar_gen.next())} )?;
-            for &(_, ref type_name) in signature.params.iter().rev() {
-              let arg_type = type_name.as_ref().map(|name| name.to_type()).unwrap_or_else(|| {Ok(uvar_gen.next())} )?;
-              ty = Func(bx!(arg_type), bx!(ty));
-            }
-            self.bindings.insert(signature.name.clone(), ty);
-          },
-          _ => ()
-        }
-      }
-    }
-    Ok(())
-  }
-  pub fn debug_symbol_table(&self) -> String {
-    let mut output = format!("Symbols\n");
-    for (sym, ty) in &self.bindings {
-      write!(output, "{} : {}\n", sym, ty).unwrap();
-    }
-    output
-  }
-}
-
-impl TypeContext {
-  pub fn type_check_ast(&mut self, ast: &parsing::AST) -> TypeResult<Type> {
-    use self::Type::*; use self::TConst::*;
-    let mut ret_type = Const(Unit);
-    for statement in ast.0.iter() {
-      ret_type = self.type_check_statement(statement)?;
-    }
-    Ok(ret_type)
-  }
-  fn type_check_statement(&mut self, statement: &parsing::Statement) -> TypeResult<Type> {
-    use self::parsing::Statement::*;
-    match statement {
-      &ExpressionStatement(ref expr) => self.infer(expr),
-      &Declaration(ref decl) => self.add_declaration(decl),
-    }
-  }
-  fn add_declaration(&mut self, decl: &parsing::Declaration) -> TypeResult<Type> {
-    use self::parsing::Declaration::*;
-    use self::Type::*;
-    match decl {
-      &Binding { ref name, ref expr, .. } => {
-        let ty = self.infer(expr)?;
-        self.bindings.insert(name.clone(), ty);
-      },
-      _ => return Err(format!("other formats not done"))
-    }
-    Ok(Void)
-  }
-  fn infer(&mut self, expr: &parsing::Expression) -> TypeResult<Type> {
-    use self::parsing::Expression;
-    match expr {
-      &Expression(ref e, Some(ref anno)) => {
-        let anno_ty = anno.to_type()?;
-        let ty = self.infer_exprtype(&e)?;
-        self.unify(ty, anno_ty)
-      },
-      &Expression(ref e, None) => self.infer_exprtype(e)
-    }
-  }
-  fn infer_exprtype(&mut self, expr: &parsing::ExpressionType) -> TypeResult<Type> {
-    use self::parsing::ExpressionType::*;
-    use self::Type::*; use self::TConst::*;
-    match expr {
-      &IntLiteral(_) => Ok(Const(Int)),
-      &FloatLiteral(_) => Ok(Const(Float)),
-      &StringLiteral(_) => Ok(Const(StringT)),
-      &BoolLiteral(_) => Ok(Const(Bool)),
-      &BinExp(ref op, ref lhs, ref rhs) => { /* remember there are both the haskell convention talk and the write you a haskell ways to do this! */
-        match op.get_type()? {
-          Func(box t1, box Func(box t2, box t3)) => {
-            let lhs_ty = self.infer(lhs)?;
-            let rhs_ty = self.infer(rhs)?;
-            self.unify(t1, lhs_ty)?;
-            self.unify(t2, rhs_ty)?;
-            Ok(t3)
-          },
-          other => Err(format!("{:?} is not a binary function type", other))
-        }
-      },
-      &PrefixExp(ref op, ref expr) => match op.get_type()? {
-        Func(box t1, box t2) => {
-          let expr_ty = self.infer(expr)?;
-          self.unify(t1, expr_ty)?;
-          Ok(t2)
-        },
-        other => Err(format!("{:?} is not a prefix op function type", other))
-      },
-      &Value(ref name) => {
-        match self.bindings.get(name) {
-          Some(ty) => Ok(ty.clone()),
-          None => Err(format!("No binding found for variable: {}", name)),
-        }
-      },
-      &Call { ref f, ref arguments } => {
-        let mut tf = self.infer(f)?;
-        for arg in arguments.iter() {
-          match tf {
-            Func(box t, box rest) => {
-              let t_arg = self.infer(arg)?;
-              self.unify(t, t_arg)?;
-              tf = rest;
-            },
-            other => return Err(format!("Function call failed to unify; last type: {:?}", other)),
-          }
-        }
-        Ok(tf)
-      },
-      &TupleLiteral(ref expressions) => {
-        let mut types = vec![];
-        for expr in expressions {
-          types.push(self.infer(expr)?);
-        }
-        Ok(Sum(types))
-      },
-      /*
-  Index {
-    indexee: Box<Expression>,
-    indexers: Vec<Expression>,
-  },
-  IfExpression(Box<Expression>, Vec<Statement>, Option<Vec<Statement>>),
-  MatchExpression(Box<Expression>, Vec<MatchArm>),
-  ForExpression
-      */
-      _ => Err(format!("Type not yet implemented"))
-    }
-  }
-  fn unify(&mut self, t1: Type, t2: Type) -> TypeResult<Type> {
-    use self::Type::*;// use self::TConst::*;
-    match (t1, t2) {
-      (Const(ref a), Const(ref b)) if a == b => Ok(Const(a.clone())),
-      (a, b) => Err(format!("Types {:?} and {:?} don't unify", a, b))
-    }
-  }
-}
-

schala-repl-codegen/Cargo.toml

@@ -0,0 +1,13 @@
+[package]
+name = "schala-repl-codegen"
+version = "0.1.0"
+authors = ["greg <greg.shuflin@protonmail.com>"]
+
+[dependencies]
+syn = { version = "0.15.6", features = ["full", "extra-traits"] }
+quote = "0.6.8"
+proc-macro2 = "0.4.19"
+schala-repl = { path = "../schala-repl" }
+
+[lib]
+proc-macro = true

schala-repl-codegen/src/lib.rs

@@ -0,0 +1,199 @@
+#![feature(trace_macros)]
+#![recursion_limit="128"]
+extern crate proc_macro;
+extern crate proc_macro2;
+#[macro_use]
+extern crate quote;
+extern crate syn;
+
+use proc_macro::TokenStream;
+use syn::{Ident, Attribute, DeriveInput};
+
+fn find_attr_by_name<'a>(name: &str, attrs: &'a Vec<Attribute>) -> Option<&'a Attribute> {
+  attrs.iter().find(|attr| {
+    let first = attr.path.segments.first();
+    let seg: Option<&&syn::PathSegment> = first.as_ref().map(|x| x.value());
+    seg.map(|seg| seg.ident.to_string() == name).unwrap_or(false)
+  })
+}
+
+fn extract_attribute_arg_by_name(name: &str, attrs: &Vec<Attribute>) -> Option<String> {
+  use syn::{Meta, Lit, MetaNameValue};
+  find_attr_by_name(name, attrs)
+  .and_then(|attr| {
+    match attr.interpret_meta() {
+      Some(Meta::NameValue(MetaNameValue { lit: Lit::Str(litstr), .. })) => Some(litstr.value()),
+      _ => None,
+    }
+  })
+}
+
+fn extract_attribute_list(name: &str, attrs: &Vec<Attribute>) -> Option<Vec<(Ident, Option<Vec<Ident>>)>> {
+  use syn::{Meta, MetaList, NestedMeta};
+  find_attr_by_name(name, attrs)
+  .and_then(|attr| {
+    match attr.interpret_meta() {
+      Some(Meta::List(MetaList { nested, .. })) => {
+        Some(nested.iter().map(|nested_meta| match nested_meta {
+          &NestedMeta::Meta(Meta::Word(ref ident)) => (ident.clone(), None),
+          &NestedMeta::Meta(Meta::List(MetaList { ref ident, nested: ref nested2, .. })) => {
+            let own_args = nested2.iter().map(|nested_meta2| match nested_meta2 {
+              &NestedMeta::Meta(Meta::Word(ref ident)) => ident.clone(),
+              _ => panic!("Bad format for doubly-nested attribute list")
+            }).collect();
+            (ident.clone(), Some(own_args))
+          },
+          _ => panic!("Bad format for nested list")
+        }).collect())
+      },
+      _ => panic!("{} must be a comma-delimited list surrounded by parens", name)
+    }
+  })
+}
+
+fn get_attribute_identifier(attr_name: &str, attrs: &Vec<Attribute>) -> Option<proc_macro2::Ident> {
+  find_attr_by_name(attr_name, attrs).and_then(|attr| {
+    let tts = attr.tts.clone().into_iter().collect::<Vec<_>>();
+
+    if tts.len() == 2 {
+      let ref after_equals: proc_macro2::TokenTree = tts[1];
+      match after_equals {
+        proc_macro2::TokenTree::Ident(ident)  => Some(ident.clone()),
+        _ => None
+      }
+    } else {
+      None
+    }
+  })
+}
+
+/* a pass_chain function signature with input A and output B looks like:
+ * fn(A, &mut ProgrammingLanguageInterface, Option<&mut DebugHandler>) -> Result<B, String>
+ *
+ * TODO use some kind of failure-handling library to make this better
+ */
+fn generate_pass_chain(idents: Vec<Ident>) -> proc_macro2::TokenStream {
+  let final_return = quote! {
+    {
+      let final_output: FinishedComputation = unfinished_computation.finish(Ok(input_to_next_stage));
+      final_output
+    }
+  };
+
+  let nested_passes = idents.iter()
+    .rev()
+    .fold(final_return, |later_fragment, pass_name| {
+      quote! {
+        {
+          let pass_name = stringify!(#pass_name);
+          let (output, duration) = {
+            let ref debug_map = eval_options.debug_passes;
+            let debug_handle = match debug_map.get(pass_name) {
+              Some(PassDebugOptionsDescriptor { opts }) => {
+                let ptr = &mut unfinished_computation;
+                ptr.cur_debug_options = opts.clone();
+                Some(ptr)
+              }
+              _ => None
+            };
+            let start = time::Instant::now();
+            let pass_output = #pass_name(input_to_next_stage, self, debug_handle);
+            let elapsed = start.elapsed();
+            (pass_output, elapsed)
+          };
+          if eval_options.debug_timing {
+            unfinished_computation.durations.push(duration);
+          }
+          match output {
+            Ok(input_to_next_stage) => #later_fragment,
+            //TODO this error type needs to be guaranteed to provide a useable string
+            Err(err) => return unfinished_computation.output(Err(format!("Pass {} failed:\n{}", pass_name, err))),
+          }
+        }
+      }
+    });
+
+  quote! {
+    {
+      use std::time;
+      use schala_repl::PassDebugOptionsDescriptor;
+
+      let eval_options = options;
+      let input_to_next_stage = input;
+      let mut unfinished_computation = UnfinishedComputation::default();
+      #nested_passes
+    }
+  }
+}
+
+#[proc_macro_derive(ProgrammingLanguageInterface,
+  attributes(LanguageName, SourceFileExtension, PipelineSteps, DocMethod, HandleCustomInterpreterDirectives))]
+pub fn derive_programming_language_interface(input: TokenStream) -> TokenStream {
+  let ast: DeriveInput = syn::parse(input).unwrap();
+  let name = &ast.ident;
+  let attrs = &ast.attrs;
+
+  let language_name: String = extract_attribute_arg_by_name("LanguageName", attrs).expect("LanguageName is required");
+  let file_ext = extract_attribute_arg_by_name("SourceFileExtension", attrs).expect("SourceFileExtension is required");
+  let passes = extract_attribute_list("PipelineSteps", attrs).expect("PipelineSteps are required");
+  let pass_idents = passes.iter().map(|x| x.0.clone());
+
+  let get_doc_impl = match get_attribute_identifier("DocMethod", attrs) {
+    None => quote! { },
+    Some(method_name) => quote! {
+      fn get_doc(&self, commands: &Vec<&str>) -> Option<String> {
+        self.#method_name(commands)
+      }
+    }
+  };
+
+  let handle_custom_interpreter_directives_impl = match get_attribute_identifier("HandleCustomInterpreterDirectives", attrs) {
+    None => quote! { },
+    Some(method_name) => quote! {
+      fn handle_custom_interpreter_directives(&mut self, commands: &Vec<&str>) -> Option<String> {
+        //println!("If #method_name is &self not &mut self, this runs forever");
+        self.#method_name(commands)
+      }
+    }
+  };
+
+  let pass_descriptors = passes.iter().map(|pass| {
+    let name = pass.0.to_string();
+    let opts: Vec<String> = match &pass.1 {
+      None => vec![],
+      Some(opts) => opts.iter().map(|o| o.to_string()).collect(),
+    };
+
+    quote! {
+      PassDescriptor {
+        name: #name.to_string(),
+        debug_options: vec![#(format!(#opts)),*]
+      }
+    }
+  });
+
+  let pass_chain = generate_pass_chain(pass_idents.collect());
+
+  let tokens = quote! {
+    use schala_repl::PassDescriptor;
+    impl ProgrammingLanguageInterface for #name {
+      fn get_language_name(&self) -> String {
+        #language_name.to_string()
+      }
+      fn get_source_file_suffix(&self) -> String {
+        #file_ext.to_string()
+      }
+      fn execute_pipeline(&mut self, input: &str, options: &EvalOptions) -> FinishedComputation {
+        #pass_chain
+      }
+      fn get_passes(&self) -> Vec<PassDescriptor> {
+        vec![ #(#pass_descriptors),* ]
+      }
+      #get_doc_impl
+      #handle_custom_interpreter_directives_impl
+    }
+  };
+
+  let output: TokenStream = tokens.into();
+  output
+}

schala-repl/Cargo.toml

@@ -4,8 +4,8 @@ version = "0.1.0"
 authors = ["greg <greg.shuflin@protonmail.com>"]
 
 [dependencies]
-llvm-sys = "*"
-take_mut = "0.1.3"
+llvm-sys = "70.0.2"
+take_mut = "0.2.2"
 itertools = "0.5.8"
 getopts = "*"
 lazy_static = "0.2.8"
@@ -14,12 +14,14 @@ colored = "1.5"
 serde = "1.0.15"
 serde_derive = "1.0.15"
 serde_json = "1.0.3"
-rocket = "0.3.5"
-rocket_codegen = "0.3.5"
-rocket_contrib = "0.3.5"
+rocket = "0.4.0"
+rocket_contrib = "0.4.0"
 phf = "0.7.12"
 includedir = "0.2.0"
-rustyline = "1.0.0"
+linefeed = "0.5.0"
+regex = "0.2"
+cursive = "0.10"
+ncurses = "5.98.0"
 
 [build-dependencies]
 includedir_codegen = "0.2.0"

schala-repl/src/language.rs

@@ -1,14 +1,26 @@
 use std::collections::HashMap;
 use colored::*;
 use std::fmt::Write;
-
-pub struct LLVMCodeString(pub String);
+use std::time;
 
 #[derive(Debug, Default, Serialize, Deserialize)]
 pub struct EvalOptions {
-  pub debug: DebugOptions,
-  pub execution_method: ExecutionMethod
+  pub execution_method: ExecutionMethod,
+  pub debug_passes: HashMap<String, PassDebugOptionsDescriptor>,
+  pub debug_timing: bool,
 }
+
+#[derive(Debug, Hash, PartialEq)]
+pub struct PassDescriptor {
+  pub name: String,
+  pub debug_options: Vec<String>
+}
+
+#[derive(Debug, Serialize, Deserialize)]
+pub struct PassDebugOptionsDescriptor {
+  pub opts: Vec<String>,
+}
+
 #[derive(Debug, Serialize, Deserialize)]
 pub enum ExecutionMethod {
   Compile,
@@ -20,87 +32,71 @@ impl Default for ExecutionMethod {
   }
 }
 
-#[derive(Debug, Default, Serialize, Deserialize)]
-pub struct DebugOptions {
-  pub tokens: bool,
-  pub parse_tree: bool,
-  pub ast: bool,
-  pub type_checking: bool,
-  pub symbol_table: bool,
-  pub evaluation: bool,
-  pub llvm_ir: bool,
-}
-
-#[derive(Debug, Default)]
-pub struct LanguageOutput {
-  output: String,
-  artifacts: Vec<TraceArtifact>,
-  pub failed: bool,
-}
-
-impl LanguageOutput {
-  pub fn add_artifact(&mut self, artifact: TraceArtifact) {
-    self.artifacts.push(artifact);
-  }
-  pub fn add_output(&mut self, output: String) {
-    self.output = output;
-  }
-
-  pub fn to_string(&self) -> String {
-    let mut acc = String::new();
-    for line in self.artifacts.iter() {
-      acc.push_str(&line.debug_output.color(line.text_color).to_string());
-      acc.push_str(&"\n");
-    }
-    acc.push_str(&self.output);
-    acc
-  }
-
-  pub fn print_to_screen(&self) {
-    for line in self.artifacts.iter() {
-      let color = line.text_color;
-      let stage = line.stage_name.color(color).to_string();
-      let output = line.debug_output.color(color).to_string();
-      println!("{}: {}", stage, output);
-    }
-    println!("{}", self.output);
-  }
-}
-
 #[derive(Debug, Default)]
 pub struct UnfinishedComputation {
-  artifacts: HashMap<String, TraceArtifact>,
+  artifacts: Vec<(String, TraceArtifact)>,
+  pub durations: Vec<time::Duration>,
+  pub cur_debug_options: Vec<String>,
 }
 
 #[derive(Debug)]
 pub struct FinishedComputation {
-  artifacts: HashMap<String, TraceArtifact>,
+  artifacts: Vec<(String, TraceArtifact)>,
+  durations: Vec<time::Duration>,
   text_output: Result<String, String>,
 }
 
 impl UnfinishedComputation {
   pub fn add_artifact(&mut self, artifact: TraceArtifact) {
-    self.artifacts.insert(artifact.stage_name.clone(), artifact);
+    self.artifacts.push((artifact.stage_name.clone(), artifact));
+  }
+  pub fn finish(self, text_output: Result<String, String>) -> FinishedComputation {
+    FinishedComputation {
+      artifacts: self.artifacts,
+      text_output,
+      durations: self.durations,
+    }
   }
   pub fn output(self, output: Result<String, String>) -> FinishedComputation {
     FinishedComputation {
       artifacts: self.artifacts,
-      text_output: output
+      text_output: output,
+      durations: self.durations,
     }
   }
 }
 
 impl FinishedComputation {
+
+  fn get_timing(&self) -> Option<String> {
+    if self.durations.len() != 0 {
+      let mut buf = String::new();
+      write!(&mut buf, "Timing: ").unwrap();
+      for duration in self.durations.iter() {
+        let timing = (duration.as_secs() as f64) + (duration.subsec_nanos() as f64 * 1e-9);
+        write!(&mut buf, "{}s, ", timing).unwrap()
+      }
+      write!(&mut buf, "\n").unwrap();
+      Some(buf)
+    } else {
+      None
+    }
+  }
+
   pub fn to_repl(&self) -> String {
     let mut buf = String::new();
-    for stage in ["tokens", "parse_trace", "ast", "symbol_table", "type_check"].iter() {
-      if let Some(artifact) = self.artifacts.get(&stage.to_string()) {
-        let color = artifact.text_color;
-        let stage = stage.color(color).bold();
-        let output = artifact.debug_output.color(color);
-        write!(&mut buf, "{}: {}\n", stage, output).unwrap();
-      }
+    for (stage, artifact) in self.artifacts.iter() {
+      let color = artifact.text_color;
+      let stage = stage.color(color).bold();
+      let output = artifact.debug_output.color(color);
+      write!(&mut buf, "{}: {}\n", stage, output).unwrap();
     }
+
+    match self.get_timing() {
+      Some(timing) => write!(&mut buf, "{}", timing).unwrap(),
+      None => ()
+    }
+
     match self.text_output {
       Ok(ref output) => write!(&mut buf, "{}", output).unwrap(),
       Err(ref err) => write!(&mut buf, "{} {}", "Error: ".red().bold(), err).unwrap(),
@@ -111,13 +107,11 @@ impl FinishedComputation {
     match self.text_output {
       Ok(_) => {
         let mut buf = String::new();
-        for stage in ["tokens", "parse_trace", "ast", "symbol_table", "type_check"].iter() {
-          if let Some(artifact) = self.artifacts.get(&stage.to_string()) {
-            let color = artifact.text_color;
-            let stage = stage.color(color).bold();
-            let output = artifact.debug_output.color(color);
-            write!(&mut buf, "{}: {}\n", stage, output).unwrap();
-          }
+        for (stage, artifact) in self.artifacts.iter() {
+          let color = artifact.text_color;
+          let stage = stage.color(color).bold();
+          let output = artifact.debug_output.color(color);
+          write!(&mut buf, "{}: {}\n", stage, output).unwrap();
         }
         if buf == "" { None } else { Some(buf) }
       },
@@ -137,6 +131,7 @@ impl TraceArtifact {
   pub fn new(stage: &str, debug: String) -> TraceArtifact {
     let color = match stage {
       "parse_trace"  | "ast" => "red",
+      "ast_reducing" => "red",
       "tokens" => "green",
       "type_check" => "magenta",
       _ => "blue",
@@ -157,25 +152,22 @@ impl TraceArtifact {
 }
 
 pub trait ProgrammingLanguageInterface {
-  /* old */
-  fn evaluate_in_repl(&mut self, _: &str, _: &EvalOptions) -> LanguageOutput {
-    LanguageOutput { output: format!("Defunct"), artifacts: vec![], failed: false }
-  }
-  /* old */
-
-  fn new_execute(&mut self, input: &str, _options: &EvalOptions) -> FinishedComputation {
-    FinishedComputation { artifacts: HashMap::new(), text_output: Err(format!("NOT DONE")) }
+  fn execute_pipeline(&mut self, _input: &str, _eval_options: &EvalOptions) -> FinishedComputation {
+    FinishedComputation { artifacts: vec![], text_output: Err(format!("Execution pipeline not done")), durations: vec![] }
   }
 
-  fn execute(&mut self, _input: &str, _eval_options: &EvalOptions) -> FinishedComputation {
-    FinishedComputation { artifacts: HashMap::new(), text_output: Err(format!("REPL evaluation not implemented")) }
-  }
   fn get_language_name(&self) -> String;
   fn get_source_file_suffix(&self) -> String;
-  fn handle_custom_interpreter_directives(&mut self, commands: &Vec<&str>) -> Option<String> {
+  fn get_passes(&self) -> Vec<PassDescriptor> {
+    vec![]
+  }
+  fn handle_custom_interpreter_directives(&mut self, _commands: &Vec<&str>) -> Option<String> {
     None
   }
   fn custom_interpreter_directives_help(&self) -> String {
     format!(">> No custom interpreter directives specified <<")
   }
+  fn get_doc(&self, _commands: &Vec<&str>) -> Option<String> {
+    None
+  }
 }

schala-repl/src/lib.rs

@@ -1,15 +1,17 @@
 #![feature(link_args)]
-#![feature(slice_patterns, box_patterns, box_syntax)]
+#![feature(slice_patterns, box_patterns, box_syntax, proc_macro_hygiene, decl_macro)]
 #![feature(plugin)]
-#![plugin(rocket_codegen)]
 extern crate getopts;
-extern crate rustyline;
+extern crate linefeed;
 extern crate itertools;
 extern crate colored;
+extern crate ncurses;
+extern crate cursive;
 
 #[macro_use]
 extern crate serde_derive;
 extern crate serde_json;
+#[macro_use]
 extern crate rocket;
 extern crate rocket_contrib;
 extern crate includedir;
@@ -17,24 +19,22 @@ extern crate phf;
 
 use std::path::Path;
 use std::fs::File;
-use std::io::{Read, Write};
+use std::io::Read;
 use std::process::exit;
 use std::default::Default;
-use std::fmt::Write as FmtWrite;
-
-use rustyline::error::ReadlineError;
-use rustyline::Editor;
-use self::colored::*;
 
+mod new_repl;
+mod repl;
 mod language;
 mod webapp;
-pub mod llvm_wrap;
 
 const VERSION_STRING: &'static str = "0.1.0";
 
 include!(concat!(env!("OUT_DIR"), "/static.rs"));
 
-pub use language::{LLVMCodeString, ProgrammingLanguageInterface, EvalOptions, ExecutionMethod, TraceArtifact, LanguageOutput, FinishedComputation, UnfinishedComputation};
+pub use language::{ProgrammingLanguageInterface, EvalOptions,
+  ExecutionMethod, TraceArtifact, FinishedComputation, UnfinishedComputation, PassDebugOptionsDescriptor, PassDescriptor};
+
 pub type PLIGenerator = Box<Fn() -> Box<ProgrammingLanguageInterface> + Send + Sync>;
 
 pub fn repl_main(generators: Vec<PLIGenerator>) {
@@ -63,12 +63,12 @@ pub fn repl_main(generators: Vec<PLIGenerator>) {
   }
 
   let mut options = EvalOptions::default();
-  if let Some(ref ltrs) = option_matches.opt_str("debug") {
-    options.debug.tokens = ltrs.contains("l");
-    options.debug.ast = ltrs.contains("a");
-    options.debug.parse_tree = ltrs.contains("r");
-    options.debug.symbol_table = ltrs.contains("s");
-  }
+  let debug_passes = if let Some(opts) = option_matches.opt_str("debug") {
+    let output: Vec<String> = opts.split_terminator(",").map(|s| s.to_string()).collect();
+    output
+  } else {
+    vec![]
+  };
 
   let language_names: Vec<String> = languages.iter().map(|lang| {lang.get_language_name()}).collect();
   let initial_index: usize =
@@ -83,17 +83,20 @@ pub fn repl_main(generators: Vec<PLIGenerator>) {
 
   match option_matches.free[..] {
     [] | [_] => {
-      let mut repl = Repl::new(languages, initial_index);
+      /*
+      let mut repl = repl::Repl::new(languages, initial_index);
       repl.run();
+      */
+      new_repl::run();
     }
     [_, ref filename, _..] => {
 
-      run_noninteractive(filename, languages, options);
+      run_noninteractive(filename, languages, options, debug_passes);
     }
   };
 }
 
-fn run_noninteractive(filename: &str, languages: Vec<Box<ProgrammingLanguageInterface>>, options: EvalOptions) {
+fn run_noninteractive(filename: &str, languages: Vec<Box<ProgrammingLanguageInterface>>, mut options: EvalOptions, debug_passes: Vec<String>) {
   let path = Path::new(filename);
   let ext = path.extension().and_then(|e| e.to_str()).unwrap_or_else(|| {
     println!("Source file lacks extension");
@@ -110,6 +113,12 @@ fn run_noninteractive(filename: &str, languages: Vec<Box<ProgrammingLanguageInte
 
   source_file.read_to_string(&mut buffer).unwrap();
 
+  for pass in debug_passes.into_iter() {
+    if let Some(_) = language.get_passes().iter().find(|desc| desc.name == pass) {
+      options.debug_passes.insert(pass, PassDebugOptionsDescriptor { opts: vec![] });
+    }
+  }
+
   match options.execution_method {
     ExecutionMethod::Compile => {
       /*
@@ -119,250 +128,12 @@ fn run_noninteractive(filename: &str, languages: Vec<Box<ProgrammingLanguageInte
       panic!("Not ready to go yet");
     },
     ExecutionMethod::Interpret => {
-      let output = language.execute(&buffer, &options);
+      let output = language.execute_pipeline(&buffer, &options);
       output.to_noninteractive().map(|text| println!("{}", text));
     }
   }
 }
 
-struct Repl {
-  options: EvalOptions,
-  languages: Vec<Box<ProgrammingLanguageInterface>>,
-  current_language_index: usize,
-  interpreter_directive_sigil: char,
-  console: rustyline::Editor<()>,
-}
-
-impl Repl {
-  fn new(languages: Vec<Box<ProgrammingLanguageInterface>>, initial_index: usize) -> Repl {
-    let i = if initial_index < languages.len() { initial_index } else { 0 };
-
-    let console = Editor::<()>::new();
-
-    Repl {
-      options: Repl::get_options(),
-      languages: languages,
-      current_language_index: i,
-      interpreter_directive_sigil: ':',
-      console
-    }
-  }
-
-  fn get_options() -> EvalOptions {
-    File::open(".schala_repl")
-      .and_then(|mut file| {
-        let mut contents = String::new();
-        file.read_to_string(&mut contents)?;
-        Ok(contents)
-      })
-      .and_then(|contents| {
-        let options: EvalOptions = serde_json::from_str(&contents)?;
-        Ok(options)
-      }).unwrap_or(EvalOptions::default())
-  }
-
-  fn save_options(&self) {
-    let ref options = self.options;
-    let read = File::create(".schala_repl")
-      .and_then(|mut file| {
-        let buf = serde_json::to_string(options).unwrap();
-        file.write_all(buf.as_bytes())
-      });
-
-    if let Err(err) = read {
-      println!("Error saving .schala_repl file {}", err);
-    }
-  }
-
-  fn run(&mut self) {
-    println!("Schala MetaInterpreter version {}", VERSION_STRING);
-    println!("Type {}help for help with the REPL", self.interpreter_directive_sigil);
-
-    self.console.get_history().load(".schala_history").unwrap_or(());
-
-    loop {
-      let language_name = self.languages[self.current_language_index].get_language_name();
-      let prompt_str = format!("{} >> ", language_name);
-
-      match self.console.readline(&prompt_str) {
-        Err(ReadlineError::Eof) | Err(ReadlineError::Interrupted) => break,
-        Err(e) => {
-          println!("Terminal read error: {}", e);
-        },
-        Ok(ref input) => {
-          let output = match input.chars().nth(0) {
-            Some(ch) if ch == self.interpreter_directive_sigil => self.handle_interpreter_directive(input),
-            _ => {
-              self.console.get_history().add(input);
-              Some(self.input_handler(input))
-            }
-          };
-          if let Some(o) = output {
-            println!("=> {}", o);
-          }
-        }
-      }
-    }
-    self.console.get_history().save(".schala_history").unwrap_or(());
-    self.save_options();
-    println!("Exiting...");
-  }
-
-  fn input_handler(&mut self, input: &str) -> String {
-    let ref mut language = self.languages[self.current_language_index];
-    let interpreter_output = language.new_execute(input, &self.options);
-    interpreter_output.to_repl()
-  }
-
-  fn handle_interpreter_directive(&mut self, input: &str) -> Option<String> {
-    let mut iter = input.chars();
-    iter.next();
-    let commands: Vec<&str> = iter
-      .as_str()
-      .split_whitespace()
-      .collect();
-
-    let cmd: &str = match commands.get(0).clone() {
-      None => return None,
-      Some(s) => s
-    };
-
-    match cmd {
-      "exit" | "quit"  => {
-        self.save_options();
-        exit(0)
-      },
-      "lang" | "language" => match commands.get(1) {
-        Some(&"show") => {
-          let mut buf = String::new();
-          for (i, lang) in self.languages.iter().enumerate() {
-            write!(buf, "{}{}\n", if i == self.current_language_index { "* "} else { "" }, lang.get_language_name()).unwrap();
-          }
-          Some(buf)
-        },
-        Some(&"go") => match commands.get(2) {
-          None => Some(format!("Must specify a language name")),
-          Some(&desired_name) => {
-            for (i, _) in self.languages.iter().enumerate() {
-              let lang_name = self.languages[i].get_language_name();
-              if lang_name.to_lowercase() == desired_name.to_lowercase() {
-                self.current_language_index = i;
-                return Some(format!("Switching to {}", self.languages[self.current_language_index].get_language_name()));
-              }
-            }
-            Some(format!("Language {} not found", desired_name))
-          }
-        },
-        Some(&"next") | Some(&"n") => {
-          self.current_language_index = (self.current_language_index + 1) % self.languages.len();
-          Some(format!("Switching to {}", self.languages[self.current_language_index].get_language_name()))
-        },
-        Some(&"previous") | Some(&"p") | Some(&"prev") => { 
-          self.current_language_index = if self.current_language_index == 0 { self.languages.len() - 1 } else { self.current_language_index - 1 };
-          Some(format!("Switching to {}", self.languages[self.current_language_index].get_language_name()))
-        },
-        Some(e) => Some(format!("Bad `lang(uage)` argument: {}", e)),
-        None => Some(format!("Valid arguments for `lang(uage)` are `show`, `next`|`n`, `previous`|`prev`|`n`"))
-      },
-      "help" =>  {
-        let mut buf = String::new();
-        let ref lang = self.languages[self.current_language_index];
-
-        writeln!(buf, "MetaInterpreter options").unwrap();
-        writeln!(buf, "-----------------------").unwrap();
-        writeln!(buf, "exit | quit - exit the REPL").unwrap();
-        writeln!(buf, "lang [prev|next|go <name> |show] - toggle to previous or next language, go to a specific language by name, or show all languages").unwrap();
-        writeln!(buf, "Language-specific help for {}", lang.get_language_name()).unwrap();
-        writeln!(buf, "-----------------------").unwrap();
-        writeln!(buf, "{}", lang.custom_interpreter_directives_help()).unwrap();
-        Some(buf)
-      },
-      "set" => {
-        let show = match commands.get(1) {
-          Some(&"show") => true,
-          Some(&"hide") => false,
-          Some(e) => {
-            return Some(format!("Bad `set` argument: {}", e));
-          }
-          None => {
-            return Some(format!("`set` - valid arguments `show {{option}}`, `hide {{option}}`"));
-          }
-        };
-        match commands.get(2) {
-          Some(&"tokens") => self.options.debug.tokens = show,
-          Some(&"parse") => self.options.debug.parse_tree = show,
-          Some(&"ast") => self.options.debug.ast = show,
-          Some(&"symbols") => self.options.debug.symbol_table = show,
-          Some(&"llvm") => self.options.debug.llvm_ir = show,
-          Some(e) => return Some(format!("Bad `show`/`hide` argument: {}", e)),
-          None => return Some(format!("`show`/`hide` requires an argument")),
-        };
-        None
-      },
-      "options" => {
-        let ref d = self.options.debug;
-        let tokens = if d.tokens { "true".green() } else { "false".red() };
-        let parse_tree = if d.parse_tree { "true".green() } else { "false".red() };
-        let ast = if d.ast { "true".green() } else { "false".red() };
-        let symbol_table = if d.symbol_table { "true".green() } else { "false".red() };
-        Some(format!(r#"Debug:
-tokens: {}, parse: {}, ast: {}, symbols: {}"#, tokens, parse_tree, ast, symbol_table))
-      },
-      e => self.languages[self.current_language_index]
-        .handle_custom_interpreter_directives(&commands)
-        .or(Some(format!("Unknown command: {}", e)))
-    }
-  }
-}
-
-/*
-pub fn compilation_sequence(llvm_code: LLVMCodeString, sourcefile: &str) {
-    use std::process::Command;
-
-    let ll_filename = "out.ll";
-    let obj_filename = "out.o";
-    let q: Vec<&str> = sourcefile.split('.').collect();
-    let bin_filename = match &q[..] {
-        &[name, "maaru"] => name,
-        _ => panic!("Bad filename {}", sourcefile),
-    };
-
-    let LLVMCodeString(llvm_str) = llvm_code;
-
-    println!("Compilation process finished for {}", ll_filename);
-    File::create(ll_filename)
-        .and_then(|mut f| f.write_all(llvm_str.as_bytes()))
-        .expect("Error writing file");
-
-    let llc_output = Command::new("llc")
-        .args(&["-filetype=obj", ll_filename, "-o", obj_filename])
-        .output()
-        .expect("Failed to run llc");
-
-
-    if !llc_output.status.success() {
-        println!("{}", String::from_utf8_lossy(&llc_output.stderr));
-    }
-
-    let gcc_output = Command::new("gcc")
-        .args(&["-o", bin_filename, &obj_filename])
-        .output()
-        .expect("failed to run gcc");
-
-    if !gcc_output.status.success() {
-        println!("{}", String::from_utf8_lossy(&gcc_output.stdout));
-        println!("{}", String::from_utf8_lossy(&gcc_output.stderr));
-    }
-
-    for filename in [obj_filename].iter() {
-        Command::new("rm")
-            .arg(filename)
-            .output()
-            .expect(&format!("failed to run rm {}", filename));
-    }
-}
-*/
-
 fn program_options() -> getopts::Options {
   let mut options = getopts::Options::new();
   options.optopt("s",

schala-repl/src/llvm_wrap.rs

@@ -1,279 +0,0 @@
-#![allow(non_snake_case)]
-#![allow(dead_code)]
-extern crate llvm_sys;
-
-use self::llvm_sys::{LLVMIntPredicate, LLVMRealPredicate};
-use self::llvm_sys::prelude::*;
-use self::llvm_sys::core;
-use std::ptr;
-use std::ffi::{CString, CStr};
-use std::os::raw::c_char;
-
-pub fn create_context() -> LLVMContextRef {
-    unsafe { core::LLVMContextCreate() }
-}
-pub fn module_create_with_name(name: &str) -> LLVMModuleRef {
-    unsafe {
-        let n = name.as_ptr() as *const _;
-        core::LLVMModuleCreateWithName(n)
-    }
-}
-pub fn CreateBuilderInContext(context: LLVMContextRef) -> LLVMBuilderRef {
-    unsafe { core::LLVMCreateBuilderInContext(context) }
-}
-
-pub fn AppendBasicBlockInContext(context: LLVMContextRef,
-                                 function: LLVMValueRef,
-                                 name: &str)
-                                 -> LLVMBasicBlockRef {
-    let c_name = CString::new(name).unwrap();
-    unsafe { core::LLVMAppendBasicBlockInContext(context, function, c_name.as_ptr()) }
-}
-
-pub fn AddFunction(module: LLVMModuleRef, name: &str, function_type: LLVMTypeRef) -> LLVMValueRef {
-    let c_name = CString::new(name).unwrap();
-    unsafe { core::LLVMAddFunction(module, c_name.as_ptr(), function_type) }
-}
-
-pub fn FunctionType(return_type: LLVMTypeRef,
-                    mut param_types: Vec<LLVMTypeRef>,
-                    is_var_rag: bool)
-                    -> LLVMTypeRef {
-    let len = param_types.len();
-    unsafe {
-        let pointer = param_types.as_mut_ptr();
-        core::LLVMFunctionType(return_type,
-                               pointer,
-                               len as u32,
-                               if is_var_rag { 1 } else { 0 })
-    }
-}
-
-pub fn GetNamedFunction(module: LLVMModuleRef,
-                        name: &str) -> Option<LLVMValueRef> {
-
-    let c_name = CString::new(name).unwrap();
-    let ret = unsafe { core::LLVMGetNamedFunction(module, c_name.as_ptr()) };
-
-    if ret.is_null() {
-        None
-    } else {
-        Some(ret)
-    }
-}
-
-pub fn VoidTypeInContext(context: LLVMContextRef) -> LLVMTypeRef {
-    unsafe { core::LLVMVoidTypeInContext(context) }
-}
-
-pub fn DisposeBuilder(builder: LLVMBuilderRef) {
-    unsafe { core::LLVMDisposeBuilder(builder) }
-}
-
-pub fn DisposeModule(module: LLVMModuleRef) {
-    unsafe { core::LLVMDisposeModule(module) }
-}
-
-pub fn ContextDispose(context: LLVMContextRef) {
-    unsafe { core::LLVMContextDispose(context) }
-}
-
-pub fn PositionBuilderAtEnd(builder: LLVMBuilderRef, basic_block: LLVMBasicBlockRef) {
-    unsafe { core::LLVMPositionBuilderAtEnd(builder, basic_block) }
-}
-
-pub fn BuildRet(builder: LLVMBuilderRef, val: LLVMValueRef) -> LLVMValueRef {
-    unsafe { core::LLVMBuildRet(builder, val) }
-}
-
-pub fn BuildRetVoid(builder: LLVMBuilderRef) -> LLVMValueRef {
-    unsafe { core::LLVMBuildRetVoid(builder) }
-}
-
-pub fn DumpModule(module: LLVMModuleRef) {
-    unsafe { core::LLVMDumpModule(module) }
-}
-
-pub fn Int64TypeInContext(context: LLVMContextRef) -> LLVMTypeRef {
-    unsafe { core::LLVMInt64TypeInContext(context) }
-}
-
-pub fn ConstInt(int_type: LLVMTypeRef, n: u64, sign_extend: bool) -> LLVMValueRef {
-    unsafe { core::LLVMConstInt(int_type, n, if sign_extend { 1 } else { 0 }) }
-}
-
-pub fn BuildAdd(builder: LLVMBuilderRef,
-                lhs: LLVMValueRef,
-                rhs: LLVMValueRef,
-                reg_name: &str)
-                -> LLVMValueRef {
-    let name = CString::new(reg_name).unwrap();
-    unsafe { core::LLVMBuildAdd(builder, lhs, rhs, name.as_ptr()) }
-}
-
-pub fn BuildSub(builder: LLVMBuilderRef,
-                lhs: LLVMValueRef,
-                rhs: LLVMValueRef,
-                reg_name: &str)
-                -> LLVMValueRef {
-    let name = CString::new(reg_name).unwrap();
-    unsafe { core::LLVMBuildSub(builder, lhs, rhs, name.as_ptr()) }
-}
-
-pub fn BuildMul(builder: LLVMBuilderRef,
-                lhs: LLVMValueRef,
-                rhs: LLVMValueRef,
-                reg_name: &str)
-                -> LLVMValueRef {
-    let name = CString::new(reg_name).unwrap();
-    unsafe { core::LLVMBuildMul(builder, lhs, rhs, name.as_ptr()) }
-}
-
-pub fn BuildUDiv(builder: LLVMBuilderRef,
-                 lhs: LLVMValueRef,
-                 rhs: LLVMValueRef,
-                 reg_name: &str)
-                 -> LLVMValueRef {
-    let name = CString::new(reg_name).unwrap();
-    unsafe { core::LLVMBuildUDiv(builder, lhs, rhs, name.as_ptr()) }
-}
-
-pub fn BuildSRem(builder: LLVMBuilderRef,
-                 lhs: LLVMValueRef,
-                 rhs: LLVMValueRef,
-                 reg_name: &str)
-                 -> LLVMValueRef {
-    let name = CString::new(reg_name).unwrap();
-    unsafe { core::LLVMBuildSRem(builder, lhs, rhs, name.as_ptr()) }
-}
-
-pub fn BuildCondBr(builder: LLVMBuilderRef,
-                   if_expr: LLVMValueRef,
-                   then_expr: LLVMBasicBlockRef,
-                   else_expr: LLVMBasicBlockRef) -> LLVMValueRef {
-
-
-    unsafe { core::LLVMBuildCondBr(builder, if_expr, then_expr, else_expr) }
-}
-
-pub fn BuildBr(builder: LLVMBuilderRef,
-               dest: LLVMBasicBlockRef) -> LLVMValueRef {
-    unsafe { core::LLVMBuildBr(builder, dest) }
-}
-
-pub fn GetInsertBlock(builder: LLVMBuilderRef) -> LLVMBasicBlockRef {
-    unsafe { core::LLVMGetInsertBlock(builder) }
-}
-
-pub fn BuildPhi(builder: LLVMBuilderRef, ty: LLVMTypeRef, name: &str) -> LLVMValueRef {
-    let name = CString::new(name).unwrap();
-    unsafe { core::LLVMBuildPhi(builder, ty, name.as_ptr()) }
-}
-
-pub fn SetValueName(value: LLVMValueRef, name: &str) {
-    let name = CString::new(name).unwrap();
-    unsafe {
-        core::LLVMSetValueName(value, name.as_ptr())
-    }
-}
-
-pub fn GetValueName(value: LLVMValueRef) -> String {
-    unsafe { 
-        let name_ptr: *const c_char = core::LLVMGetValueName(value);
-        CStr::from_ptr(name_ptr).to_string_lossy().into_owned()
-    }
-}
-
-pub fn GetParams(function: LLVMValueRef) -> Vec<LLVMValueRef> {
-    let size = CountParams(function);
-    unsafe {
-        let mut container = Vec::with_capacity(size);
-        container.set_len(size);
-        core::LLVMGetParams(function, container.as_mut_ptr());
-        container
-    }
-}
-
-pub fn CountParams(function: LLVMValueRef) -> usize {
-    unsafe { core::LLVMCountParams(function) as usize }
-}
-
-pub fn BuildFCmp(builder: LLVMBuilderRef,
-                 op: LLVMRealPredicate,
-                 lhs: LLVMValueRef,
-                 rhs: LLVMValueRef,
-                 name: &str) -> LLVMValueRef {
-    let name = CString::new(name).unwrap();
-    unsafe { core::LLVMBuildFCmp(builder, op, lhs, rhs, name.as_ptr()) }
-}
-
-pub fn BuildZExt(builder: LLVMBuilderRef,
-                       val: LLVMValueRef,
-                       dest_type: LLVMTypeRef,
-                       name: &str) -> LLVMValueRef {
-    let name = CString::new(name).unwrap();
-    unsafe { core::LLVMBuildZExt(builder, val, dest_type, name.as_ptr()) }
-}
-
-pub fn BuildUIToFP(builder: LLVMBuilderRef,
-                       val: LLVMValueRef,
-                       dest_type: LLVMTypeRef,
-                       name: &str) -> LLVMValueRef {
-
-    let name = CString::new(name).unwrap();
-    unsafe { core::LLVMBuildUIToFP(builder, val, dest_type, name.as_ptr()) }
-}
-
-pub fn BuildICmp(builder: LLVMBuilderRef,
-                 op: LLVMIntPredicate,
-                 lhs: LLVMValueRef,
-                 rhs: LLVMValueRef,
-                 name: &str) -> LLVMValueRef {
-    let name = CString::new(name).unwrap();
-    unsafe { core::LLVMBuildICmp(builder, op, lhs, rhs, name.as_ptr()) }
-}
-
-pub fn GetBasicBlockParent(block: LLVMBasicBlockRef) -> LLVMValueRef {
-    unsafe { core::LLVMGetBasicBlockParent(block) }
-}
-
-pub fn GetBasicBlocks(function: LLVMValueRef) -> Vec<LLVMBasicBlockRef> {
-    let size = CountBasicBlocks(function);
-    unsafe { 
-        let mut container = Vec::with_capacity(size);
-        container.set_len(size);
-        core::LLVMGetBasicBlocks(function, container.as_mut_ptr());
-        container
-    }
-}
-
-pub fn CountBasicBlocks(function: LLVMValueRef) -> usize {
-    unsafe { core::LLVMCountBasicBlocks(function) as usize }
-}
-
-pub fn PrintModuleToString(module: LLVMModuleRef) -> String {
-    unsafe {
-        let str_ptr: *const c_char = core::LLVMPrintModuleToString(module);
-        CStr::from_ptr(str_ptr).to_string_lossy().into_owned()
-    }
-}
-
-pub fn AddIncoming(phi_node: LLVMValueRef, mut incoming_values: Vec<LLVMValueRef>,
-                   mut incoming_blocks: Vec<LLVMBasicBlockRef>) {
-
-    let count = incoming_blocks.len() as u32;
-    if incoming_values.len() as u32 != count {
-        panic!("Bad invocation of AddIncoming");
-    }
-
-    unsafe {
-        let vals = incoming_values.as_mut_ptr();
-        let blocks = incoming_blocks.as_mut_ptr();
-        core::LLVMAddIncoming(phi_node, vals, blocks, count)
-    }
-}
-
-pub fn PrintModuleToFile(module: LLVMModuleRef, filename: &str) -> LLVMBool {
-    let out_file = CString::new(filename).unwrap();
-    unsafe { core::LLVMPrintModuleToFile(module, out_file.as_ptr(), ptr::null_mut()) }
-}

schala-repl/src/new_repl.rs

@@ -0,0 +1,11 @@
+use cursive::Cursive;
+use cursive::views::{Dialog, TextView};
+
+pub fn run() {
+  println!("YOLO");
+  let mut siv = Cursive::default();
+  siv.add_layer(Dialog::around(TextView::new("FUCKO"))
+                .title("YOLO SWAGGGGG")
+                .button("exit", |s| { s.quit() }));
+  siv.run();
+}

schala-repl/src/repl/command_tree.rs

@@ -0,0 +1,53 @@
+
+#[derive(Clone)]
+pub enum CommandTree {
+  Terminal {
+    name: String,
+    help_msg: Option<String>,
+    function: Option<Box<(fn() -> Option<String>)>>,
+  },
+  NonTerminal {
+    name: String,
+    children: Vec<CommandTree>,
+    help_msg: Option<String>,
+    function: Option<Box<(fn() -> Option<String>)>>,
+  },
+  Top(Vec<CommandTree>),
+}
+
+impl CommandTree {
+  pub fn term(s: &str, help: Option<&str>) -> CommandTree {
+    CommandTree::Terminal {name: s.to_string(), help_msg: help.map(|x| x.to_string()), function: None }
+  }
+
+  pub fn nonterm(s: &str, help: Option<&str>, children: Vec<CommandTree>) -> CommandTree {
+    CommandTree::NonTerminal {
+      name: s.to_string(),
+      help_msg: help.map(|x| x.to_string()),
+      children,
+      function: None,
+    }
+  }
+
+  pub fn get_cmd(&self) -> &str {
+    match self {
+      CommandTree::Terminal { name, .. } => name.as_str(),
+      CommandTree::NonTerminal {name, ..} => name.as_str(),
+      CommandTree::Top(_) => "",
+    }
+  }
+  pub fn get_help(&self) -> &str {
+    match self {
+      CommandTree::Terminal { help_msg, ..} => help_msg.as_ref().map(|s| s.as_str()).unwrap_or(""),
+      CommandTree::NonTerminal { help_msg, .. } => help_msg.as_ref().map(|s| s.as_str()).unwrap_or(""),
+      CommandTree::Top(_) => ""
+    }
+  }
+  pub fn get_children(&self) -> Vec<&str> {
+    match self {
+      CommandTree::Terminal { .. } => vec![],
+      CommandTree::NonTerminal { children, .. } => children.iter().map(|x| x.get_cmd()).collect(),
+      CommandTree::Top(children) => children.iter().map(|x| x.get_cmd()).collect(),
+    }
+  }
+}

schala-repl/src/repl/mod.rs

@@ -0,0 +1,355 @@
+use std::fmt::Write as FmtWrite;
+use std::io::{Read, Write};
+use std::fs::File;
+use std::sync::Arc;
+
+use colored::*;
+use itertools::Itertools;
+use language::{ProgrammingLanguageInterface, EvalOptions,
+  PassDebugOptionsDescriptor};
+mod command_tree;
+use self::command_tree::CommandTree;
+
+const HISTORY_SAVE_FILE: &'static str = ".schala_history";
+const OPTIONS_SAVE_FILE: &'static str = ".schala_repl";
+
+pub struct Repl {
+  options: EvalOptions,
+  languages: Vec<Box<ProgrammingLanguageInterface>>,
+  current_language_index: usize,
+  interpreter_directive_sigil: char,
+  line_reader: ::linefeed::interface::Interface<::linefeed::terminal::DefaultTerminal>,
+}
+
+impl Repl {
+  pub fn new(languages: Vec<Box<ProgrammingLanguageInterface>>, initial_index: usize) -> Repl {
+    use linefeed::Interface;
+    let current_language_index = if initial_index < languages.len() { initial_index } else { 0 };
+
+    let line_reader = Interface::new("schala-repl").unwrap();
+
+    Repl {
+      options: Repl::get_options(),
+      languages,
+      current_language_index,
+      interpreter_directive_sigil: ':',
+      line_reader
+    }
+  }
+
+  fn get_cur_language(&self) -> &ProgrammingLanguageInterface {
+    self.languages[self.current_language_index].as_ref()
+  }
+
+  fn get_options() -> EvalOptions {
+    File::open(OPTIONS_SAVE_FILE)
+      .and_then(|mut file| {
+        let mut contents = String::new();
+        file.read_to_string(&mut contents)?;
+        Ok(contents)
+      })
+      .and_then(|contents| {
+        let options: EvalOptions = ::serde_json::from_str(&contents)?;
+        Ok(options)
+      }).unwrap_or(EvalOptions::default())
+  }
+
+  fn save_options(&self) {
+    let ref options = self.options;
+    let read = File::create(OPTIONS_SAVE_FILE)
+      .and_then(|mut file| {
+        let buf = ::serde_json::to_string(options).unwrap();
+        file.write_all(buf.as_bytes())
+      });
+
+    if let Err(err) = read {
+      println!("Error saving {} file {}", OPTIONS_SAVE_FILE, err);
+    }
+  }
+
+  pub fn run(&mut self) {
+    use linefeed::ReadResult;
+
+    println!("Schala MetaInterpreter version {}", ::VERSION_STRING);
+    println!("Type {}help for help with the REPL", self.interpreter_directive_sigil);
+
+    self.line_reader.load_history(HISTORY_SAVE_FILE).unwrap_or(());
+
+    loop {
+      let language_name = self.get_cur_language().get_language_name();
+      let directives = self.get_directives();
+      let tab_complete_handler = TabCompleteHandler::new(self.interpreter_directive_sigil, directives);
+      self.line_reader.set_completer(Arc::new(tab_complete_handler));
+
+      let prompt_str = format!("{} >> ", language_name);
+      self.line_reader.set_prompt(&prompt_str).unwrap();
+
+      match self.line_reader.read_line() {
+        Err(e) => {
+          println!("Terminal read error: {}", e);
+        },
+        Ok(ReadResult::Eof) => break,
+        Ok(ReadResult::Signal(_)) => break,
+        Ok(ReadResult::Input(ref input)) => {
+          self.line_reader.add_history_unique(input.to_string());
+          let output = match input.chars().nth(0) {
+            Some(ch) if ch == self.interpreter_directive_sigil => self.handle_interpreter_directive(input),
+            _ => Some(self.input_handler(input)),
+          };
+          if let Some(o) = output {
+            println!("=> {}", o);
+          }
+        }
+      }
+    }
+    self.line_reader.save_history(HISTORY_SAVE_FILE).unwrap_or(());
+    self.save_options();
+    println!("Exiting...");
+  }
+
+  fn input_handler(&mut self, input: &str) -> String {
+    let ref mut language = self.languages[self.current_language_index];
+    let interpreter_output = language.execute_pipeline(input, &self.options);
+    interpreter_output.to_repl()
+  }
+
+  fn get_directives(&self) -> CommandTree {
+    let ref passes = self.get_cur_language().get_passes();
+
+    let passes_directives: Vec<CommandTree> = passes.iter()
+      .map(|pass_descriptor| {
+        let name = &pass_descriptor.name;
+        if pass_descriptor.debug_options.len() == 0 {
+          CommandTree::term(name, None)
+        } else {
+          let children: Vec<CommandTree> = pass_descriptor.debug_options.iter()
+            .map(|o| CommandTree::term(o, None)).collect();
+          CommandTree::NonTerminal {
+            name: name.clone(),
+            children,
+            help_msg: None,
+            function: None,
+          }
+        }
+      }).collect();
+
+    CommandTree::Top(vec![
+      CommandTree::term("exit", Some("exit the REPL")),
+      CommandTree::term("quit", Some("exit the REPL")),
+      CommandTree::term("help", Some("Print this help message")),
+      CommandTree::nonterm("debug",
+        Some("show or hide pass debug info for a given pass, or display the names of all passes, or turn timing on/off"),
+        vec![
+          CommandTree::term("passes", None),
+          CommandTree::nonterm("show", None, passes_directives.clone()),
+          CommandTree::nonterm("hide", None, passes_directives.clone()),
+          CommandTree::nonterm("timing", None, vec![
+            CommandTree::term("on", None),
+            CommandTree::term("off", None),
+          ])
+        ]
+      ),
+      CommandTree::nonterm("lang",
+        Some("switch between languages, or go directly to a langauge by name"),
+        vec![
+          CommandTree::term("next", None),
+          CommandTree::term("prev", None),
+          CommandTree::nonterm("go", None, vec![]),
+        ]
+      ),
+      CommandTree::term("doc", Some("Get language-specific help for an item")),
+    ])
+  }
+
+  fn handle_interpreter_directive(&mut self, input: &str) -> Option<String> {
+    let mut iter = input.chars();
+    iter.next();
+    let commands: Vec<&str> = iter
+      .as_str()
+      .split_whitespace()
+      .collect();
+
+    let initial_cmd: &str = match commands.get(0).clone() {
+      None => return None,
+      Some(s) => s
+    };
+
+    match initial_cmd {
+      "exit" | "quit"  => {
+        self.save_options();
+        ::std::process::exit(0)
+      },
+      "lang" | "language" => match commands.get(1) {
+        Some(&"show") => {
+          let mut buf = String::new();
+          for (i, lang) in self.languages.iter().enumerate() {
+            write!(buf, "{}{}\n", if i == self.current_language_index { "* "} else { "" }, lang.get_language_name()).unwrap();
+          }
+          Some(buf)
+        },
+        Some(&"go") => match commands.get(2) {
+          None => Some(format!("Must specify a language name")),
+          Some(&desired_name) => {
+            for (i, _) in self.languages.iter().enumerate() {
+              let lang_name = self.languages[i].get_language_name();
+              if lang_name.to_lowercase() == desired_name.to_lowercase() {
+                self.current_language_index = i;
+                return Some(format!("Switching to {}", self.languages[self.current_language_index].get_language_name()));
+              }
+            }
+            Some(format!("Language {} not found", desired_name))
+          }
+        },
+        Some(&"next") | Some(&"n") => {
+          self.current_language_index = (self.current_language_index + 1) % self.languages.len();
+          Some(format!("Switching to {}", self.languages[self.current_language_index].get_language_name()))
+        },
+        Some(&"previous") | Some(&"p") | Some(&"prev") => { 
+          self.current_language_index = if self.current_language_index == 0 { self.languages.len() - 1 } else { self.current_language_index - 1 };
+          Some(format!("Switching to {}", self.languages[self.current_language_index].get_language_name()))
+        },
+        Some(e) => Some(format!("Bad `lang(uage)` argument: {}", e)),
+        None => Some(format!("Valid arguments for `lang(uage)` are `show`, `next`|`n`, `previous`|`prev`|`n`"))
+      },
+      "help" =>  {
+        let mut buf = String::new();
+        let ref lang = self.languages[self.current_language_index];
+        let directives = match self.get_directives() {
+            CommandTree::Top(children) => children,
+            _ => panic!("Top-level CommandTree not Top")
+        };
+
+        writeln!(buf, "MetaInterpreter options").unwrap();
+        writeln!(buf, "-----------------------").unwrap();
+
+        for directive in directives {
+          let trailer = " ";
+          writeln!(buf, "{}{}- {}", directive.get_cmd(), trailer, directive.get_help()).unwrap();
+        }
+
+        writeln!(buf, "").unwrap();
+        writeln!(buf, "Language-specific help for {}", lang.get_language_name()).unwrap();
+        writeln!(buf, "-----------------------").unwrap();
+        writeln!(buf, "{}", lang.custom_interpreter_directives_help()).unwrap();
+        Some(buf)
+      },
+      "debug" => self.handle_debug(commands),
+      "doc" => self.languages[self.current_language_index]
+        .get_doc(&commands)
+        .or(Some(format!("No docs implemented"))),
+      e => {
+        self.languages[self.current_language_index]
+        .handle_custom_interpreter_directives(&commands)
+        .or(Some(format!("Unknown command: {}", e)))
+      }
+    }
+  }
+  fn handle_debug(&mut self, commands: Vec<&str>) -> Option<String> {
+    let passes = self.get_cur_language().get_passes();
+    match commands.get(1) {
+      Some(&"timing") => match commands.get(2) {
+        Some(&"on") => { self.options.debug_timing = true; None }
+        Some(&"off") => { self.options.debug_timing = false; None }
+        _ => return Some(format!(r#"Argument to "timing" must be "on" or "off""#)),
+      },
+      Some(&"passes") => Some(
+        passes.into_iter()
+        .map(|desc| {
+          if self.options.debug_passes.contains_key(&desc.name) {
+            let color = "green";
+            format!("*{}", desc.name.color(color))
+          } else {
+            desc.name
+          }
+        })
+        .intersperse(format!(" -> "))
+        .collect()),
+      b @ Some(&"show") | b @ Some(&"hide") => {
+        let show = b == Some(&"show");
+        let debug_pass: String = match commands.get(2) {
+          Some(s) => s.to_string(),
+          None => return Some(format!("Must specify a stage to debug")),
+        };
+        let pass_opt = commands.get(3);
+        if let Some(desc) = passes.iter().find(|desc| desc.name == debug_pass) {
+          let mut opts = vec![];
+          if let Some(opt) = pass_opt {
+            opts.push(opt.to_string());
+          }
+          let msg = format!("{} debug for pass {}", if show { "Enabling" } else { "Disabling" }, debug_pass);
+          if show {
+            self.options.debug_passes.insert(desc.name.clone(), PassDebugOptionsDescriptor { opts });
+          } else {
+            self.options.debug_passes.remove(&desc.name);
+          }
+          Some(msg)
+        } else {
+          Some(format!("Couldn't find stage: {}", debug_pass))
+        }
+      },
+      _ => Some(format!("Unknown debug command"))
+    }
+  }
+}
+
+struct TabCompleteHandler {
+  sigil: char,
+  top_level_commands: CommandTree,
+}
+
+use linefeed::complete::{Completion, Completer};
+use linefeed::terminal::Terminal;
+
+impl TabCompleteHandler {
+  fn new(sigil: char, top_level_commands: CommandTree) -> TabCompleteHandler {
+    TabCompleteHandler {
+      top_level_commands,
+      sigil,
+    }
+  }
+}
+
+impl<T: Terminal> Completer<T> for TabCompleteHandler {
+  fn complete(&self, word: &str, prompter: &::linefeed::prompter::Prompter<T>, start: usize, _end: usize) -> Option<Vec<Completion>> {
+    let line = prompter.buffer();
+
+    if line.starts_with(&format!("{}", self.sigil)) {
+      let mut words = line[1..(if start == 0 { 1 } else { start })].split_whitespace();
+      let mut completions = Vec::new();
+      let mut command_tree: Option<&CommandTree> = Some(&self.top_level_commands);
+
+      loop {
+        match words.next() {
+          None => {
+            let top = match command_tree {
+              Some(CommandTree::Top(_)) => true,
+              _ => false
+            };
+            let word = if top { word.get(1..).unwrap() } else { word };
+            for cmd in command_tree.map(|x| x.get_children()).unwrap_or(vec![]).into_iter() {
+              if cmd.starts_with(word) {
+                completions.push(Completion {
+                    completion: format!("{}{}", if top { ":" } else { "" }, cmd),
+                    display: Some(cmd.to_string()),
+                    suffix: ::linefeed::complete::Suffix::Some(' ')
+                })
+              }
+            }
+            break;
+          },
+          Some(s) => {
+            let new_ptr: Option<&CommandTree> = command_tree.and_then(|cm| match cm {
+              CommandTree::Top(children) => children.iter().find(|c| c.get_cmd() == s),
+              CommandTree::NonTerminal { children, .. } => children.iter().find(|c| c.get_cmd() == s),
+              CommandTree::Terminal { .. } => None,
+            });
+            command_tree = new_ptr;
+          }
+        }
+      }
+      Some(completions)
+    } else {
+      None
+    }
+  }
+}

schala-repl/src/webapp.rs

@@ -2,7 +2,7 @@ use rocket;
 use rocket::State;
 use rocket::response::Content;
 use rocket::http::ContentType;
-use rocket_contrib::Json;
+use rocket_contrib::json::Json;
 use language::{ProgrammingLanguageInterface, EvalOptions};
 use WEBFILES;
 use ::PLIGenerator;
@@ -35,8 +35,8 @@ struct Output {
 fn interpreter_input(input: Json<Input>, generators: State<Vec<PLIGenerator>>) -> Json<Output> {
   let schala_gen = generators.get(0).unwrap();
   let mut schala: Box<ProgrammingLanguageInterface> = schala_gen();
-  let code_output = schala.evaluate_in_repl(&input.source, &EvalOptions::default());
-  Json(Output { text: code_output.to_string() })
+  let code_output = schala.execute_pipeline(&input.source, &EvalOptions::default());
+  Json(Output { text: code_output.to_repl() })
 }
 
 pub fn web_main(language_generators: Vec<PLIGenerator>) {

source_files/schala/does_scope_work.schala

@@ -0,0 +1,11 @@
+let c = 10
+
+fn add(a, b) {
+  let c = a + b
+  c
+}
+
+let mut b = 20
+
+println(add(1,2))
+println(c + b)

source_files/schala/first.schala

@@ -1,12 +0,0 @@
-fn main() {
-  const a = 10
-  const b = 20
-  a + b
-}
-
-//foo
-
-print(main())
-
-
-

source_files/schala/first_program.schala

@@ -0,0 +1,17 @@
+fn main() {
+  let a = 10
+  let b = 20
+  a + b
+}
+
+//this is a one-line comment
+
+/* this is
+a multiline
+comment
+*/
+
+print(main())
+
+
+

source_files/schala/fizzbuzz.schala

@@ -0,0 +1,12 @@
+
+for n <- 1..=100 {
+  if n % 15 == 0 {
+    print("FizzBuzz")
+  } else if n % 5 == 0 {
+    print("Buzz")
+  } else if n % 3 == 0 {
+    print("Fizz")
+  } else {
+    print(n.to_string())
+  }
+}

source_files/schala/syntax_playground.schala

@@ -0,0 +1,114 @@
+
+fn main() {
+
+//comments are C-style
+/* nested comments /* are cool */ */
+
+}
+
+@annotations are with @-
+
+// variable expressions
+  var a: I32 = 20
+  const b: String = 20
+
+  there(); can(); be(); multiple(); statements(); per_line();
+
+  //string interpolation
+  const yolo = "I have ${a + b} people in my house"
+
+  // let expressions ??? not sure if I want this
+  let a = 10, b = 20, c = 30 in a + b + c
+
+  //list literal
+  const q = [1,2,3,4]
+
+  //lambda literal 
+  q.map({|item| item * 100 })
+
+  fn yolo(a: MyType, b: YourType): ReturnType<Param1, Param2> {
+    if a == 20 {
+      return "early"
+    }
+    var sex = 20
+    sex
+  }
+
+
+/* for/while loop topics */
+
+   //infinite loop
+   while {
+     if x() { break }
+     ...
+   }
+
+
+   //conditional loop
+   while conditionHolds() {
+      ...
+   }
+
+
+  //iteration over a variable
+  for i <- [1..1000]  {
+
+  } //return type is return type of block
+
+
+  //monadic decomposition
+  for {
+    a <- maybeInt();
+    s <- foo() 
+  } return {
+    a + s
+  } //return type is Monad<return type of block>
+
+/* end of for loops */
+
+
+
+/* conditionals/pattern matching */
+
+// "is" operator for "does this pattern match"
+
+x is Some(t) // type bool
+
+if x {
+  is Some(t) => {
+  },
+  is None => {
+
+  }
+}
+
+
+ //syntax is, I guess, for <expr> <brace-block>, where <expr> is a bool, or a <arrow-expr>
+
+ // type level alises
+ typealias <name> = <other type> #maybe thsi should be 'alias'?
+
+/*
+what if type A = B meant that you could had to create A's with A(B), but when you used A's the interface was exactly like B's?
+ maybe introduce a 'newtype' keyword for this
+ */
+
+ //declaring types of all stripes
+ type MyData = { a: i32, b: String }
+ type MyType = MyType
+ type Option<a> = None | Some(a)
+ type Signal = Absence | SimplePresence(i32) | ComplexPresence {a: i32, b: MyCustomData}
+
+ //traits
+ 
+ trait Bashable { }
+ trait Luggable {
+  fn lug(self, a: Option<Self>)
+ }
+
+}
+
+
+// lambdas
+// ruby-style not rust-style
+const a: X -> Y -> Z = {|x,y|  }

source_files/schala/test.schala

@@ -1,105 +1,17 @@
 
-fn main() {
-
-//comments are C-style
-/* nested comments /* are cool */ */
+println(sua(4))
 
+fn sua(x): Int {
+  x + 10
 }
 
-@annotations are with @-
 
-// variable expressions
-  var a: I32 = 20
-  const b: String = 20
-
-  there(); can(); be(); multiple(); statements(); per_line();
-
-  //string interpolation
-  const yolo = "I have ${a + b} people in my house"
-
-  // let expressions ??? not sure if I want this
-  let a = 10, b = 20, c = 30 in a + b + c
-
-  //list literal
-  const q = [1,2,3,4]
-
-  //lambda literal 
-  q.map({|item| item * 100 })
-
-  fn yolo(a: MyType, b: YourType): ReturnType<Param1, Param2> {
-    if a == 20 {
-      return "early"
-    }
-    var sex = 20
-    sex
-  }
-
-
-  for {
-  //infinite loop
-  }
-
-  //iteration over a variable
-  for i <- [1..1000]  {
-
-  } //return type is return type of block
-
-  //while loop
-  for a != 3 || fuckTard() {
-    break
-  } //return type is return type of block
-
-  //monadic decomposition
-  for {
-    a <- maybeInt();
-    s <- foo() 
-  } return {
-    a + s
-  } //return type is Monad<return type of block>
-
-  // let statements too!!
-  for (a = 20
-  b = fuck) {
-    a + b
-  }
-
-
-  // pattern-matching
-  match <expr> {
-    Some(a) => {
-
-    },
-    None => {
-
-    },
-  }
-
- //syntax is, I guess, for <expr> <brace-block>, where <expr> is a bool, or a <arrow-expr>
-
- // type level alises
- typealias <name> = <other type> #maybe thsi should be 'alias'?
+//let a = getline()
 
 /*
-what if type A = B meant that you could had to create A's with A(B), but when you used A's the interface was exactly like B's?
- maybe introduce a 'newtype' keyword for this
- */
-
- //declaring types of all stripes
- type MyData = { a: i32, b: String }
- type MyType = MyType
- type Option<a> = None | Some(a)
- type Signal = Absence | SimplePresence(i32) | ComplexPresence {a: i32, b: MyCustomData}
-
- //traits
- 
- trait Bashable { }
- trait Luggable {
-  fn lug(self, a: Option<Self>)
- }
-
+if a == "true" {
+  println("You typed true")
+} else {
+  println("You typed something else")
 }
-
-
-// lambdas
-// ruby-style not rust-style
-const a: X -> Y -> Z = {|x,y|  }
+*/