Compare commits

..

18 Commits

Author SHA1 Message Date
Greg Shuflin
57a0d0a603 Add parser module 2024-04-23 18:03:27 -07:00
Greg Shuflin
b44fda3283 Fix markdown 2024-04-23 02:47:16 -07:00
Greg Shuflin
1be26eb453 Fix readme for real 2024-04-23 02:46:43 -07:00
Greg Shuflin
7067edc86f Fix readme 2024-04-23 02:46:26 -07:00
Greg Shuflin
dc771fc7ad Working simple tree-sitter grammar 2024-04-23 02:37:01 -07:00
Greg Shuflin
45c4d08fb9 Add justfile 2024-04-23 02:15:26 -07:00
Greg Shuflin
77257d0eb7 Messing with treesitter grammar
doesn't work yet
2024-04-23 02:13:44 -07:00
Greg Shuflin
f33195ab28 Trying out a thing 2024-04-21 03:08:05 -07:00
Greg Shuflin
8cde20641b working on new grammar 2024-04-21 03:01:13 -07:00
Greg Shuflin
ba4ccfe6bf More tree-sitter testing stuff 2024-04-21 02:34:39 -07:00
Greg Shuflin
7bc92aef97 treesitter test 2024-04-21 02:26:53 -07:00
Greg Shuflin
95e22567e7 Add experiments crate 2024-04-20 01:39:11 -07:00
Greg Shuflin
dc09d804ef Split into workspace 2024-04-20 01:37:57 -07:00
Greg Shuflin
49e6e3a71d Update readme 2024-04-20 01:29:10 -07:00
Greg Shuflin
cf7a2ff9ba Add logo
Logo originally from 2018 Nov 11
2023-03-24 03:30:48 -07:00
Greg Shuflin
aff809e4ce Merge commit '18b4ac0d4b79377428a0a32c16712057cc0a9a61' as 'subtrees/parser-combinator' 2023-03-09 17:30:07 -08:00
Greg Shuflin
18b4ac0d4b Squashed 'subtrees/parser-combinator/' content from commit 5526ce7
git-subtree-dir: subtrees/parser-combinator
git-subtree-split: 5526ce7bd17beda52047fbc3442e23e0174b79a7
2023-03-09 17:30:07 -08:00
Greg Shuflin
ab53cfdb7d Rust preliminaries 2023-01-14 02:00:26 -08:00
110 changed files with 1984 additions and 17031 deletions

5
.gitignore vendored
View File

@ -1,4 +1,3 @@
target
.schala_repl
.schala_history
rusty-tags.vi
node_modules/
experiments/tree-sitter-test/src

1249
Cargo.lock generated

File diff suppressed because it is too large Load Diff

View File

@ -1,20 +1,7 @@
[package]
name = "schala"
version = "0.1.0"
authors = ["greg <greg.shuflin@protonmail.com>"]
edition = "2018"
resolver = "2"
[dependencies]
getopts = "0.2.21"
schala-repl = { path = "schala-repl" }
schala-lang = { path = "schala-lang" }
# maaru-lang = { path = "maaru" }
# rukka-lang = { path = "rukka" }
# robo-lang = { path = "robo" }
[build-dependencies]
includedir_codegen = "0.2.0"
[workspace]
members = [
"schala-main",
"schala-parser",
"experiments",
]
resolver = "2"

View File

@ -1,920 +0,0 @@
{-# 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

185
Main.hs
View File

@ -1,185 +0,0 @@
{-# 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

112
README.md
View File

@ -1,110 +1,4 @@
# Schala - a programming language meta-interpreter
# Schala - A Programming Language Implementation
Schala is a Rust framework written to make it easy to create and experiment
with multiple 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, as well as
sharing state between multiple programming languages.
Schala is implemented as a Rust library `schala-repl`, which provides a `Repl`
data structure that takes in a value implementing the
`ProgrammingLanguageInterface` trait. Individual programming language
implementations are Rust types that implement `ProgrammingLanguageInterface`
and store whatever persistent state is relevant to that language.
## Running
Run schala with the normal `cargo run`. This will drop you into a REPL
environment. Type `:help` for more information, or type in text in any
supported programming language (currently only `schala-lang`) to evaluate it in
the REPL.
### Examples
Try running the following `schala-lang` code example in the REPL:
```
>> 1 + 1
(Total time)=> 736.368µs
=> 2
>> fn foo(x) { x + 10 }
(Total time)=> 772.496µs
=>
>> foo(0)
(Total time)=> 593.591µs
=> 10
>> 5 + foo(1)
(Total time)=> 1.119916ms
=> 16
>>
```
## History
Schala started out life as an experiment in writing a Javascript-like
programming language that would never encounter any kind of runtime value
error, but rather always return `null` under any kind of error condition. I had
seen one too many Javascript `Uncaught TypeError: Cannot read property ___ of
undefined` messages, and I was a bit frustrated. Plus I had always wanted to
write a programming langauge from scratch, and Rust is a fun language to
program in. Over time I became interested in playing around with other sorts
of programming languages as well, and wanted to make the process as general as
possible.
The name of the project comes from Schala the Princess of Zeal from the 1995
SNES RPG *Chrono Trigger*. I like classic JRPGs and enjoyed the thought of
creating a language name confusingly close to Scala. The naming scheme for
languages implemented with the Schala meta-interpreter is Chrono Trigger
characters.
Schala and languages implemented with it are incomplete alpha software and are
not ready for public release.
## Languages implemented using the meta-interpreter
* The eponymous *Schala* language is a work-in-progress general purpose
programming language with static typing and algebraic data types. Its design
goals include having a very straightforward implemenation and being syntactically
minimal.
* *Maaru* is a very simple dynamically-typed scripting language, with the semantics
that all runtime errors return a `null` value rather than fail.
* *Robo* is an experiment in creating a lazy, functional, strongly-typed language
much like Haskell
* *Rukka* is a straightforward LISP implementation
## Reference works
Here's a partial list of resources I've made use of in the process
of learning how to write a programming language.
### General
* http://thume.ca/2019/04/18/writing-a-compiler-in-rust/
### 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
* https://eli.thegreenplace.net/2018/unification/
* https://eli.thegreenplace.net/2018/type-inference/
* http://smallcultfollowing.com/babysteps/blog/2017/03/25/unification-in-chalk-part-1/
* http://reasonableapproximation.net/2019/05/05/hindley-milner.html
https://rickyhan.com/jekyll/update/2018/05/26/hindley-milner-tutorial-rust.html
### Evaluation
* _Understanding Computation_, Tom Stuart, O'Reilly 2013
* _Basics of Compiler Design_, Torben Mogensen
### 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/)
### LLVM
* http://blog.ulysse.io/2016/07/03/llvm-getting-started.html
`schala` is an implementation of a yet-unnamed quasi-functional programming
language.

213
TODO.md
View File

@ -1,213 +0,0 @@
# Immediate TODOs / General Code Cleanup
## Parsing
* cf. https://siraben.dev/2022/03/22/tree-sitter-linter.html write a tree-sitter parser for Schala
* Create a macro system, perhaps c.f. Crystal's?
* Macro system should be able to implement:
* printf-style variadic arguments
* something like the Rust/Haskell `Derive` construct
* doing useful things with all variants of an enum
* (e.g. what https://matklad.github.io//2022/03/26/self-modifying-code.html tries to solve)
## Testing
* Make an automatic (macro-based?) system for numbering compiler errors, this should be every type of error
## Symbols
* Add some good printf-debugging impls for SymbolTable-related items
* the symbol table should probably *only* be for global definitions (maybe rename it to reflect this?)
* dealing with variable lookup w/in functions/closures should probably happen in AST -> ReducedAST
* b/c that's where we go from a string name to a canonical ID (for e.g. 2nd param in 3rd enclosing scope)
* In fact to prove this works, the symbol table shoudl _parallelize_ the process of checking subscopes for local items
* Old notes on a plan of attack:
1. modify visitor so it can handle scopes
-this is needed both to handle import scope correctly
-and also to support making FQSNs aware of function parameters
2. Once FQSNs are aware of function parameters, most of the Rc<String> things in eval.rs can go away
## Typechecking
* make a type to represent types rather than relying on string comparisons
* look at https://rickyhan.com/jekyll/update/2018/05/26/hindley-milner-tutorial-rust.html
## General code cleanup
* standardize on an error type that isn't String
* implement a visitor pattern for the use of scope_resolver
* maybe implement this twice: 1) the value-returning, no-default one in the haoyi blogpost,
* look at
* https://gitlab.haskell.org/ghc/ghc/wikis/pattern-synonyms
* the non-value-returning, default one like in rustc (cf. https://github.com/rust-unofficial/patterns/blob/master/patterns/visitor.md)
# Longer-term Ideas
## Language Syntax
* the `type` declaration should have some kind of GADT-like syntax
* syntactic sugar for typestates? (cf. https://rustype.github.io/notes/notes/rust-typestate-series/rust-typestate-part-1.html )
* use `let` sigil to indicate a variable in a pattern explicitly:
```
q is MyStruct(let a, Chrono::Trigga) then {
// a is in scope here
}
```
* if you have a pattern-match where one variant has a variable and the other
lacks it instead of treating this as a type error, promote the bound variable
to an option type
* what if there was something like React jsx syntas built in? i.e. a way to
automatically transform some kind of markup into a function call, cf. `<h1
prop="arg">` -> h1(prop=arg)
* implement and test open/use statements
* Include extensible scala-style `html"string ${var}"` string interpolations
* 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 ["==, "<"] -> ...
}
```
* Schala should have both currying *and* default arguments!
```
fn a(b: Int, c:Int, d:Int = 1) -> Int
a(1,2) : Int
a(1,2,d=2): Int
a(_,1,3) : Int -> Int
a(1,2, c=_): Int -> Int
a(_,_,_) : Int -> Int -> Int -> Int
```
* scoped types - be able to define a quick enum type scoped to a function or other type for
something, that only is meant to be used as a quick bespoke interface between
two other things
ex.
```
type enum {
type enum MySubVariant {
SubVariant1, SubVariant2, etc.
}
Variant1(MySubVariant),
Variant2(...),
}
```
* inclusive/exclusive range syntax like .. vs ..=
* Nameable patterns/ pattern synonyms cf. https://gitlab.haskell.org/ghc/ghc/-/wikis/pattern-synonyms
## Typechecking
* cf. the notation mentioned in the cardelli paper, the debug information for the `typechecking` pass should
* print the generated type variable for every subexpression in an expression
* think about idris-related ideas of multiple implementations of a type for an interface (+ vs * impl for monoids, for preorder/inorder/postorder for Foldable)
* should have an Idris-like `cast To From` function
* something like the swift `Never` type ( https://nshipster.com/never/ ) in the stdlib
## Compilation
* look into Inkwell for rust LLVM bindings
* https://cranelift.readthedocs.io/en/latest/?badge=latest<Paste>
* look at https://gluon-lang.org/doc/nightly/book/embedding-api.html
# Syntax Playground
## Trying if-syntax again
```
//simple if expr
if x == 10 then "a" else "z"
//complex if expr
if x == 10 then {
let a = 1
let b = 2
a + b
} else {
55
}
// different comparison ops
if x {
== 1 then "a"
.isPrime() then "b"
else "c"
}
/* for now disallow `if x == { 1 then ... }`, b/c hard to parse
//simple pattern-matching
if x is Person("Ivan", age) then age else 0
//match-block equivalent
if x {
is Person("Ivan", _) then "Ivan"
is Person(_, age) if age > 13 then "barmitzvah'd"
else "foo"
}
```
## (OLD) Playing around with conditional syntax ideas
- 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 '}'`

8
experiments/Cargo.toml Normal file
View File

@ -0,0 +1,8 @@
[package]
name = "experiments"
version = "0.1.0"
edition = "2021"
# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
[dependencies]

3
experiments/src/main.rs Normal file
View File

@ -0,0 +1,3 @@
fn main() {
println!("Hello, world!");
}

View File

@ -0,0 +1,48 @@
module.exports = grammar({
name: "TestLang",
rules: {
source_file: $ => repeat($._definition),
_definition: $ => choice(
$.function_definition
//TODO others
),
function_definition: $ => seq(
'fn',
$.identifier,
$.parameter_list,
field("return_type", optional($._type)),
$.block,
),
parameter_list: $ => seq("(", /* TODO */ ")"),
block: $ => seq(
"{",
choice(
repeat($._statement),
"",
),
"}"
),
_statement: $ => choice(
$._return_statement
),
_return_statement: $ => seq("return", $._expression, ";"),
_expression: $ => choice($.identifier, $.unary, $.binary),
unary: $ => prec(4, choice(seq("-", $._expression), seq("!", $._expression))),
binary: $ => choice(prec.left(2, seq($._expression, "*", $._expression)), prec.left(1, seq($._expression, "+", $._expression))),
_type: $ => "bool",
_type: $ => choice(
$.primitive_type,
),
primitive_type: $ => choice("bool", "int"),
identifier: $ => /[a-z]+/,
}
});

View File

@ -0,0 +1,8 @@
_default:
just --list
# Test out the grammar
test-grammar:
#!/usr/bin/env bash
tree-sitter generate
tree-sitter test

View File

@ -0,0 +1,380 @@
{
"name": "tree-sitter-test",
"version": "1.0.0",
"lockfileVersion": 3,
"requires": true,
"packages": {
"": {
"name": "tree-sitter-test",
"version": "1.0.0",
"hasInstallScript": true,
"license": "ISC",
"dependencies": {
"node-addon-api": "^7.1.0",
"node-gyp-build": "^4.8.0"
},
"devDependencies": {
"prebuildify": "^6.0.0",
"tree-sitter-cli": "^0.22.5"
},
"peerDependencies": {
"tree-sitter": "^0.21.0"
},
"peerDependenciesMeta": {
"tree_sitter": {
"optional": true
}
}
},
"node_modules/base64-js": {
"version": "1.5.1",
"resolved": "https://registry.npmjs.org/base64-js/-/base64-js-1.5.1.tgz",
"integrity": "sha512-AKpaYlHn8t4SVbOHCy+b5+KKgvR4vrsD8vbvrbiQJps7fKDTkjkDry6ji0rUJjC0kzbNePLwzxq8iypo41qeWA==",
"dev": true,
"funding": [
{
"type": "github",
"url": "https://github.com/sponsors/feross"
},
{
"type": "patreon",
"url": "https://www.patreon.com/feross"
},
{
"type": "consulting",
"url": "https://feross.org/support"
}
]
},
"node_modules/bl": {
"version": "4.1.0",
"resolved": "https://registry.npmjs.org/bl/-/bl-4.1.0.tgz",
"integrity": "sha512-1W07cM9gS6DcLperZfFSj+bWLtaPGSOHWhPiGzXmvVJbRLdG82sH/Kn8EtW1VqWVA54AKf2h5k5BbnIbwF3h6w==",
"dev": true,
"dependencies": {
"buffer": "^5.5.0",
"inherits": "^2.0.4",
"readable-stream": "^3.4.0"
}
},
"node_modules/buffer": {
"version": "5.7.1",
"resolved": "https://registry.npmjs.org/buffer/-/buffer-5.7.1.tgz",
"integrity": "sha512-EHcyIPBQ4BSGlvjB16k5KgAJ27CIsHY/2JBmCRReo48y9rQ3MaUzWX3KVlBa4U7MyX02HdVj0K7C3WaB3ju7FQ==",
"dev": true,
"funding": [
{
"type": "github",
"url": "https://github.com/sponsors/feross"
},
{
"type": "patreon",
"url": "https://www.patreon.com/feross"
},
{
"type": "consulting",
"url": "https://feross.org/support"
}
],
"dependencies": {
"base64-js": "^1.3.1",
"ieee754": "^1.1.13"
}
},
"node_modules/chownr": {
"version": "1.1.4",
"resolved": "https://registry.npmjs.org/chownr/-/chownr-1.1.4.tgz",
"integrity": "sha512-jJ0bqzaylmJtVnNgzTeSOs8DPavpbYgEr/b0YL8/2GO3xJEhInFmhKMUnEJQjZumK7KXGFhUy89PrsJWlakBVg==",
"dev": true
},
"node_modules/end-of-stream": {
"version": "1.4.4",
"resolved": "https://registry.npmjs.org/end-of-stream/-/end-of-stream-1.4.4.tgz",
"integrity": "sha512-+uw1inIHVPQoaVuHzRyXd21icM+cnt4CzD5rW+NC1wjOUSTOs+Te7FOv7AhN7vS9x/oIyhLP5PR1H+phQAHu5Q==",
"dev": true,
"dependencies": {
"once": "^1.4.0"
}
},
"node_modules/fs-constants": {
"version": "1.0.0",
"resolved": "https://registry.npmjs.org/fs-constants/-/fs-constants-1.0.0.tgz",
"integrity": "sha512-y6OAwoSIf7FyjMIv94u+b5rdheZEjzR63GTyZJm5qh4Bi+2YgwLCcI/fPFZkL5PSixOt6ZNKm+w+Hfp/Bciwow==",
"dev": true
},
"node_modules/ieee754": {
"version": "1.2.1",
"resolved": "https://registry.npmjs.org/ieee754/-/ieee754-1.2.1.tgz",
"integrity": "sha512-dcyqhDvX1C46lXZcVqCpK+FtMRQVdIMN6/Df5js2zouUsqG7I6sFxitIC+7KYK29KdXOLHdu9zL4sFnoVQnqaA==",
"dev": true,
"funding": [
{
"type": "github",
"url": "https://github.com/sponsors/feross"
},
{
"type": "patreon",
"url": "https://www.patreon.com/feross"
},
{
"type": "consulting",
"url": "https://feross.org/support"
}
]
},
"node_modules/inherits": {
"version": "2.0.4",
"resolved": "https://registry.npmjs.org/inherits/-/inherits-2.0.4.tgz",
"integrity": "sha512-k/vGaX4/Yla3WzyMCvTQOXYeIHvqOKtnqBduzTHpzpQZzAskKMhZ2K+EnBiSM9zGSoIFeMpXKxa4dYeZIQqewQ==",
"dev": true
},
"node_modules/lru-cache": {
"version": "6.0.0",
"resolved": "https://registry.npmjs.org/lru-cache/-/lru-cache-6.0.0.tgz",
"integrity": "sha512-Jo6dJ04CmSjuznwJSS3pUeWmd/H0ffTlkXXgwZi+eq1UCmqQwCh+eLsYOYCwY991i2Fah4h1BEMCx4qThGbsiA==",
"dev": true,
"dependencies": {
"yallist": "^4.0.0"
},
"engines": {
"node": ">=10"
}
},
"node_modules/minimist": {
"version": "1.2.8",
"resolved": "https://registry.npmjs.org/minimist/-/minimist-1.2.8.tgz",
"integrity": "sha512-2yyAR8qBkN3YuheJanUpWC5U3bb5osDywNB8RzDVlDwDHbocAJveqqj1u8+SVD7jkWT4yvsHCpWqqWqAxb0zCA==",
"dev": true,
"funding": {
"url": "https://github.com/sponsors/ljharb"
}
},
"node_modules/mkdirp-classic": {
"version": "0.5.3",
"resolved": "https://registry.npmjs.org/mkdirp-classic/-/mkdirp-classic-0.5.3.tgz",
"integrity": "sha512-gKLcREMhtuZRwRAfqP3RFW+TK4JqApVBtOIftVgjuABpAtpxhPGaDcfvbhNvD0B8iD1oUr/txX35NjcaY6Ns/A==",
"dev": true
},
"node_modules/node-abi": {
"version": "3.60.0",
"resolved": "https://registry.npmjs.org/node-abi/-/node-abi-3.60.0.tgz",
"integrity": "sha512-zcGgwoXbzw9NczqbGzAWL/ToDYAxv1V8gL1D67ClbdkIfeeDBbY0GelZtC25ayLvVjr2q2cloHeQV1R0QAWqRQ==",
"dev": true,
"dependencies": {
"semver": "^7.3.5"
},
"engines": {
"node": ">=10"
}
},
"node_modules/node-addon-api": {
"version": "7.1.0",
"resolved": "https://registry.npmjs.org/node-addon-api/-/node-addon-api-7.1.0.tgz",
"integrity": "sha512-mNcltoe1R8o7STTegSOHdnJNN7s5EUvhoS7ShnTHDyOSd+8H+UdWODq6qSv67PjC8Zc5JRT8+oLAMCr0SIXw7g==",
"engines": {
"node": "^16 || ^18 || >= 20"
}
},
"node_modules/node-gyp-build": {
"version": "4.8.0",
"resolved": "https://registry.npmjs.org/node-gyp-build/-/node-gyp-build-4.8.0.tgz",
"integrity": "sha512-u6fs2AEUljNho3EYTJNBfImO5QTo/J/1Etd+NVdCj7qWKUSN/bSLkZwhDv7I+w/MSC6qJ4cknepkAYykDdK8og==",
"bin": {
"node-gyp-build": "bin.js",
"node-gyp-build-optional": "optional.js",
"node-gyp-build-test": "build-test.js"
}
},
"node_modules/npm-run-path": {
"version": "3.1.0",
"resolved": "https://registry.npmjs.org/npm-run-path/-/npm-run-path-3.1.0.tgz",
"integrity": "sha512-Dbl4A/VfiVGLgQv29URL9xshU8XDY1GeLy+fsaZ1AA8JDSfjvr5P5+pzRbWqRSBxk6/DW7MIh8lTM/PaGnP2kg==",
"dev": true,
"dependencies": {
"path-key": "^3.0.0"
},
"engines": {
"node": ">=8"
}
},
"node_modules/once": {
"version": "1.4.0",
"resolved": "https://registry.npmjs.org/once/-/once-1.4.0.tgz",
"integrity": "sha512-lNaJgI+2Q5URQBkccEKHTQOPaXdUxnZZElQTZY0MFUAuaEqe1E+Nyvgdz/aIyNi6Z9MzO5dv1H8n58/GELp3+w==",
"dev": true,
"dependencies": {
"wrappy": "1"
}
},
"node_modules/path-key": {
"version": "3.1.1",
"resolved": "https://registry.npmjs.org/path-key/-/path-key-3.1.1.tgz",
"integrity": "sha512-ojmeN0qd+y0jszEtoY48r0Peq5dwMEkIlCOu6Q5f41lfkswXuKtYrhgoTpLnyIcHm24Uhqx+5Tqm2InSwLhE6Q==",
"dev": true,
"engines": {
"node": ">=8"
}
},
"node_modules/prebuildify": {
"version": "6.0.1",
"resolved": "https://registry.npmjs.org/prebuildify/-/prebuildify-6.0.1.tgz",
"integrity": "sha512-8Y2oOOateom/s8dNBsGIcnm6AxPmLH4/nanQzL5lQMU+sC0CMhzARZHizwr36pUPLdvBnOkCNQzxg4djuFSgIw==",
"dev": true,
"dependencies": {
"minimist": "^1.2.5",
"mkdirp-classic": "^0.5.3",
"node-abi": "^3.3.0",
"npm-run-path": "^3.1.0",
"pump": "^3.0.0",
"tar-fs": "^2.1.0"
},
"bin": {
"prebuildify": "bin.js"
}
},
"node_modules/pump": {
"version": "3.0.0",
"resolved": "https://registry.npmjs.org/pump/-/pump-3.0.0.tgz",
"integrity": "sha512-LwZy+p3SFs1Pytd/jYct4wpv49HiYCqd9Rlc5ZVdk0V+8Yzv6jR5Blk3TRmPL1ft69TxP0IMZGJ+WPFU2BFhww==",
"dev": true,
"dependencies": {
"end-of-stream": "^1.1.0",
"once": "^1.3.1"
}
},
"node_modules/readable-stream": {
"version": "3.6.2",
"resolved": "https://registry.npmjs.org/readable-stream/-/readable-stream-3.6.2.tgz",
"integrity": "sha512-9u/sniCrY3D5WdsERHzHE4G2YCXqoG5FTHUiCC4SIbr6XcLZBY05ya9EKjYek9O5xOAwjGq+1JdGBAS7Q9ScoA==",
"dev": true,
"dependencies": {
"inherits": "^2.0.3",
"string_decoder": "^1.1.1",
"util-deprecate": "^1.0.1"
},
"engines": {
"node": ">= 6"
}
},
"node_modules/safe-buffer": {
"version": "5.2.1",
"resolved": "https://registry.npmjs.org/safe-buffer/-/safe-buffer-5.2.1.tgz",
"integrity": "sha512-rp3So07KcdmmKbGvgaNxQSJr7bGVSVk5S9Eq1F+ppbRo70+YeaDxkw5Dd8NPN+GD6bjnYm2VuPuCXmpuYvmCXQ==",
"dev": true,
"funding": [
{
"type": "github",
"url": "https://github.com/sponsors/feross"
},
{
"type": "patreon",
"url": "https://www.patreon.com/feross"
},
{
"type": "consulting",
"url": "https://feross.org/support"
}
]
},
"node_modules/semver": {
"version": "7.6.0",
"resolved": "https://registry.npmjs.org/semver/-/semver-7.6.0.tgz",
"integrity": "sha512-EnwXhrlwXMk9gKu5/flx5sv/an57AkRplG3hTK68W7FRDN+k+OWBj65M7719OkA82XLBxrcX0KSHj+X5COhOVg==",
"dev": true,
"dependencies": {
"lru-cache": "^6.0.0"
},
"bin": {
"semver": "bin/semver.js"
},
"engines": {
"node": ">=10"
}
},
"node_modules/string_decoder": {
"version": "1.3.0",
"resolved": "https://registry.npmjs.org/string_decoder/-/string_decoder-1.3.0.tgz",
"integrity": "sha512-hkRX8U1WjJFd8LsDJ2yQ/wWWxaopEsABU1XfkM8A+j0+85JAGppt16cr1Whg6KIbb4okU6Mql6BOj+uup/wKeA==",
"dev": true,
"dependencies": {
"safe-buffer": "~5.2.0"
}
},
"node_modules/tar-fs": {
"version": "2.1.1",
"resolved": "https://registry.npmjs.org/tar-fs/-/tar-fs-2.1.1.tgz",
"integrity": "sha512-V0r2Y9scmbDRLCNex/+hYzvp/zyYjvFbHPNgVTKfQvVrb6guiE/fxP+XblDNR011utopbkex2nM4dHNV6GDsng==",
"dev": true,
"dependencies": {
"chownr": "^1.1.1",
"mkdirp-classic": "^0.5.2",
"pump": "^3.0.0",
"tar-stream": "^2.1.4"
}
},
"node_modules/tar-stream": {
"version": "2.2.0",
"resolved": "https://registry.npmjs.org/tar-stream/-/tar-stream-2.2.0.tgz",
"integrity": "sha512-ujeqbceABgwMZxEJnk2HDY2DlnUZ+9oEcb1KzTVfYHio0UE6dG71n60d8D2I4qNvleWrrXpmjpt7vZeF1LnMZQ==",
"dev": true,
"dependencies": {
"bl": "^4.0.3",
"end-of-stream": "^1.4.1",
"fs-constants": "^1.0.0",
"inherits": "^2.0.3",
"readable-stream": "^3.1.1"
},
"engines": {
"node": ">=6"
}
},
"node_modules/tree-sitter": {
"version": "0.21.1",
"resolved": "https://registry.npmjs.org/tree-sitter/-/tree-sitter-0.21.1.tgz",
"integrity": "sha512-7dxoA6kYvtgWw80265MyqJlkRl4yawIjO7S5MigytjELkX43fV2WsAXzsNfO7sBpPPCF5Gp0+XzHk0DwLCq3xQ==",
"hasInstallScript": true,
"peer": true,
"dependencies": {
"node-addon-api": "^8.0.0",
"node-gyp-build": "^4.8.0"
}
},
"node_modules/tree-sitter-cli": {
"version": "0.22.5",
"resolved": "https://registry.npmjs.org/tree-sitter-cli/-/tree-sitter-cli-0.22.5.tgz",
"integrity": "sha512-c3VT46Bc3a6pEd0JAwufbqEw9Q2FRLDp5E230hGvnr+Hivw+Y6jyeP+3T89KDptvn48MOPVmbgaLm69xYgLVTw==",
"dev": true,
"hasInstallScript": true,
"bin": {
"tree-sitter": "cli.js"
}
},
"node_modules/tree-sitter/node_modules/node-addon-api": {
"version": "8.0.0",
"resolved": "https://registry.npmjs.org/node-addon-api/-/node-addon-api-8.0.0.tgz",
"integrity": "sha512-ipO7rsHEBqa9STO5C5T10fj732ml+5kLN1cAG8/jdHd56ldQeGj3Q7+scUS+VHK/qy1zLEwC4wMK5+yM0btPvw==",
"peer": true,
"engines": {
"node": "^18 || ^20 || >= 21"
}
},
"node_modules/util-deprecate": {
"version": "1.0.2",
"resolved": "https://registry.npmjs.org/util-deprecate/-/util-deprecate-1.0.2.tgz",
"integrity": "sha512-EPD5q1uXyFxJpCrLnCc1nHnq3gOa6DZBocAIiI2TaSCA7VCJ1UJDMagCzIkXNsUYfD1daK//LTEQ8xiIbrHtcw==",
"dev": true
},
"node_modules/wrappy": {
"version": "1.0.2",
"resolved": "https://registry.npmjs.org/wrappy/-/wrappy-1.0.2.tgz",
"integrity": "sha512-l4Sp/DRseor9wL6EvV2+TuQn63dMkPjZ/sp9XkghTEbV9KlPS1xUsZ3u7/IQO4wxtcFB4bgpQPRcR3QCvezPcQ==",
"dev": true
},
"node_modules/yallist": {
"version": "4.0.0",
"resolved": "https://registry.npmjs.org/yallist/-/yallist-4.0.0.tgz",
"integrity": "sha512-3wdGidZyq5PB084XLES5TpOSRA3wjXAlIWMhum2kRcv/41Sn2emQ0dycQW4uZXLejwKvg6EsvbdlVL+FYEct7A==",
"dev": true
}
}
}

View File

@ -0,0 +1,38 @@
{
"name": "tree-sitter-test",
"version": "1.0.0",
"main": "index.js",
"types": "bindings/node",
"scripts": {
"test": "echo \"Error: no test specified\" && exit 1",
"install": "node-gyp-build",
"prebuildify": "prebuildify --napi --strip"
},
"author": "",
"license": "ISC",
"description": "",
"dependencies": {
"node-addon-api": "^7.1.0",
"node-gyp-build": "^4.8.0"
},
"peerDependencies": {
"tree-sitter": "^0.21.0"
},
"peerDependenciesMeta": {
"tree_sitter": {
"optional": true
}
},
"devDependencies": {
"prebuildify": "^6.0.0",
"tree-sitter-cli": "^0.22.5"
},
"files": [
"grammar.js",
"binding.gyp",
"prebuilds/**",
"bindings/node/*",
"queries/*",
"src/**"
]
}

View File

@ -0,0 +1,26 @@
=============
Initial test
=============
fn main() {
}
----
(source_file
(function_definition
(identifier)
(parameter_list)
(block)
)
)
====
Another test
====
fn yolo() bool { }
----
(source_file
(function_definition
(identifier) (parameter_list) (primitive_type) (block)))

View File

@ -1,11 +0,0 @@
[package]
name = "maaru-lang"
version = "0.1.0"
authors = ["greg <greg.shuflin@protonmail.com>"]
[dependencies]
itertools = "0.5.8"
take_mut = "0.1.3"
llvm-sys = "*"
schala-repl = { path = "../schala-repl" }

View File

@ -1,481 +0,0 @@
extern crate take_mut;
use std::collections::HashMap;
use std::collections::VecDeque;
use parser::{AST, Statement, Expression, Function, Callable, BinOp};
use std::rc::Rc;
use std::io::{Write, Stdout, BufWriter};
use std::convert::From;
use parser::Expression::*;
use parser::Statement::*;
type Reduction<T> = (T, Option<SideEffect>);
#[derive(Debug, Clone)]
enum ReducedValue {
StringLiteral(Rc<String>),
ListLiteral(VecDeque<Expression>),
StructLiteral(VecDeque<(Rc<String>, Expression)>),
Number(f64),
Lambda(Function),
}
impl From<ReducedValue> for Expression {
fn from(rv: ReducedValue) -> Expression {
match rv {
ReducedValue::Number(n) => Expression::Number(n),
ReducedValue::StringLiteral(n) => Expression::StringLiteral(n),
ReducedValue::Lambda(f) => Expression::Lambda(f),
ReducedValue::ListLiteral(items) => Expression::ListLiteral(items),
ReducedValue::StructLiteral(items) => Expression::StructLiteral(items),
}
}
}
impl From<Expression> for ReducedValue {
fn from(rv: Expression) -> ReducedValue {
match rv {
Expression::Number(n) => ReducedValue::Number(n),
Expression::StringLiteral(n) => ReducedValue::StringLiteral(n),
Expression::Lambda(f) => ReducedValue::Lambda(f),
Expression::ListLiteral(items) => ReducedValue::ListLiteral(items),
Expression::StructLiteral(items) => ReducedValue::StructLiteral(items),
_ => panic!("trying to store a non-fully-reduced variable"),
}
}
}
fn get_indexer(f: f64) -> Option<usize> {
if f.fract() == 0.0 {
if f.trunc() >= 0.0 {
return Some(f.trunc() as usize);
}
}
None
}
#[derive(Debug)]
enum SideEffect {
Print(String),
AddBinding(Rc<String>, ReducedValue),
}
pub struct Evaluator<'a> {
parent: Option<&'a Evaluator<'a>>,
variables: HashMap<String, ReducedValue>,
stdout: BufWriter<Stdout>,
pub trace_evaluation: bool,
}
impl<'a> Evaluator<'a> {
pub fn new(parent: Option<&'a Evaluator>) -> Evaluator<'a> {
Evaluator {
variables: HashMap::new(),
parent: parent,
stdout: BufWriter::new(::std::io::stdout()),
trace_evaluation: parent.map_or(false, |e| e.trace_evaluation),
}
}
pub fn run(&mut self, ast: AST) -> Vec<String> {
ast.into_iter()
.map(|astnode| format!("{}", self.reduction_loop(astnode)))
.collect()
}
fn add_binding(&mut self, var: String, value: ReducedValue) {
self.variables.insert(var, value);
}
fn lookup_binding(&self, var: &str) -> Option<ReducedValue> {
match self.variables.get(var) {
Some(expr) => Some(expr.clone()),
None => match self.parent {
Some(env) => env.lookup_binding(var),
None => None
}
}
}
}
trait Evaluable {
fn is_reducible(&self) -> bool;
}
impl Evaluable for Statement {
fn is_reducible(&self) -> bool {
match self {
&ExprNode(ref expr) => expr.is_reducible(),
&FuncDefNode(_) => true,
}
}
}
impl Evaluable for Expression {
fn is_reducible(&self) -> bool {
match *self {
Null => false,
StringLiteral(_) => false,
Lambda(_) => false,
Number(_) => false,
ListLiteral(ref items) => {
items.iter().any(|x| x.is_reducible())
}
StructLiteral(ref items) => {
items.iter().any(|pair| pair.1.is_reducible())
}
_ => true,
}
}
}
impl Expression {
fn is_truthy(&self) -> bool {
match *self {
Null => false,
StringLiteral(ref s) if **s == "" => false,
Number(n) if n == 0.0 => false,
_ => true,
}
}
}
fn is_assignment(op: &BinOp) -> bool {
use self::BinOp::*;
match *op {
Assign | AddAssign | SubAssign |
MulAssign | DivAssign => true,
_ => false,
}
}
impl<'a> Evaluator<'a> {
fn reduction_loop(&mut self, mut node: Statement) -> Statement {
loop {
node = self.step(node);
if !node.is_reducible() {
break;
}
}
node
}
fn step(&mut self, node: Statement) -> Statement {
let mut trace = String::new();
if self.trace_evaluation {
trace.push_str(&format!("Step: {:?}", node));
}
let (new_node, side_effect) = self.reduce_astnode(node);
if self.trace_evaluation {
trace.push_str(&format!("{:?}", new_node));
}
if let Some(s) = side_effect {
if self.trace_evaluation {
trace.push_str(&format!(" | side-effect: {:?}", s));
}
self.perform_side_effect(s);
}
if self.trace_evaluation {
println!("{}", trace);
}
new_node
}
fn perform_side_effect(&mut self, side_effect: SideEffect) {
use self::SideEffect::*;
match side_effect {
Print(s) => {
write!(self.stdout, "{}\n", s).unwrap();
match self.stdout.flush() {
Ok(_) => (),
Err(_) => println!("Could not flush stdout"),
};
}
AddBinding(var, value) => {
self.add_binding((*var).clone(), value);
},
}
}
fn reduce_astnode(&mut self, node: Statement) -> Reduction<Statement> {
match node {
ExprNode(expr) => {
if expr.is_reducible() {
let (new_expr, side_effect) = self.reduce_expr(expr);
(ExprNode(new_expr), side_effect)
} else {
(ExprNode(expr), None)
}
}
FuncDefNode(func) => {
let name = func.prototype.name.clone();
let reduced_value = ReducedValue::Lambda(func.clone());
let binding = Some(SideEffect::AddBinding(name, reduced_value));
(ExprNode(Expression::Lambda(func)), binding)
}
}
}
//TODO I probably want another Expression variant that holds a ReducedValue
fn reduce_expr(&mut self, expression: Expression) -> Reduction<Expression> {
match expression {
Null => (Null, None),
e @ StringLiteral(_) => (e, None),
e @ Number(_) => (e, None),
e @ Lambda(_) => (e, None),
Variable(ref var) => {
match self.lookup_binding(var).map(|x| x.into()) {
None => (Null, None),
Some(expr) => (expr, None),
}
}
BinExp(op, mut left, mut right) => {
if right.is_reducible() {
let mut side_effect = None;
take_mut::take(right.as_mut(), |expr| { let (a, b) = self.reduce_expr(expr); side_effect = b; a});
return (BinExp(op, left, right), side_effect);
}
if let BinOp::Assign = op {
return match *left {
Variable(var) => {
let reduced_value: ReducedValue = ReducedValue::from(*right);
let binding = SideEffect::AddBinding(var, reduced_value);
(Null, Some(binding))
},
_ => (Null, None)
};
}
if is_assignment(&op) {
use self::BinOp::*;
let new_op = match op {
AddAssign => Add,
SubAssign => Sub,
MulAssign => Mul,
DivAssign => Div,
_ => unreachable!(),
};
let reduction =
BinExp(BinOp::Assign,
Box::new(*left.clone()),
Box::new(BinExp(new_op, left, right))
);
return (reduction, None);
}
if left.is_reducible() {
let mut side_effect = None;
take_mut::take(left.as_mut(), |expr| { let (a, b) = self.reduce_expr(expr); side_effect = b; a});
(BinExp(op, left, right), side_effect)
} else {
(self.reduce_binop(op, *left, *right), None) //can assume both arguments are maximally reduced
}
}
Call(callable, mut args) => {
let mut f = true;
for arg in args.iter_mut() {
if arg.is_reducible() {
take_mut::take(arg, |arg| self.reduce_expr(arg).0);
f = false;
break;
}
}
if f {
self.reduce_call(callable, args)
} else {
(Call(callable, args), None)
}
}
While(test, body) => {
let mut block = VecDeque::from(body.clone());
block.push_back(While(test.clone(), body.clone()));
let reduction = Conditional(test, Box::new(Block(block)), None);
(reduction, None)
}
Conditional(box test, then_block, else_block) => {
if test.is_reducible() {
let (new_test, new_effect) = self.reduce_expr(test);
(Conditional(Box::new(new_test), then_block, else_block), new_effect)
} else {
if test.is_truthy() {
(*then_block, None)
} else {
match else_block {
Some(box expr) => (expr, None),
None => (Null, None),
}
}
}
}
Block(mut exprs) => {
let first = exprs.pop_front();
match first {
None => (Null, None),
Some(expr) => {
if exprs.len() == 0 {
(expr, None)
} else {
if expr.is_reducible() {
let (new, side_effect) = self.reduce_expr(expr);
exprs.push_front(new);
(Block(exprs), side_effect)
} else {
(Block(exprs), None)
}
}
}
}
}
Index(mut expr, mut index_expr) => {
if index_expr.is_reducible() {
let mut side_effect = None;
take_mut::take(index_expr.as_mut(), |expr| { let (a, b) = self.reduce_expr(expr); side_effect = b; a});
return (Index(expr, index_expr), side_effect)
}
if expr.is_reducible() {
let mut side_effect = None;
take_mut::take(expr.as_mut(), |expr| { let (a, b) = self.reduce_expr(expr); side_effect = b; a});
return (Index(expr, index_expr), side_effect);
}
match (*expr, *index_expr) {
(ListLiteral(list_items), Number(n)) => {
let indexed_expr = get_indexer(n).and_then(|i| list_items.get(i));
if let Some(e) = indexed_expr {
(e.clone(), None)
} else {
(Null, None)
}
}
(StructLiteral(items), StringLiteral(s)) => {
for item in items {
if s == item.0 {
return (item.1.clone(), None); //TODO this is hella inefficient
}
}
(Null, None)
},
_ => (Null, None)
}
}
ListLiteral(mut exprs) => {
let mut side_effect = None;
for expr in exprs.iter_mut() {
if expr.is_reducible() {
take_mut::take(expr, |expr| {
let (a, b) = self.reduce_expr(expr);
side_effect = b;
a
});
break;
}
}
(ListLiteral(exprs), side_effect)
},
StructLiteral(mut items) => {
let mut side_effect = None;
for pair in items.iter_mut() {
if pair.1.is_reducible() {
take_mut::take(pair, |pair| {
let (name, expr) = pair;
let (a, b) = self.reduce_expr(expr);
side_effect = b;
(name, a)
});
break;
}
}
(StructLiteral(items), side_effect)
}
}
}
fn reduce_binop(&mut self, op: BinOp, left: Expression, right: Expression) -> Expression {
use self::BinOp::*;
let truthy = Number(1.0);
let falsy = Null;
match (op, left, right) {
(Add, Number(l), Number(r)) => Number(l + r),
(Add, StringLiteral(s1), StringLiteral(s2)) => StringLiteral(Rc::new(format!("{}{}", *s1, *s2))),
(Add, StringLiteral(s1), Number(r)) => StringLiteral(Rc::new(format!("{}{}", *s1, r))),
(Add, Number(l), StringLiteral(s1)) => StringLiteral(Rc::new(format!("{}{}", l, *s1))),
(Sub, Number(l), Number(r)) => Number(l - r),
(Mul, Number(l), Number(r)) => Number(l * r),
(Div, Number(l), Number(r)) if r != 0.0 => Number(l / r),
(Mod, Number(l), Number(r)) => Number(l % r),
(Less, Number(l), Number(r)) => if l < r { truthy } else { falsy },
(LessEq, Number(l), Number(r)) => if l <= r { truthy } else { falsy },
(Greater, Number(l), Number(r)) => if l > r { truthy } else { falsy },
(GreaterEq, Number(l), Number(r)) => if l >= r { truthy } else { falsy },
(Equal, Number(l), Number(r)) => if l == r { truthy } else { falsy },
(Equal, Null, Null) => truthy,
(Equal, StringLiteral(s1), StringLiteral(s2)) => if s1 == s2 { truthy } else { falsy },
(Equal, _, _) => falsy,
_ => falsy,
}
}
fn reduce_call(&mut self, callable: Callable, arguments: Vec<Expression>) -> Reduction<Expression> {
if let Some(res) = handle_builtin(&callable, &arguments) {
return res;
}
let function = match callable {
Callable::Lambda(func) => func.clone(),
Callable::NamedFunction(name) => {
match self.lookup_binding(&*name) {
Some(ReducedValue::Lambda(func)) => func,
_ => return (Null, None),
}
}
};
if function.prototype.parameters.len() != arguments.len() {
return (Null, None);
}
let mut evaluator = Evaluator::new(Some(self));
for (binding, expr) in function.prototype.parameters.iter().zip(arguments.iter()) {
evaluator.add_binding((**binding).clone(), expr.clone().into());
}
let nodes = function.body.iter().map(|node| node.clone());
let mut retval = ExprNode(Null);
for n in nodes {
retval = evaluator.reduction_loop(n);
}
match retval {
ExprNode(expr) => (expr, None),
FuncDefNode(_) => panic!("This should never happen! A maximally-reduced node\
should never be a function definition!")
}
}
}
fn handle_builtin(callable: &Callable, arguments: &Vec<Expression>) -> Option<Reduction<Expression>> {
let name: &str = match *callable {
Callable::NamedFunction(ref name) => *&name,
_ => return None,
};
match name {
"print" => {
let mut s = String::new();
for arg in arguments {
s.push_str(&format!("{} ", arg));
}
return Some((Null, Some(SideEffect::Print(s))));
},
_ => None
}
}

View File

@ -1,78 +0,0 @@
#![feature(box_patterns)]
extern crate schala_repl;
mod tokenizer;
mod parser;
mod eval;
#[derive(Debug)]
pub struct TokenError {
pub msg: String,
}
impl TokenError {
pub fn new(msg: &str) -> TokenError {
TokenError { msg: msg.to_string() }
}
}
pub use self::eval::Evaluator as MaaruEvaluator;
pub struct Maaru<'a> {
evaluator: MaaruEvaluator<'a>
}
impl<'a> Maaru<'a> {
pub fn new() -> Maaru<'a> {
Maaru {
evaluator: MaaruEvaluator::new(None),
}
}
}
/*
fn execute_pipeline(&mut self, input: &str, options: &EvalOptions) -> Result<String, String> {
let mut output = UnfinishedComputation::default();
let tokens = match tokenizer::tokenize(input) {
Ok(tokens) => {
if let Some(_) = options.debug_passes.get("tokens") {
output.add_artifact(TraceArtifact::new("tokens", format!("{:?}", tokens)));
}
tokens
},
Err(err) => {
return output.finish(Err(format!("Tokenization error: {:?}\n", err.msg)))
}
};
let ast = match parser::parse(&tokens, &[]) {
Ok(ast) => {
if let Some(_) = options.debug_passes.get("ast") {
output.add_artifact(TraceArtifact::new("ast", format!("{:?}", ast)));
}
ast
},
Err(err) => {
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);
}
Ok(evaluation_output)
}
*/
/*
impl<'a> ProgrammingLanguageInterface for Maaru<'a> {
fn get_language_name(&self) -> String {
"Maaru".to_string()
}
fn get_source_file_suffix(&self) -> String {
format!("maaru")
}
}
*/

View File

@ -1,755 +0,0 @@
use tokenizer::{Token, Kw, OpTok};
use tokenizer::Token::*;
use std::fmt;
use std::collections::VecDeque;
use std::rc::Rc;
use std::convert::From;
// Grammar
// program := (statement delimiter ?)*
// delimiter := Newline | Semicolon
// statement := declaration | expression
// declaration := FN prototype LCurlyBrace (statement)* RCurlyBrace
// prototype := identifier LParen identlist RParen
// identlist := Ident (Comma Ident)* | ε
// exprlist := Expression (Comma Expression)* | ε
// itemlist := Ident COLON Expression (Comma Ident COLON Expression)* | ε
//
// expression := postop_expression (op postop_expression)*
// postop_expression := primary_expression postop
// primary_expression := number_expr | String | identifier_expr | paren_expr | conditional_expr | while_expr | lambda_expr | list_expr | struct_expr
// number_expr := (PLUS | MINUS ) number_expr | Number
// identifier_expr := call_expression | Variable
// list_expr := LSquareBracket exprlist RSquareBracket
// struct_expr := LCurlyBrace itemlist RCurlyBrace
// call_expression := Identifier LParen exprlist RParen
// while_expr := WHILE primary_expression LCurlyBrace (expression delimiter)* RCurlyBrace
// paren_expr := LParen expression RParen
// conditional_expr := IF expression LCurlyBrace (expression delimiter)* RCurlyBrace (LCurlyBrace (expresion delimiter)* RCurlyBrace)?
// lambda_expr := FN LParen identlist RParen LCurlyBrace (expression delimiter)* RCurlyBrace
// lambda_call := | LParen exprlist RParen
// postop := ε | LParen exprlist RParen | LBracket expression RBracket
// op := '+', '-', etc.
//
pub type AST = Vec<Statement>;
#[derive(Debug, Clone)]
pub enum Statement {
ExprNode(Expression),
FuncDefNode(Function),
}
impl fmt::Display for Statement {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
use self::Statement::*;
match *self {
ExprNode(ref expr) => write!(f, "{}", expr),
FuncDefNode(_) => write!(f, "UNIMPLEMENTED"),
}
}
}
#[derive(Debug, Clone)]
pub struct Function {
pub prototype: Prototype,
pub body: Vec<Statement>,
}
#[derive(Debug, Clone, PartialEq)]
pub struct Prototype {
pub name: Rc<String>,
pub parameters: Vec<Rc<String>>,
}
#[derive(Debug, Clone)]
pub enum Expression {
Null,
StringLiteral(Rc<String>),
Number(f64),
Variable(Rc<String>),
BinExp(BinOp, Box<Expression>, Box<Expression>),
Call(Callable, Vec<Expression>),
Conditional(Box<Expression>, Box<Expression>, Option<Box<Expression>>),
Lambda(Function),
Block(VecDeque<Expression>),
While(Box<Expression>, Vec<Expression>),
Index(Box<Expression>, Box<Expression>),
ListLiteral(VecDeque<Expression>),
StructLiteral(VecDeque<(Rc<String>, Expression)>),
}
#[derive(Clone, Debug)]
pub enum Callable {
NamedFunction(Rc<String>),
Lambda(Function),
}
//TODO this ought to be ReducedExpression
impl fmt::Display for Expression {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
use self::Expression::*;
match *self {
Null => write!(f, "null"),
StringLiteral(ref s) => write!(f, "\"{}\"", s),
Number(n) => write!(f, "{}", n),
Lambda(Function { prototype: Prototype { ref name, ref parameters, .. }, .. }) => {
write!(f, "«function: {}, {} arg(s)»", name, parameters.len())
}
ListLiteral(ref items) => {
write!(f, "[ ")?;
let mut iter = items.iter().peekable();
while let Some(item) = iter.next() {
write!(f, "{}", item)?;
if let Some(_) = iter.peek() {
write!(f, ", ")?;
}
}
write!(f, " ]")
}
StructLiteral(ref items) => {
write!(f, "{} ", "{")?;
let mut iter = items.iter().peekable();
while let Some(pair) = iter.next() {
write!(f, "{}: {}", pair.0, pair.1)?;
if let Some(_) = iter.peek() {
write!(f, ", ")?;
}
}
write!(f, "{} ", "}")
}
_ => write!(f, "UNIMPLEMENTED"),
}
}
}
#[derive(Debug, Clone)]
pub enum BinOp {
Add,
AddAssign,
Sub,
SubAssign,
Mul,
MulAssign,
Div,
DivAssign,
Mod,
Less,
LessEq,
Greater,
GreaterEq,
Equal,
Assign,
Custom(String),
}
impl From<OpTok> for BinOp {
fn from(token: OpTok) -> BinOp {
use self::BinOp::*;
match &token.0[..] {
"+" => Add,
"+=" => AddAssign,
"-" => Sub,
"-=" => SubAssign,
"*" => Mul,
"*=" => MulAssign,
"/" => Div,
"/=" => DivAssign,
"%" => Mod,
"<" => Less,
"<=" => LessEq,
">" => Greater,
">=" => GreaterEq,
"==" => Equal,
"=" => Assign,
op => Custom(op.to_string()),
}
}
}
type Precedence = u8;
// TODO make this support incomplete parses
pub type ParseResult<T> = Result<T, ParseError>;
#[derive(Debug)]
pub struct ParseError {
pub msg: String,
pub remaining_tokens: Vec<Token>,
}
impl ParseError {
fn result_from_str<T>(msg: &str) -> ParseResult<T> {
Err(ParseError {
msg: msg.to_string(),
remaining_tokens: vec![],
})
}
}
struct Parser {
tokens: Vec<Token>,
}
impl Parser {
fn initialize(tokens: &[Token]) -> Parser {
let mut tokens = tokens.to_vec();
tokens.reverse();
Parser { tokens: tokens }
}
fn peek(&self) -> Option<Token> {
self.tokens.last().map(|x| x.clone())
}
fn next(&mut self) -> Option<Token> {
self.tokens.pop()
}
fn get_precedence(&self, op: &OpTok) -> Precedence {
match &op.0[..] {
"+" => 10,
"-" => 10,
"*" => 20,
"/" => 20,
"%" => 20,
"==" => 40,
"=" | "+=" | "-=" | "*=" | "/=" => 1,
">" | ">=" | "<" | "<=" => 30,
_ => 255,
}
}
}
macro_rules! expect {
($self_:expr, $token:pat) => {
match $self_.peek() {
Some($token) => {$self_.next();},
Some(x) => {
let err = format!("Expected `{:?}` but got `{:?}`", stringify!($token), x);
return ParseError::result_from_str(&err)
},
None => {
let err = format!("Expected `{:?}` but got end of input", stringify!($token));
return ParseError::result_from_str(&err) //TODO make this not require 2 stringifications
}
}
}
}
macro_rules! expect_identifier {
($self_:expr) => {
match $self_.peek() {
Some(Identifier(s)) => {$self_.next(); s},
Some(x) => return ParseError::result_from_str(&format!("Expected identifier, but got {:?}", x)),
None => return ParseError::result_from_str("Expected identifier, but got end of input"),
}
}
}
macro_rules! skip_whitespace {
($_self: expr) => {
loop {
match $_self.peek() {
Some(ref t) if is_delimiter(t) => {
$_self.next();
continue;
}
_ => break,
}
}
}
}
macro_rules! delimiter_block {
($_self: expr, $try_parse: ident, $($break_pattern: pat)|+) => {
{
let mut acc = Vec::new();
loop {
match $_self.peek() {
None => break,
Some(ref t) if is_delimiter(t) => { $_self.next(); continue; },
$($break_pattern)|+ => break,
_ => {
let a = try!($_self.$try_parse());
acc.push(a);
}
}
}
acc
}
}
}
fn is_delimiter(token: &Token) -> bool {
match *token {
Newline | Semicolon => true,
_ => false,
}
}
impl Parser {
fn program(&mut self) -> ParseResult<AST> {
let mut ast = Vec::new(); //TODO have this come from previously-parsed tree
loop {
let result: ParseResult<Statement> = match self.peek() {
Some(ref t) if is_delimiter(t) => {
self.next();
continue;
}
Some(_) => self.statement(),
None => break,
};
match result {
Ok(node) => ast.push(node),
Err(mut err) => {
err.remaining_tokens = self.tokens.clone();
err.remaining_tokens.reverse();
return Err(err);
}
}
}
Ok(ast)
}
fn statement(&mut self) -> ParseResult<Statement> {
let node: Statement = match self.peek() {
Some(Keyword(Kw::Fn)) => self.declaration()?,
Some(_) => Statement::ExprNode(self.expression()?),
None => panic!("Unexpected end of tokens"),
};
Ok(node)
}
fn declaration(&mut self) -> ParseResult<Statement> {
expect!(self, Keyword(Kw::Fn));
let prototype = self.prototype()?;
expect!(self, LCurlyBrace);
let body = self.body()?;
expect!(self, RCurlyBrace);
Ok(Statement::FuncDefNode(Function {
prototype: prototype,
body: body,
}))
}
fn prototype(&mut self) -> ParseResult<Prototype> {
let name = expect_identifier!(self);
expect!(self, LParen);
let parameters = self.identlist()?;
expect!(self, RParen);
Ok(Prototype {
name: name,
parameters: parameters,
})
}
fn identlist(&mut self) -> ParseResult<Vec<Rc<String>>> {
let mut args = Vec::new();
while let Some(Identifier(name)) = self.peek() {
args.push(name.clone());
self.next();
match self.peek() {
Some(Comma) => {self.next();},
_ => break,
}
}
Ok(args)
}
fn exprlist(&mut self) -> ParseResult<Vec<Expression>> {
let mut exprs = Vec::new();
loop {
if let Some(RParen) = self.peek() {
break;
}
let exp = self.expression()?;
exprs.push(exp);
match self.peek() {
Some(Comma) => {self.next();},
_ => break,
}
}
Ok(exprs)
}
fn itemlist(&mut self) -> ParseResult<VecDeque<(Rc<String>, Expression)>> {
let mut items = VecDeque::new();
loop {
if let Some(RCurlyBrace) = self.peek() {
break;
}
let name = expect_identifier!(self);
expect!(self, Colon);
let expr = self.expression()?;
items.push_back((name, expr));
match self.peek() {
Some(Comma) => {self.next();},
_ => break,
};
}
Ok(items)
}
fn body(&mut self) -> ParseResult<Vec<Statement>> {
let statements = delimiter_block!(
self,
statement,
Some(RCurlyBrace)
);
Ok(statements)
}
fn expression(&mut self) -> ParseResult<Expression> {
let lhs: Expression = self.postop_expression()?;
self.precedence_expr(lhs, 0)
}
fn precedence_expr(&mut self,
mut lhs: Expression,
min_precedence: u8)
-> ParseResult<Expression> {
while let Some(Operator(op)) = self.peek() {
let precedence = self.get_precedence(&op);
if precedence < min_precedence {
break;
}
self.next();
let mut rhs = self.postop_expression()?;
while let Some(Operator(ref op)) = self.peek() {
if self.get_precedence(op) > precedence {
let new_prec = self.get_precedence(op);
rhs = self.precedence_expr(rhs, new_prec)?;
} else {
break;
}
}
lhs = Expression::BinExp(op.into(), Box::new(lhs), Box::new(rhs));
}
Ok(lhs)
}
fn postop_expression(&mut self) -> ParseResult<Expression> {
use self::Expression::*;
let expr = self.primary_expression()?;
let ret = match self.peek() {
Some(LParen) => {
let args = self.call_expression()?;
match expr {
Lambda(f) => Call(Callable::Lambda(f), args),
e => {
let err = format!("Expected lambda expression before a call, got {:?}", e);
return ParseError::result_from_str(&err);
},
}
},
Some(LSquareBracket) => {
expect!(self, LSquareBracket);
let index_expr = self.expression()?;
expect!(self, RSquareBracket);
Index(Box::new(expr), Box::new(index_expr))
},
_ => {
expr
}
};
Ok(ret)
}
fn primary_expression(&mut self) -> ParseResult<Expression> {
Ok(match self.peek() {
Some(Keyword(Kw::Null)) => {
self.next();
Expression::Null
}
Some(NumLiteral(_)) => self.number_expression()?,
Some(Operator(OpTok(ref a))) if **a == "+" || **a == "-" => self.number_expression()?,
Some(StrLiteral(s)) => {
self.next();
Expression::StringLiteral(s)
}
Some(Keyword(Kw::If)) => self.conditional_expr()?,
Some(Keyword(Kw::While)) => self.while_expr()?,
Some(Identifier(_)) => self.identifier_expr()?,
Some(Token::LParen) => self.paren_expr()?,
Some(Keyword(Kw::Fn)) => self.lambda_expr()?,
Some(Token::LSquareBracket) => self.list_expr()?,
Some(Token::LCurlyBrace) => self.struct_expr()?,
Some(e) => {
return ParseError::result_from_str(&format!("Expected primary expression, got \
{:?}",
e));
}
None => return ParseError::result_from_str("Expected primary expression received EoI"),
})
}
fn list_expr(&mut self) -> ParseResult<Expression> {
expect!(self, LSquareBracket);
let exprlist: Vec<Expression> = self.exprlist()?;
expect!(self, RSquareBracket);
Ok(Expression::ListLiteral(VecDeque::from(exprlist)))
}
fn struct_expr(&mut self) -> ParseResult<Expression> {
expect!(self, LCurlyBrace);
let struct_items = self.itemlist()?;
expect!(self, RCurlyBrace);
Ok(Expression::StructLiteral(struct_items))
}
fn number_expression(&mut self) -> ParseResult<Expression> {
let mut multiplier = 1;
loop {
match self.peek() {
Some(NumLiteral(n)) => {
self.next();
return Ok(Expression::Number(n * multiplier as f64));
}
Some(Operator(OpTok(ref a))) if **a == "+" => {
self.next();
}
Some(Operator(OpTok(ref a))) if **a == "-" => {
multiplier *= -1;
self.next();
}
Some(e) => {
return ParseError::result_from_str(
&format!("Expected +, - or number, got {:?}", e));
}
None => {
return ParseError::result_from_str(
&format!("Expected +, - or number, got EoI"));
}
}
}
}
fn lambda_expr(&mut self) -> ParseResult<Expression> {
use self::Expression::*;
expect!(self, Keyword(Kw::Fn));
skip_whitespace!(self);
expect!(self, LParen);
let parameters = self.identlist()?;
expect!(self, RParen);
skip_whitespace!(self);
expect!(self, LCurlyBrace);
let body = self.body()?;
expect!(self, RCurlyBrace);
let prototype = Prototype {
name: Rc::new("a lambda yo!".to_string()),
parameters: parameters,
};
let function = Function {
prototype: prototype,
body: body,
};
Ok(Lambda(function))
}
fn while_expr(&mut self) -> ParseResult<Expression> {
use self::Expression::*;
expect!(self, Keyword(Kw::While));
let test = self.expression()?;
expect!(self, LCurlyBrace);
let body = delimiter_block!(
self,
expression,
Some(RCurlyBrace)
);
expect!(self, RCurlyBrace);
Ok(While(Box::new(test), body))
}
fn conditional_expr(&mut self) -> ParseResult<Expression> {
use self::Expression::*;
expect!(self, Keyword(Kw::If));
let test = self.expression()?;
skip_whitespace!(self);
expect!(self, LCurlyBrace);
skip_whitespace!(self);
let then_block = delimiter_block!(
self,
expression,
Some(RCurlyBrace)
);
expect!(self, RCurlyBrace);
skip_whitespace!(self);
let else_block = if let Some(Keyword(Kw::Else)) = self.peek() {
self.next();
skip_whitespace!(self);
expect!(self, LCurlyBrace);
let else_exprs = delimiter_block!(
self,
expression,
Some(RCurlyBrace)
);
Some(else_exprs)
} else {
None
};
expect!(self, RCurlyBrace);
Ok(Conditional(Box::new(test),
Box::new(Block(VecDeque::from(then_block))),
else_block.map(|list| Box::new(Block(VecDeque::from(list))))))
}
fn identifier_expr(&mut self) -> ParseResult<Expression> {
let name = expect_identifier!(self);
let expr = match self.peek() {
Some(LParen) => {
let args = self.call_expression()?;
Expression::Call(Callable::NamedFunction(name), args)
}
__ => Expression::Variable(name),
};
Ok(expr)
}
fn call_expression(&mut self) -> ParseResult<Vec<Expression>> {
expect!(self, LParen);
let args: Vec<Expression> = self.exprlist()?;
expect!(self, RParen);
Ok(args)
}
fn paren_expr(&mut self) -> ParseResult<Expression> {
expect!(self, Token::LParen);
let expr = self.expression()?;
expect!(self, Token::RParen);
Ok(expr)
}
}
pub fn parse(tokens: &[Token], _parsed_tree: &[Statement]) -> ParseResult<AST> {
let mut parser = Parser::initialize(tokens);
parser.program()
}
/*
#[cfg(test)]
mod tests {
use schala_lang::tokenizer;
use super::*;
use super::Statement::*;
use super::Expression::*;
macro_rules! parsetest {
($input:expr, $output:pat, $ifexpr:expr) => {
{
let tokens = tokenizer::tokenize($input).unwrap();
let ast = parse(&tokens, &[]).unwrap();
match &ast[..] {
$output if $ifexpr => (),
x => panic!("Error in parse test, got {:?} instead", x)
}
}
}
}
#[test]
fn function_parse_test() {
use super::Function;
parsetest!(
"fn a() { 1 + 2 }",
&[FuncDefNode(Function {prototype: Prototype { ref name, ref parameters }, ref body})],
match &body[..] { &[ExprNode(BinExp(_, box Number(1.0), box Number(2.0)))] => true, _ => false }
&& **name == "a" && match &parameters[..] { &[] => true, _ => false }
);
parsetest!(
"fn a(x,y){ 1 + 2 }",
&[FuncDefNode(Function {prototype: Prototype { ref name, ref parameters }, ref body})],
match &body[..] { &[ExprNode(BinExp(_, box Number(1.0), box Number(2.0)))] => true, _ => false }
&& **name == "a" && *parameters[0] == "x" && *parameters[1] == "y" && parameters.len() == 2
);
let t3 = "fn (x) { x + 2 }";
let tokens3 = tokenizer::tokenize(t3).unwrap();
assert!(parse(&tokens3, &[]).is_err());
}
#[test]
fn expression_parse_test() {
parsetest!("a", &[ExprNode(Variable(ref s))], **s == "a");
parsetest!("a + b",
&[ExprNode(BinExp(BinOp::Add, box Variable(ref a), box Variable(ref b)))],
**a == "a" && **b == "b");
parsetest!("a + b * c",
&[ExprNode(BinExp(BinOp::Add, box Variable(ref a), box BinExp(BinOp::Mul, box Variable(ref b), box Variable(ref c))))],
**a == "a" && **b == "b" && **c == "c");
parsetest!("a * b + c",
&[ExprNode(BinExp(BinOp::Add, box BinExp(BinOp::Mul, box Variable(ref a), box Variable(ref b)), box Variable(ref c)))],
**a == "a" && **b == "b" && **c == "c");
parsetest!("(a + b) * c",
&[ExprNode(BinExp(BinOp::Mul, box BinExp(BinOp::Add, box Variable(ref a), box Variable(ref b)), box Variable(ref c)))],
**a == "a" && **b == "b" && **c == "c");
}
#[test]
fn lambda_parse_test() {
use schala_lang::tokenizer;
let t1 = "(fn(x) { x + 2 })";
let tokens1 = tokenizer::tokenize(t1).unwrap();
match parse(&tokens1, &[]).unwrap()[..] {
_ => (),
}
let t2 = "fn(x) { x + 2 }";
let tokens2 = tokenizer::tokenize(t2).unwrap();
assert!(parse(&tokens2, &[]).is_err());
let t3 = "(fn(x) { x + 10 })(20)";
let tokens3 = tokenizer::tokenize(t3).unwrap();
match parse(&tokens3, &[]).unwrap() {
_ => (),
};
}
#[test]
fn conditional_parse_test() {
use schala_lang::tokenizer;
let t1 = "if null { 20 } else { 40 }";
let tokens = tokenizer::tokenize(t1).unwrap();
match parse(&tokens, &[]).unwrap()[..] {
[ExprNode(Conditional(box Null, box Block(_), Some(box Block(_))))] => (),
_ => panic!(),
}
let t2 = r"
if null {
20
} else {
40
}
";
let tokens2 = tokenizer::tokenize(t2).unwrap();
match parse(&tokens2, &[]).unwrap()[..] {
[ExprNode(Conditional(box Null, box Block(_), Some(box Block(_))))] => (),
_ => panic!(),
}
let t2 = r"
if null {
20 } else
{
40
}
";
let tokens3 = tokenizer::tokenize(t2).unwrap();
match parse(&tokens3, &[]).unwrap()[..] {
[ExprNode(Conditional(box Null, box Block(_), Some(box Block(_))))] => (),
_ => panic!(),
}
}
}
*/

View File

@ -1,208 +0,0 @@
extern crate itertools;
use std::iter::Peekable;
use std::str::Chars;
use self::itertools::Itertools;
use std::rc::Rc;
use TokenError;
#[derive(Debug, Clone, PartialEq)]
pub enum Token {
Newline,
Semicolon,
LParen,
RParen,
LSquareBracket,
RSquareBracket,
LCurlyBrace,
RCurlyBrace,
Comma,
Period,
Colon,
NumLiteral(f64),
StrLiteral(Rc<String>),
Identifier(Rc<String>),
Operator(OpTok),
Keyword(Kw),
}
#[derive(Debug, Clone, PartialEq)]
pub struct OpTok(pub Rc<String>);
#[derive(Debug, Clone, PartialEq)]
pub enum Kw {
If,
Else,
While,
Let,
Fn,
Null,
}
pub type TokenizeResult = Result<Vec<Token>, TokenError>;
fn is_digit(c: &char) -> bool {
c.is_digit(10)
}
pub fn tokenize(input: &str) -> TokenizeResult {
use self::Token::*;
let mut tokens = Vec::new();
let mut iter: Peekable<Chars> = input.chars().peekable();
while let Some(c) = iter.next() {
if c == '#' {
while let Some(c) = iter.next() {
if c == '\n' {
break;
}
}
continue;
}
let cur_tok = match c {
c if char::is_whitespace(c) && c != '\n' => continue,
'\n' => Newline,
';' => Semicolon,
'(' => LParen,
')' => RParen,
':' => Colon,
',' => Comma,
'{' => LCurlyBrace,
'}' => RCurlyBrace,
'[' => LSquareBracket,
']' => RSquareBracket,
'"' => tokenize_str(&mut iter)?,
c if !char::is_alphanumeric(c) => tokenize_operator(c, &mut iter)?,
c @ '.' | c if is_digit(&c) => tokenize_number_or_period(c, &mut iter)?,
c => tokenize_identifier(c, &mut iter)?,
};
tokens.push(cur_tok);
}
Ok(tokens)
}
fn tokenize_str(iter: &mut Peekable<Chars>) -> Result<Token, TokenError> {
let mut buffer = String::new();
loop {
// TODO handle string escapes, interpolation
match iter.next() {
Some(x) if x == '"' => break,
Some(x) => buffer.push(x),
None => return Err(TokenError::new("Unclosed quote")),
}
}
Ok(Token::StrLiteral(Rc::new(buffer)))
}
fn tokenize_operator(c: char, iter: &mut Peekable<Chars>) -> Result<Token, TokenError> {
let mut buffer = String::new();
buffer.push(c);
buffer.extend(iter.peeking_take_while(|x| !char::is_alphanumeric(*x) && !char::is_whitespace(*x)));
Ok(Token::Operator(OpTok(Rc::new(buffer))))
}
fn tokenize_number_or_period(c: char, iter: &mut Peekable<Chars>) -> Result<Token, TokenError> {
if c == '.' && !iter.peek().map_or(false, is_digit) {
return Ok(Token::Period);
}
let mut buffer = String::new();
buffer.push(c);
buffer.extend(iter.peeking_take_while(|x| is_digit(x) || *x == '.'));
match buffer.parse::<f64>() {
Ok(f) => Ok(Token::NumLiteral(f)),
Err(_) => Err(TokenError::new("Failed to parse digit")),
}
}
fn tokenize_identifier(c: char, iter: &mut Peekable<Chars>) -> Result<Token, TokenError> {
fn ends_identifier(c: &char) -> bool {
let c = *c;
char::is_whitespace(c) || is_digit(&c) || c == ';' || c == '(' || c == ')' ||
c == ',' || c == '.' || c == ',' || c == ':' || c == '[' || c == ']'
}
use self::Token::*;
let mut buffer = String::new();
buffer.push(c);
buffer.extend(iter.peeking_take_while(|x| !ends_identifier(x)));
Ok(match &buffer[..] {
"if" => Keyword(Kw::If),
"else" => Keyword(Kw::Else),
"while" => Keyword(Kw::While),
"let" => Keyword(Kw::Let),
"fn" => Keyword(Kw::Fn),
"null" => Keyword(Kw::Null),
b => Identifier(Rc::new(b.to_string())),
})
}
/*
#[cfg(test)]
mod tests {
use super::*;
use super::Token::*;
macro_rules! token_test {
($input: expr, $output: pat, $ifexpr: expr) => {
let tokens = tokenize($input).unwrap();
match tokens[..] {
$output if $ifexpr => (),
_ => panic!("Actual output: {:?}", tokens),
}
}
}
#[test]
fn basic_tokeniziation_tests() {
token_test!("let a = 3\n",
[Keyword(Kw::Let), Identifier(ref a), Operator(OpTok(ref b)), NumLiteral(3.0), Newline],
**a == "a" && **b == "=");
token_test!("2+1",
[NumLiteral(2.0), Operator(OpTok(ref a)), NumLiteral(1.0)],
**a == "+");
token_test!("2 + 1",
[NumLiteral(2.0), Operator(OpTok(ref a)), NumLiteral(1.0)],
**a == "+");
token_test!("2.3*49.2",
[NumLiteral(2.3), Operator(OpTok(ref a)), NumLiteral(49.2)],
**a == "*");
token_test!("a+3",
[Identifier(ref a), NumLiteral(3.0)],
**a == "a+");
assert!(tokenize("2.4.5").is_err());
token_test!("fn my_func(a) { a ? 3[1] }",
[Keyword(Kw::Fn), Identifier(ref a), LParen, Identifier(ref b), RParen, LCurlyBrace, Identifier(ref c),
Operator(OpTok(ref d)), NumLiteral(3.0), LSquareBracket, NumLiteral(1.0), RSquareBracket, RCurlyBrace],
**a == "my_func" && **b == "a" && **c == "a" && **d == "?");
}
#[test]
fn string_test() {
token_test!("null + \"a string\"",
[Keyword(Kw::Null), Operator(OpTok(ref a)), StrLiteral(ref b)],
**a == "+" && **b == "a string");
token_test!("\"{?'q@?\"",
[StrLiteral(ref a)],
**a == "{?'q@?");
}
#[test]
fn operator_test() {
token_test!("a *> b",
[Identifier(ref a), Operator(OpTok(ref b)), Identifier(ref c)],
**a == "a" && **b == "*>" && **c == "b");
}
}
*/

View File

@ -1,11 +0,0 @@
[package]
name = "robo-lang"
version = "0.1.0"
authors = ["greg <greg.shuflin@protonmail.com>"]
[dependencies]
itertools = "0.5.8"
take_mut = "0.1.3"
llvm-sys = "*"
schala-repl = { path = "../schala-repl" }

View File

@ -1,158 +0,0 @@
#![feature(box_patterns)]
extern crate itertools;
extern crate schala_repl;
use itertools::Itertools;
use schala_repl::{ProgrammingLanguageInterface, EvalOptions};
pub struct Robo {
}
impl Robo {
pub fn new() -> Robo {
Robo { }
}
}
#[derive(Debug)]
pub struct TokenError {
pub msg: String,
}
impl TokenError {
pub fn new(msg: &str) -> TokenError {
TokenError { msg: msg.to_string() }
}
}
#[allow(dead_code)]
#[derive(Debug)]
pub enum Token {
StrLiteral(String),
Backtick,
Newline,
LParen,
RParen,
LBracket,
RBracket,
LBrace,
RBrace,
Period,
Comma,
Colon,
Semicolon,
SingleQuote,
Identifier(String),
Operator(String),
NumLiteral(Number),
}
#[allow(dead_code)]
#[derive(Debug)]
pub enum Number {
IntegerRep(String),
FloatRep(String)
}
#[allow(dead_code)]
pub type AST = Vec<ASTNode>;
#[allow(dead_code)]
#[derive(Debug)]
pub enum ASTNode {
FunctionDefinition(String, Expression),
ImportStatement(String),
}
#[allow(dead_code)]
#[derive(Debug)]
pub enum Expression {
}
fn tokenize(input: &str) -> Result<Vec<Token>, TokenError> {
use self::Token::*;
let mut tokens = Vec::new();
let mut iter = input.chars().peekable();
while let Some(c) = iter.next() {
if c == ';' {
while let Some(c) = iter.next() {
if c == '\n' {
break;
}
}
continue;
}
let cur_tok = match c {
c if char::is_whitespace(c) && c != '\n' => continue,
'\n' => Newline,
'(' => LParen,
')' => RParen,
'[' => LBracket,
']' => RBracket,
'{' => LBrace,
'}' => RBrace,
',' => Comma,
':' => Colon,
';' => Semicolon,
'.' => Period,
'`' => Backtick,
'\'' => SingleQuote,
'"' => {
let mut buffer = String::new();
loop {
match iter.next() {
Some(x) if x == '"' => break,
Some(x) => buffer.push(x),
None => return Err(TokenError::new("Unclosed quote")),
}
}
StrLiteral(buffer)
}
c if c.is_digit(10) => {
let mut integer = true;
let mut buffer = String::new();
buffer.push(c);
buffer.extend(iter.peeking_take_while(|x| x.is_digit(10)));
if let Some(&'.') = iter.peek() {
buffer.push(iter.next().unwrap());
integer = false;
}
buffer.extend(iter.peeking_take_while(|x| x.is_digit(10)));
let inner = if integer {
Number::IntegerRep(buffer)
} else {
Number::FloatRep(buffer)
};
NumLiteral(inner)
},
c if char::is_alphanumeric(c) => {
let mut buffer = String::new();
buffer.push(c);
buffer.extend(iter.peeking_take_while(|x| char::is_alphanumeric(*x)));
Identifier(buffer)
},
c => {
let mut buffer = String::new();
buffer.push(c);
buffer.extend(iter.peeking_take_while(|x| !char::is_whitespace(*x)));
Operator(buffer)
}
};
tokens.push(cur_tok);
}
Ok(tokens)
}
impl ProgrammingLanguageInterface for Robo {
fn get_language_name(&self) -> String {
"Robo".to_string()
}
fn get_source_file_suffix(&self) -> String {
format!("robo")
}
}

View File

@ -1,11 +0,0 @@
[package]
name = "rukka-lang"
version = "0.1.0"
authors = ["greg <greg.shuflin@protonmail.com>"]
[dependencies]
itertools = "0.5.8"
take_mut = "0.1.3"
llvm-sys = "*"
schala-repl = { path = "../schala-repl" }

View File

@ -1,417 +0,0 @@
#![feature(box_patterns)]
extern crate itertools;
extern crate schala_repl;
use itertools::Itertools;
use schala_repl::{ProgrammingLanguageInterface, EvalOptions};
use std::iter::Peekable;
use std::vec::IntoIter;
use std::str::Chars;
use std::collections::HashMap;
pub struct EvaluatorState {
binding_stack: Vec<HashMap<String, Sexp>>
}
impl EvaluatorState {
fn new() -> EvaluatorState {
use self::Sexp::Primitive;
use self::PrimitiveFn::*;
let mut default_map = HashMap::new();
default_map.insert(format!("+"), Primitive(Plus));
default_map.insert(format!("-"), Primitive(Minus));
default_map.insert(format!("*"), Primitive(Mult));
default_map.insert(format!("/"), Primitive(Div));
default_map.insert(format!("%"), Primitive(Mod));
default_map.insert(format!(">"), Primitive(Greater));
default_map.insert(format!("<"), Primitive(Less));
default_map.insert(format!("<="), Primitive(LessThanOrEqual));
default_map.insert(format!(">="), Primitive(GreaterThanOrEqual));
default_map.insert(format!("display"), Primitive(Display));
EvaluatorState {
binding_stack: vec![default_map],
}
}
fn set_var(&mut self, var: String, value: Sexp) {
let binding = self.binding_stack.last_mut().unwrap();
binding.insert(var, value);
}
fn get_var(&self, var: &str) -> Option<&Sexp> {
for bindings in self.binding_stack.iter().rev() {
match bindings.get(var) {
Some(x) => return Some(x),
None => (),
}
}
None
}
fn push_env(&mut self) {
self.binding_stack.push(HashMap::new());
}
fn pop_env(&mut self) {
self.binding_stack.pop();
}
}
pub struct Rukka {
state: EvaluatorState
}
impl Rukka {
pub fn new() -> Rukka { Rukka { state: EvaluatorState::new() } }
}
impl ProgrammingLanguageInterface for Rukka {
fn get_language_name(&self) -> String {
"Rukka".to_string()
}
fn get_source_file_suffix(&self) -> String {
format!("rukka")
}
}
impl EvaluatorState {
fn eval(&mut self, expr: Sexp) -> Result<Sexp, String> {
use self::Sexp::*;
Ok(match expr {
SymbolAtom(ref sym) => match self.get_var(sym) {
Some(ref sexp) => {
let q: &Sexp = sexp; //WTF? if I delete this line, the copy doesn't work??
q.clone() //TODO make this not involve a clone
},
None => return Err(format!("Variable {} not bound", sym)),
},
expr @ Primitive(_) => expr,
expr @ FnLiteral { .. } => expr,
expr @ StringAtom(_) => expr,
expr @ NumberAtom(_) => expr,
expr @ BoolAtom(_) => expr,
Cons(box operator, box operands) => match operator {
SymbolAtom(ref sym) if match &sym[..] {
"quote" | "eq?" | "cons" | "car" | "cdr" | "atom?" | "define" | "lambda" | "if" | "cond" => true, _ => false
} => self.eval_special_form(sym, operands)?,
_ => {
let evaled = self.eval(operator)?;
self.apply(evaled, operands)?
}
},
Nil => Nil,
})
}
fn eval_special_form(&mut self, form: &str, operands: Sexp) -> Result<Sexp, String> {
use self::Sexp::*;
Ok(match form {
"quote" => match operands {
Cons(box quoted, box Nil) => quoted,
_ => return Err(format!("Bad syntax in quote")),
},
"eq?" => match operands {//TODO make correct
Cons(box lhs, box Cons(box rhs, _)) => BoolAtom(lhs == rhs),
_ => BoolAtom(true),
},
"cons" => match operands {
Cons(box cadr, box Cons(box caddr, box Nil)) => {
let newl = self.eval(cadr)?;
let newr = self.eval(caddr)?;
Cons(Box::new(newl), Box::new(newr))
},
_ => return Err(format!("Bad arguments for cons")),
},
"car" => match operands {
Cons(box car, _) => car,
_ => return Err(format!("called car with a non-pair argument")),
},
"cdr" => match operands {
Cons(_, box cdr) => cdr,
_ => return Err(format!("called cdr with a non-pair argument")),
},
"atom?" => match operands {
Cons(_, _) => BoolAtom(false),
_ => BoolAtom(true),
},
"define" => match operands {
Cons(box SymbolAtom(sym), box Cons(box expr, box Nil)) => {
let evaluated = self.eval(expr)?;
self.set_var(sym, evaluated);
Nil
},
_ => return Err(format!("Bad assignment")),
}
"lambda" => match operands {
Cons(box mut paramlist, box Cons(box formalexp, box Nil)) => {
let mut formal_params = vec![];
{
let mut ptr = &paramlist;
loop {
match ptr {
&Cons(ref arg, ref rest) => {
if let SymbolAtom(ref sym) = **arg {
formal_params.push(sym.clone());
ptr = rest;
} else {
return Err(format!("Bad lambda format"));
}
},
_ => break,
}
}
}
FnLiteral {
formal_params,
body: Box::new(formalexp)
}
},
_ => return Err(format!("Bad lambda expression")),
},
"if" => match operands {
Cons(box test, box body) => {
let truth_value = test.truthy();
match (truth_value, body) {
(true, Cons(box consequent, _)) => consequent,
(false, Cons(_, box Cons(box alternative, _))) => alternative,
_ => return Err(format!("Bad if expression"))
}
},
_ => return Err(format!("Bad if expression"))
},
s => return Err(format!("Non-existent special form {}; this should never happen", s)),
})
}
fn apply(&mut self, function: Sexp, operands: Sexp) -> Result<Sexp, String> {
use self::Sexp::*;
match function {
FnLiteral { formal_params, body } => {
self.push_env();
let mut cur = operands;
for param in formal_params {
match cur {
Cons(box arg, box rest) => {
cur = rest;
self.set_var(param, arg);
},
_ => return Err(format!("Bad argument for function application")),
}
}
let result = self.eval(*body);
self.pop_env();
result
},
Primitive(prim) => {
let mut evaled_operands = Vec::new();
let mut cur_operand = operands;
loop {
match cur_operand {
Nil => break,
Cons(box l, box rest) => {
evaled_operands.push(self.eval(l)?);
cur_operand = rest;
},
_ => return Err(format!("Bad operands list"))
}
}
prim.apply(evaled_operands)
}
_ => return Err(format!("Bad type to apply")),
}
}
}
fn read(input: &str) -> Result<Vec<Sexp>, String> {
let mut chars: Peekable<Chars> = input.chars().peekable();
let mut tokens = tokenize(&mut chars).into_iter().peekable();
let mut sexps = Vec::new();
while let Some(_) = tokens.peek() {
sexps.push(parse(&mut tokens)?);
}
Ok(sexps)
}
#[derive(Debug)]
enum Token {
LParen,
RParen,
Quote,
Word(String),
StringLiteral(String),
NumLiteral(u64),
}
//TODO make this notion of Eq more sophisticated
#[derive(Debug, PartialEq, Clone)]
enum Sexp {
SymbolAtom(String),
StringAtom(String),
NumberAtom(u64),
BoolAtom(bool),
Cons(Box<Sexp>, Box<Sexp>),
Nil,
FnLiteral {
formal_params: Vec<String>,
body: Box<Sexp>
},
Primitive(PrimitiveFn)
}
#[derive(Debug, PartialEq, Clone)]
enum PrimitiveFn {
Plus, Minus, Mult, Div, Mod, Greater, Less, GreaterThanOrEqual, LessThanOrEqual, Display
}
impl PrimitiveFn {
fn apply(&self, evaled_operands: Vec<Sexp>) -> Result<Sexp, String> {
use self::Sexp::*;
use self::PrimitiveFn::*;
let op = self.clone();
Ok(match op {
Display => {
for arg in evaled_operands {
print!("{}\n", arg.print());
}
Nil
},
Plus | Mult => {
let mut result = match op { Plus => 0, Mult => 1, _ => unreachable!() };
for arg in evaled_operands {
if let NumberAtom(n) = arg {
if let Plus = op {
result += n;
} else if let Mult = op {
result *= n;
}
} else {
return Err(format!("Bad operand: {:?}", arg));
}
}
NumberAtom(result)
},
op => return Err(format!("Primitive op {:?} not implemented", op)),
})
}
}
impl Sexp {
fn print(&self) -> String {
use self::Sexp::*;
match self {
&BoolAtom(true) => format!("#t"),
&BoolAtom(false) => format!("#f"),
&SymbolAtom(ref sym) => format!("{}", sym),
&StringAtom(ref s) => format!("\"{}\"", s),
&NumberAtom(ref n) => format!("{}", n),
&Cons(ref car, ref cdr) => format!("({} . {})", car.print(), cdr.print()),
&Nil => format!("()"),
&FnLiteral { ref formal_params, .. } => format!("<lambda {:?}>", formal_params),
&Primitive(ref sym) => format!("<primitive \"{:?}\">", sym),
}
}
fn truthy(&self) -> bool {
use self::Sexp::*;
match self {
&BoolAtom(false) => false,
_ => true
}
}
}
fn tokenize(input: &mut Peekable<Chars>) -> Vec<Token> {
use self::Token::*;
let mut tokens = Vec::new();
loop {
match input.next() {
None => break,
Some('(') => tokens.push(LParen),
Some(')') => tokens.push(RParen),
Some('\'') => tokens.push(Quote),
Some(c) if c.is_whitespace() => continue,
Some(c) if c.is_numeric() => {
let tok: String = input.peeking_take_while(|next| next.is_numeric()).collect();
let n: u64 = format!("{}{}", c, tok).parse().unwrap();
tokens.push(NumLiteral(n));
},
Some('"') => {
let string: String = input.scan(false, |escape, cur_char| {
let seen_escape = *escape;
*escape = cur_char == '\\' && !seen_escape;
match (cur_char, seen_escape) {
('"', false) => None,
('\\', false) => Some(None),
(c, _) => Some(Some(c))
}
}).filter_map(|x| x).collect();
tokens.push(StringLiteral(string));
}
Some(c) => {
let sym: String = input.peeking_take_while(|next| {
match *next {
'(' | ')' => false,
c if c.is_whitespace() => false,
_ => true
}
}).collect();
tokens.push(Word(format!("{}{}", c, sym)));
}
}
}
tokens
}
fn parse(tokens: &mut Peekable<IntoIter<Token>>) -> Result<Sexp, String> {
use self::Token::*;
use self::Sexp::*;
match tokens.next() {
Some(Word(ref s)) if s == "#f" => Ok(BoolAtom(false)),
Some(Word(ref s)) if s == "#t" => Ok(BoolAtom(true)),
Some(Word(s)) => Ok(SymbolAtom(s)),
Some(StringLiteral(s)) => Ok(StringAtom(s)),
Some(LParen) => parse_sexp(tokens),
Some(RParen) => Err(format!("Unexpected ')'")),
Some(Quote) => {
let quoted = parse(tokens)?;
Ok(Cons(Box::new(SymbolAtom(format!("quote"))), Box::new(Cons(Box::new(quoted), Box::new(Nil)))))
},
Some(NumLiteral(n)) => Ok(NumberAtom(n)),
None => Err(format!("Unexpected end of input")),
}
}
fn parse_sexp(tokens: &mut Peekable<IntoIter<Token>>) -> Result<Sexp, String> {
use self::Token::*;
use self::Sexp::*;
let mut cell = Nil;
{
let mut cell_ptr = &mut cell;
loop {
match tokens.peek() {
None => return Err(format!("Unexpected end of input")),
Some(&RParen) => {
tokens.next();
break;
},
_ => {
let current = parse(tokens)?;
let new_cdr = Cons(Box::new(current), Box::new(Nil));
match cell_ptr {
&mut Cons(_, ref mut cdr) => **cdr = new_cdr,
&mut Nil => *cell_ptr = new_cdr,
_ => unreachable!()
};
let old_ptr = cell_ptr;
let new_ptr: &mut Sexp = match old_ptr { &mut Cons(_, ref mut cdr) => cdr, _ => unreachable!() } as &mut Sexp;
cell_ptr = new_ptr;
}
}
}
}
Ok(cell)
}

View File

@ -1,2 +0,0 @@
[toolchain]
channel = "nightly"

View File

@ -1,8 +0,0 @@
max_width = 110
use_small_heuristics = "max"
imports_indent = "block"
imports_granularity = "crate"
group_imports = "stdexternalcrate"
match_arm_blocks = false
where_single_line = true

View File

@ -1,27 +0,0 @@
[package]
name = "schala-lang"
version = "0.1.0"
authors = ["greg <greg.shuflin@protonmail.com>"]
edition = "2021"
[dependencies]
itertools = "0.10"
take_mut = "0.2.2"
failure = "0.1.5"
ena = "0.11.0"
stopwatch = "0.0.7"
derivative = "2.2.0"
colored = "1.8"
radix_trie = "0.1.5"
assert_matches = "1.5"
#peg = "0.7.0"
peg = "0.8.1"
nom = "7.1.0"
nom_locate = "4.0.0"
schala-repl = { path = "../schala-repl" }
[dev-dependencies]
test-case = "1.2.0"
pretty_assertions = "1.0.0"

View File

@ -1,22 +0,0 @@
let _SCHALA_VERSION = "0.1.0"
type Option<T> = Some(T) | None
type Ord = LT | EQ | GT
@register_builtin(print)
fn print(arg) { }
@register_builtin(println)
fn println(arg) { }
@register_builtin(getline)
fn getline(arg) { }
fn map(input: Option<T>, func: Func): Option<T> {
if input {
is Option::Some(x) then Option::Some(func(x))
is Option::None then Option::None
}
}
type Complicated = Sunrise | Metal { black: bool, norwegian: bool } | Fella(String, Int)

View File

@ -1,345 +0,0 @@
#![allow(clippy::upper_case_acronyms)]
#![allow(clippy::enum_variant_names)]
use std::{
convert::{AsRef, From},
fmt,
rc::Rc,
};
mod operators;
mod visitor;
mod visualize;
pub use operators::{BinOp, PrefixOp};
pub use visitor::*;
use crate::{
derivative::Derivative,
identifier::{define_id_kind, Id},
parsing::Location,
util::delim_wrapped,
};
define_id_kind!(ASTItem);
pub type ItemId = Id<ASTItem>;
#[derive(Derivative, Debug)]
#[derivative(PartialEq)]
pub struct AST {
#[derivative(PartialEq = "ignore")]
pub id: ItemId,
pub statements: Block,
}
impl fmt::Display for AST {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
write!(f, "{}", visualize::render_ast(self))
}
}
#[derive(Derivative, Debug, Clone)]
#[derivative(PartialEq)]
pub struct Statement<K> {
#[derivative(PartialEq = "ignore")]
pub id: ItemId,
#[derivative(PartialEq = "ignore")]
pub location: Location,
pub kind: K,
}
#[derive(Debug, PartialEq, Clone)]
pub enum StatementKind {
Expression(Expression),
Declaration(Declaration),
Import(ImportSpecifier),
Flow(FlowControl),
}
#[derive(Debug, Clone, PartialEq)]
pub enum FlowControl {
Continue,
Break,
Return(Option<Expression>),
}
#[derive(Debug, Clone, PartialEq, Default)]
pub struct Block {
pub statements: Vec<Statement<StatementKind>>,
}
impl From<Vec<Statement<StatementKind>>> for Block {
fn from(statements: Vec<Statement<StatementKind>>) -> Self {
Self { statements }
}
}
impl From<Statement<StatementKind>> for Block {
fn from(statement: Statement<StatementKind>) -> Self {
Self { statements: vec![statement] }
}
}
impl AsRef<[Statement<StatementKind>]> for Block {
fn as_ref(&self) -> &[Statement<StatementKind>] {
self.statements.as_ref()
}
}
pub type ParamName = Rc<String>;
#[derive(Debug, Derivative, Clone)]
#[derivative(PartialEq)]
pub struct QualifiedName {
#[derivative(PartialEq = "ignore")]
pub id: ItemId,
pub components: Vec<Rc<String>>,
}
impl fmt::Display for QualifiedName {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
match &self.components[..] {
[] => write!(f, "[<empty>]"),
[name] => write!(f, "{}", name),
[name, rest @ ..] => {
write!(f, "{}", name)?;
for c in rest {
write!(f, "::{}", c)?;
}
Ok(())
}
}
}
}
#[derive(Debug, PartialEq, Clone)]
pub struct FormalParam {
pub name: ParamName,
pub default: Option<Expression>,
pub anno: Option<TypeIdentifier>,
}
#[derive(Debug, PartialEq, Clone)]
pub enum Declaration {
FuncSig(Signature),
FuncDecl(Signature, Block),
TypeDecl {
name: TypeSingletonName,
body: TypeBody,
mutable: bool,
},
//TODO TypeAlias `original` needs to be a more complex type definition
TypeAlias {
alias: Rc<String>,
original: Rc<String>,
},
Binding {
name: Rc<String>,
constant: bool,
type_anno: Option<TypeIdentifier>,
expr: Expression,
},
Impl {
type_name: TypeIdentifier,
interface_name: Option<TypeSingletonName>,
block: Vec<Statement<Declaration>>,
},
Interface {
name: Rc<String>,
signatures: Vec<Signature>,
},
//TODO need to limit the types of statements that can be annotated
Annotation {
name: Rc<String>,
arguments: Vec<Expression>,
inner: Box<Statement<StatementKind>>,
},
Module {
name: Rc<String>,
items: Block,
},
}
#[derive(Debug, PartialEq, Clone)]
pub struct Signature {
pub name: Rc<String>,
pub operator: bool,
pub params: Vec<FormalParam>,
pub type_anno: Option<TypeIdentifier>,
}
//TODO I can probably get rid of TypeBody
#[derive(Debug, Derivative, Clone)]
#[derivative(PartialEq)]
pub enum TypeBody {
Variants(Vec<Variant>),
ImmediateRecord {
#[derivative(PartialEq = "ignore")]
id: ItemId,
fields: Vec<(Rc<String>, TypeIdentifier)>,
},
}
#[derive(Debug, Derivative, Clone)]
#[derivative(PartialEq)]
pub struct Variant {
#[derivative(PartialEq = "ignore")]
pub id: ItemId,
pub name: Rc<String>,
pub kind: VariantKind,
}
#[derive(Debug, PartialEq, Clone)]
pub enum VariantKind {
UnitStruct,
TupleStruct(Vec<TypeIdentifier>),
Record(Vec<(Rc<String>, TypeIdentifier)>),
}
#[derive(Debug, Derivative, Clone)]
#[derivative(PartialEq)]
pub struct Expression {
#[derivative(PartialEq = "ignore")]
pub id: ItemId,
pub kind: ExpressionKind,
//TODO this should only allow singletons, not tuples
pub type_anno: Option<TypeIdentifier>,
}
impl Expression {
pub fn new(id: ItemId, kind: ExpressionKind) -> Expression {
Expression { id, kind, type_anno: None }
}
}
#[derive(Debug, PartialEq, Clone)]
pub enum TypeIdentifier {
Tuple(Vec<TypeIdentifier>),
Singleton(TypeSingletonName),
}
impl fmt::Display for TypeIdentifier {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
match self {
TypeIdentifier::Tuple(items) =>
write!(f, "{}", delim_wrapped('(', ')', items.iter().map(|item| item.to_string()))),
TypeIdentifier::Singleton(tsn) => {
write!(f, "{}", tsn.name)?;
if !tsn.params.is_empty() {
write!(f, "{}", delim_wrapped('<', '>', tsn.params.iter().map(|item| item.to_string())))?;
}
Ok(())
}
}
}
}
#[derive(Debug, PartialEq, Clone)]
pub struct TypeSingletonName {
pub name: Rc<String>,
pub params: Vec<TypeIdentifier>,
}
#[derive(Debug, PartialEq, Clone)]
pub enum ExpressionKind {
NatLiteral(u64),
FloatLiteral(f64),
StringLiteral { prefix: Option<Rc<String>>, s: Rc<String> },
BoolLiteral(bool),
BinExp(BinOp, Box<Expression>, Box<Expression>),
PrefixExp(PrefixOp, Box<Expression>),
TupleLiteral(Vec<Expression>),
Value(QualifiedName),
SelfValue,
NamedStruct { name: QualifiedName, fields: Vec<(Rc<String>, Expression)> },
Call { f: Box<Expression>, arguments: Vec<InvocationArgument> },
Index { indexee: Box<Expression>, indexers: Vec<Expression> },
IfExpression { discriminator: Option<Box<Expression>>, 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 },
Access { name: Rc<String>, expr: Box<Expression> },
ListLiteral(Vec<Expression>),
}
#[derive(Debug, PartialEq, Clone)]
pub enum InvocationArgument {
Positional(Expression),
Keyword { name: Rc<String>, expr: Expression },
Ignored,
}
#[derive(Debug, PartialEq, Clone)]
pub enum IfExpressionBody {
SimpleConditional { then_case: Block, else_case: Option<Block> },
SimplePatternMatch { pattern: Pattern, then_case: Block, else_case: Option<Block> },
CondList(Vec<ConditionArm>),
}
#[derive(Debug, PartialEq, Clone)]
pub struct ConditionArm {
pub condition: Condition,
pub guard: Option<Expression>,
pub body: Block,
}
#[derive(Debug, PartialEq, Clone)]
pub enum Condition {
Pattern(Pattern),
TruncatedOp(BinOp, Expression),
//Expression(Expression), //I'm pretty sure I don't actually want this
Else,
}
#[derive(Debug, PartialEq, Clone)]
pub enum Pattern {
Ignored,
TuplePattern(Vec<Pattern>),
Literal(PatternLiteral),
TupleStruct(QualifiedName, Vec<Pattern>),
Record(QualifiedName, Vec<(Rc<String>, Pattern)>),
VarOrName(QualifiedName),
}
#[derive(Debug, PartialEq, Clone)]
pub enum PatternLiteral {
NumPattern { neg: bool, num: ExpressionKind },
StringPattern(Rc<String>),
BoolPattern(bool),
}
#[derive(Debug, PartialEq, Clone)]
pub struct Enumerator {
pub identifier: Rc<String>,
pub generator: Expression,
pub assignment: bool, //true if `=`, false if `<-`
}
#[derive(Debug, PartialEq, Clone)]
pub enum ForBody {
MonadicReturn(Expression),
StatementBlock(Block),
}
#[derive(Debug, Derivative, Clone)]
#[derivative(PartialEq)]
pub struct ImportSpecifier {
#[derivative(PartialEq = "ignore")]
pub id: ItemId,
pub path_components: Vec<Rc<String>>,
pub imported_names: ImportedNames,
}
#[derive(Debug, PartialEq, Clone)]
pub enum ImportedNames {
All,
LastOfPath,
List(Vec<Rc<String>>),
}
#[derive(Debug, PartialEq, Clone)]
pub struct ModuleSpecifier {
pub name: Rc<String>,
pub contents: Block,
}

View File

@ -1,61 +0,0 @@
use std::rc::Rc;
#[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) -> &str {
&self.sigil
}
}
#[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) -> &str {
&self.sigil
}
pub fn min_precedence() -> i32 {
i32::min_value()
}
pub fn get_precedence(&self) -> i32 {
binop_precedences(self.sigil.as_ref())
}
}
fn binop_precedences(s: &str) -> i32 {
let default = 10_000_000;
match s {
"+" => 10,
"-" => 10,
"*" => 20,
"/" => 20,
"%" => 20,
"++" => 30,
"^" => 30,
"&" => 20,
"|" => 20,
">" => 20,
">=" => 20,
"<" => 20,
"<=" => 20,
"==" => 40,
"<=>" => 30,
"=" => 5, // Assignment shoudl have highest precedence
_ => default,
}
}

View File

@ -1,202 +0,0 @@
use crate::ast::*;
#[derive(Debug)]
pub enum Recursion {
Continue,
Stop,
}
pub trait ASTVisitor: Sized {
fn expression(&mut self, _expression: &Expression) -> Recursion {
Recursion::Continue
}
fn declaration(&mut self, _declaration: &Declaration, _id: &ItemId) -> Recursion {
Recursion::Continue
}
fn import(&mut self, _import: &ImportSpecifier) -> Recursion {
Recursion::Continue
}
fn pattern(&mut self, _pat: &Pattern) -> Recursion {
Recursion::Continue
}
}
pub fn walk_ast<V: ASTVisitor>(v: &mut V, ast: &AST) {
walk_block(v, &ast.statements);
}
pub fn walk_block<V: ASTVisitor>(v: &mut V, block: &Block) {
use StatementKind::*;
for statement in block.statements.iter() {
match statement.kind {
StatementKind::Expression(ref expr) => {
walk_expression(v, expr);
}
Declaration(ref decl) => {
walk_declaration(v, decl, &statement.id);
}
Import(ref import_spec) => {
v.import(import_spec);
}
Flow(ref flow_control) =>
if let FlowControl::Return(Some(ref retval)) = flow_control {
walk_expression(v, retval);
},
}
}
}
pub fn walk_declaration<V: ASTVisitor>(v: &mut V, decl: &Declaration, id: &ItemId) {
use Declaration::*;
if let Recursion::Continue = v.declaration(decl, id) {
match decl {
FuncDecl(_sig, block) => {
walk_block(v, block);
}
Binding { name: _, constant: _, type_anno: _, expr } => {
walk_expression(v, expr);
}
Module { name: _, items } => {
walk_block(v, items);
}
_ => (),
};
}
}
pub fn walk_expression<V: ASTVisitor>(v: &mut V, expr: &Expression) {
use ExpressionKind::*;
if let Recursion::Continue = v.expression(expr) {
match &expr.kind {
NatLiteral(_)
| FloatLiteral(_)
| StringLiteral { .. }
| BoolLiteral(_)
| Value(_)
| SelfValue => (),
BinExp(_, lhs, rhs) => {
walk_expression(v, lhs);
walk_expression(v, rhs);
}
PrefixExp(_, arg) => {
walk_expression(v, arg);
}
TupleLiteral(exprs) =>
for expr in exprs {
walk_expression(v, expr);
},
NamedStruct { name: _, fields } =>
for (_, expr) in fields.iter() {
walk_expression(v, expr);
},
Call { f, arguments } => {
walk_expression(v, f);
for arg in arguments.iter() {
match arg {
InvocationArgument::Positional(expr) | InvocationArgument::Keyword { expr, .. } =>
walk_expression(v, expr),
_ => (),
}
}
}
Index { indexee, indexers } => {
walk_expression(v, indexee);
for indexer in indexers.iter() {
walk_expression(v, indexer);
}
}
IfExpression { discriminator, body } => {
if let Some(d) = discriminator.as_ref() {
walk_expression(v, d);
}
walk_if_expr_body(v, body.as_ref());
}
WhileExpression { condition, body } => {
if let Some(d) = condition.as_ref() {
walk_expression(v, d);
}
walk_block(v, body);
}
ForExpression { enumerators, body } => {
for enumerator in enumerators {
walk_expression(v, &enumerator.generator);
}
match body.as_ref() {
ForBody::MonadicReturn(expr) => walk_expression(v, expr),
ForBody::StatementBlock(block) => walk_block(v, block),
};
}
Lambda { params: _, type_anno: _, body } => {
walk_block(v, body);
}
Access { name: _, expr } => {
walk_expression(v, expr);
}
ListLiteral(exprs) =>
for expr in exprs {
walk_expression(v, expr);
},
};
}
}
pub fn walk_if_expr_body<V: ASTVisitor>(v: &mut V, body: &IfExpressionBody) {
use IfExpressionBody::*;
match body {
SimpleConditional { then_case, else_case } => {
walk_block(v, then_case);
if let Some(block) = else_case.as_ref() {
walk_block(v, block)
}
}
SimplePatternMatch { pattern, then_case, else_case } => {
walk_pattern(v, pattern);
walk_block(v, then_case);
if let Some(block) = else_case.as_ref() {
walk_block(v, block)
}
}
CondList(arms) =>
for arm in arms {
match arm.condition {
Condition::Pattern(ref pat) => {
walk_pattern(v, pat);
}
Condition::TruncatedOp(ref _binop, ref expr) => {
walk_expression(v, expr);
}
Condition::Else => (),
}
if let Some(ref guard) = arm.guard {
walk_expression(v, guard);
}
walk_block(v, &arm.body);
},
}
}
pub fn walk_pattern<V: ASTVisitor>(v: &mut V, pat: &Pattern) {
use Pattern::*;
if let Recursion::Continue = v.pattern(pat) {
match pat {
TuplePattern(patterns) =>
for pat in patterns {
walk_pattern(v, pat);
},
TupleStruct(_, patterns) =>
for pat in patterns {
walk_pattern(v, pat);
},
Record(_, name_and_patterns) =>
for (_, pat) in name_and_patterns {
walk_pattern(v, pat);
},
_ => (),
};
}
}

View File

@ -1,282 +0,0 @@
#![allow(clippy::single_char_add_str)]
use std::fmt::Write;
use super::{
Block, Declaration, Expression, ExpressionKind, FlowControl, ImportSpecifier, InvocationArgument,
Signature, Statement, StatementKind, AST,
};
const LEVEL: usize = 2;
fn do_indent(n: usize, buf: &mut String) {
for _ in 0..n {
buf.push(' ');
}
}
fn newline(buf: &mut String) {
buf.push('\n');
}
pub(super) fn render_ast(ast: &AST) -> String {
let AST { statements, .. } = ast;
let mut buf = "(AST\n".to_string();
render_block(statements, LEVEL, &mut buf);
buf.push(')');
buf
}
fn render_statement(stmt: &Statement<StatementKind>, indent: usize, buf: &mut String) {
use StatementKind::*;
do_indent(indent, buf);
match stmt.kind {
Expression(ref expr) => render_expression(expr, indent, buf),
Declaration(ref decl) => render_declaration(decl, indent, buf),
Import(ref spec) => render_import(spec, indent, buf),
Flow(ref flow_control) => render_flow_control(flow_control, indent, buf),
}
}
fn render_expression(expr: &Expression, indent: usize, buf: &mut String) {
use ExpressionKind::*;
buf.push_str("(Expr ");
match &expr.kind {
SelfValue => write!(buf, "(SelfValue)").unwrap(),
NatLiteral(n) => buf.push_str(&format!("(NatLiteral {})", n)),
FloatLiteral(f) => buf.push_str(&format!("(FloatLiteral {})", f)),
StringLiteral { s, prefix } => buf.push_str(&format!("(StringLiteral prefix: {:?} {})", prefix, s)),
BoolLiteral(b) => buf.push_str(&format!("(BoolLiteral {})", b)),
BinExp(binop, lhs, rhs) => {
let new_indent = indent + LEVEL;
buf.push_str(&format!("Binop {}\n", binop.sigil()));
do_indent(new_indent, buf);
render_expression(lhs, new_indent, buf);
newline(buf);
do_indent(new_indent, buf);
render_expression(rhs, new_indent, buf);
newline(buf);
do_indent(indent, buf);
}
PrefixExp(prefix, expr) => {
let new_indent = indent + LEVEL;
buf.push_str(&format!("PrefixOp {}\n", prefix.sigil()));
do_indent(new_indent, buf);
render_expression(expr, new_indent, buf);
newline(buf);
do_indent(indent, buf);
}
TupleLiteral(..) => (),
Value(name) => {
buf.push_str(&format!("Value {})", name));
}
NamedStruct { name: _, fields: _ } => (),
Call { f, arguments } => {
let new_indent = indent + LEVEL;
buf.push_str("Call ");
render_expression(f, new_indent, buf);
newline(buf);
for arg in arguments {
do_indent(new_indent, buf);
match arg {
InvocationArgument::Positional(expr) => render_expression(expr, new_indent, buf),
InvocationArgument::Keyword { .. } => buf.push_str("<keyword>"),
InvocationArgument::Ignored => buf.push_str("<ignored>"),
}
newline(buf);
do_indent(indent, buf);
}
}
Index { .. } => buf.push_str("<index>"),
IfExpression { .. } => buf.push_str("<if-expr>"),
WhileExpression { .. } => buf.push_str("<while-expr>"),
ForExpression { .. } => buf.push_str("<for-expr>"),
Lambda { params, type_anno: _, body } => {
let new_indent = indent + LEVEL;
buf.push_str("Lambda ");
newline(buf);
do_indent(new_indent, buf);
buf.push_str("(Args ");
for p in params {
buf.push_str(&format!("{} ", p.name));
}
buf.push(')');
newline(buf);
do_indent(new_indent, buf);
buf.push_str("(Body ");
newline(buf);
render_block(body, new_indent + LEVEL, buf);
do_indent(new_indent, buf);
buf.push(')');
newline(buf);
do_indent(indent, buf);
}
Access { .. } => buf.push_str("<access-expr>"),
ListLiteral(..) => buf.push_str("<list-literal>"),
}
buf.push(')');
}
fn render_declaration(decl: &Declaration, indent: usize, buf: &mut String) {
use Declaration::*;
buf.push_str("(Decl ");
match decl {
FuncSig(ref sig) => render_signature(sig, indent, buf),
FuncDecl(ref sig, ref block) => {
let indent = indent + LEVEL;
buf.push_str("Function");
newline(buf);
do_indent(indent, buf);
render_signature(sig, indent, buf);
newline(buf);
do_indent(indent, buf);
buf.push_str("(Body");
newline(buf);
render_block(block, indent + LEVEL, buf);
do_indent(indent, buf);
buf.push_str(")");
newline(buf);
}
TypeDecl { name: _, body: _, .. } => {
buf.push_str("<type-decl>");
}
TypeAlias { alias: _, original: _ } => {
buf.push_str("<type-alias>");
}
Binding { name, constant: _, type_anno: _, expr } => {
let new_indent = indent + LEVEL;
buf.push_str(&format!("Binding {}", name));
newline(buf);
do_indent(new_indent, buf);
render_expression(expr, new_indent, buf);
newline(buf);
}
Module { name, items: _ } => {
write!(buf, "(Module {} <body>)", name).unwrap();
}
_ => (), /*
Impl { type_name: TypeIdentifier, interface_name: Option<TypeSingletonName>, block: Vec<Declaration> },
Interface { name: Rc<String>, signatures: Vec<Signature> },
Annotation { name: Rc<String>, arguments: Vec<Expression> },
*/
}
do_indent(indent, buf);
buf.push(')');
}
fn render_block(block: &Block, indent: usize, buf: &mut String) {
for stmt in block.statements.iter() {
render_statement(stmt, indent, buf);
newline(buf);
}
}
fn render_signature(sig: &Signature, _indent: usize, buf: &mut String) {
buf.push_str(&format!("(Signature {} )", sig.name));
}
fn render_import(_import: &ImportSpecifier, _indent: usize, buf: &mut String) {
buf.push_str("(Import <some import>)");
}
fn render_flow_control(flow: &FlowControl, _indent: usize, buf: &mut String) {
use FlowControl::*;
match flow {
Return(ref _expr) => write!(buf, "return <expr>").unwrap(),
Break => write!(buf, "break").unwrap(),
Continue => write!(buf, "continue").unwrap(),
}
}
#[cfg(test)]
mod test {
use super::render_ast;
use crate::util::quick_ast;
#[test]
fn test_visualization() {
let ast = quick_ast(
r#"
fn test(x) {
let m = 9
1 * 4 <> m |> somemod::output(x)
}
let quincy = \(no, yes, maybe) {
let a = 10
yes * no + a
}
let b = 54
test(b) == 3
"#,
);
let expected_output = r#"(AST
(Decl Function
(Signature test )
(Body
(Decl Binding m
(Expr (NatLiteral 9))
)
(Expr Binop *
(Expr (NatLiteral 1))
(Expr Binop |>
(Expr Binop <>
(Expr (NatLiteral 4))
(Expr Value m))
)
(Expr Call (Expr Value somemod::output))
(Expr Value x))
)
)
)
)
)
(Decl Binding quincy
(Expr Lambda
(Args no yes maybe )
(Body
(Decl Binding a
(Expr (NatLiteral 10))
)
(Expr Binop +
(Expr Binop *
(Expr Value yes))
(Expr Value no))
)
(Expr Value a))
)
)
)
)
(Decl Binding b
(Expr (NatLiteral 54))
)
(Expr Binop ==
(Expr Call (Expr Value test))
(Expr Value b))
)
(Expr (NatLiteral 3))
)
)"#;
let rendered = render_ast(&ast);
assert_eq!(rendered, expected_output);
}
}

View File

@ -1,130 +0,0 @@
use std::{convert::TryFrom, str::FromStr};
use crate::{
ast::{BinOp, PrefixOp},
type_inference::Type,
};
/// "Builtin" computational operations with some kind of semantics, mostly mathematical operations.
#[derive(Debug, Clone, Copy, PartialEq)]
pub enum Builtin {
Add,
Increment,
Subtract,
Negate,
Multiply,
Divide,
Quotient,
Modulo,
Exponentiation,
BitwiseAnd,
BitwiseOr,
BooleanAnd,
BooleanOr,
BooleanNot,
Equality,
LessThan,
LessThanOrEqual,
GreaterThan,
GreaterThanOrEqual,
Comparison,
IOPrint,
IOPrintLn,
IOGetLine,
Assignment,
Concatenate,
NotEqual,
}
impl Builtin {
#[allow(dead_code)]
pub fn get_type(&self) -> Type {
use Builtin::*;
match self {
Add => ty!(Nat -> Nat -> Nat),
Subtract => ty!(Nat -> Nat -> Nat),
Multiply => ty!(Nat -> Nat -> Nat),
Divide => ty!(Nat -> Nat -> Float),
Quotient => ty!(Nat -> Nat -> Nat),
Modulo => ty!(Nat -> Nat -> Nat),
Exponentiation => ty!(Nat -> Nat -> Nat),
BitwiseAnd => ty!(Nat -> Nat -> Nat),
BitwiseOr => ty!(Nat -> Nat -> Nat),
BooleanAnd => ty!(Bool -> Bool -> Bool),
BooleanOr => ty!(Bool -> Bool -> Bool),
BooleanNot => ty!(Bool -> Bool),
Equality => ty!(Nat -> Nat -> Bool),
LessThan => ty!(Nat -> Nat -> Bool),
LessThanOrEqual => ty!(Nat -> Nat -> Bool),
GreaterThan => ty!(Nat -> Nat -> Bool),
GreaterThanOrEqual => ty!(Nat -> Nat -> Bool),
Comparison => ty!(Nat -> Nat -> Ordering),
IOPrint => ty!(Unit),
IOPrintLn => ty!(Unit),
IOGetLine => ty!(StringT),
Assignment => ty!(Unit),
Concatenate => ty!(StringT -> StringT -> StringT),
Increment => ty!(Nat -> Int),
Negate => ty!(Nat -> Int),
NotEqual => ty!(Nat -> Nat -> Bool),
}
}
}
impl TryFrom<&BinOp> for Builtin {
type Error = ();
fn try_from(binop: &BinOp) -> Result<Self, Self::Error> {
FromStr::from_str(binop.sigil())
}
}
impl TryFrom<&PrefixOp> for Builtin {
type Error = ();
fn try_from(prefix_op: &PrefixOp) -> Result<Self, Self::Error> {
use Builtin::*;
match prefix_op.sigil() {
"+" => Ok(Increment),
"-" => Ok(Negate),
"!" => Ok(BooleanNot),
_ => Err(()),
}
}
}
impl FromStr for Builtin {
type Err = ();
fn from_str(s: &str) -> Result<Self, Self::Err> {
use Builtin::*;
Ok(match s {
"+" => Add,
"-" => Subtract,
"*" => Multiply,
"/" => Divide,
"quot" => Quotient,
"%" => Modulo,
"++" => Concatenate,
"^" => Exponentiation,
"&" => BitwiseAnd,
"&&" => BooleanAnd,
"|" => BitwiseOr,
"||" => BooleanOr,
"!" => BooleanNot,
">" => GreaterThan,
">=" => GreaterThanOrEqual,
"<" => LessThan,
"<=" => LessThanOrEqual,
"==" => Equality,
"!=" => NotEqual,
"=" => Assignment,
"<=>" => Comparison,
"print" => IOPrint,
"println" => IOPrintLn,
"getline" => IOGetLine,
_ => return Err(()),
})
}
}

View File

@ -1,79 +0,0 @@
use crate::{
parsing::{Location, ParseError},
schala::{SourceReference, Stage},
symbol_table::SymbolError,
type_inference::TypeError,
};
pub struct SchalaError {
errors: Vec<Error>,
}
impl SchalaError {
pub(crate) fn display(&self) -> String {
match self.errors[0] {
Error::Parse(ref parse_err) => parse_err.to_string(),
Error::Standard { ref text, .. } => text.as_ref().cloned().unwrap_or_default(),
}
}
#[allow(dead_code)]
pub(crate) fn from_type_error(err: TypeError) -> Self {
Self {
errors: vec![Error::Standard { location: None, text: Some(err.msg), stage: Stage::Typechecking }],
}
}
pub(crate) fn from_symbol_table(symbol_errs: Vec<SymbolError>) -> Self {
//TODO this could be better
let errors = symbol_errs
.into_iter()
.map(|_symbol_err| Error::Standard {
location: None,
text: Some("symbol table error".to_string()),
stage: Stage::Symbols,
})
.collect();
Self { errors }
}
pub(crate) fn from_string(text: String, stage: Stage) -> Self {
Self { errors: vec![Error::Standard { location: None, text: Some(text), stage }] }
}
pub(crate) fn from_parse_error(parse_error: ParseError, source_reference: &SourceReference) -> Self {
let formatted_parse_error = format_parse_error(parse_error, source_reference);
Self { errors: vec![Error::Parse(formatted_parse_error)] }
}
}
#[allow(dead_code)]
enum Error {
Standard { location: Option<Location>, text: Option<String>, stage: Stage },
Parse(String),
}
fn format_parse_error(error: ParseError, source_reference: &SourceReference) -> String {
let offset = error.location.offset;
let (line_start, line_num, line_from_program) = source_reference.get_line(offset);
let ch = offset - line_start;
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,
)
}

View File

@ -1,75 +0,0 @@
use std::{
fmt::{self, Debug},
hash::Hash,
marker::PhantomData,
};
pub trait IdKind: Debug + Copy + Clone + Hash + PartialEq + Eq + Default {
fn tag() -> &'static str;
}
/// A generalized abstract identifier type of up to 2^32-1 entries.
#[derive(Debug, Copy, Clone, Hash, PartialEq, Eq, Default)]
pub struct Id<T>
where T: IdKind
{
idx: u32,
t: PhantomData<T>,
}
impl<T> Id<T>
where T: IdKind
{
fn new(n: u32) -> Self {
Self { idx: n, t: PhantomData }
}
#[allow(dead_code)]
pub fn as_u32(&self) -> u32 {
self.idx
}
}
impl<T> fmt::Display for Id<T>
where T: IdKind
{
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
write!(f, "{}:{}", self.idx, T::tag())
}
}
#[derive(Debug)]
pub struct IdStore<T>
where T: IdKind
{
last_idx: u32,
t: PhantomData<T>,
}
impl<T> IdStore<T>
where T: IdKind
{
pub fn new() -> Self {
Self { last_idx: 0, t: PhantomData }
}
pub fn fresh(&mut self) -> Id<T> {
let idx = self.last_idx;
self.last_idx += 1;
Id::new(idx)
}
}
macro_rules! define_id_kind {
($name:ident) => {
#[derive(Debug, Copy, Clone, Hash, PartialEq, Eq, Default)]
pub struct $name;
impl crate::identifier::IdKind for $name {
fn tag() -> &'static str {
stringify!($name)
}
}
};
}
pub(crate) use define_id_kind;

View File

@ -1,31 +0,0 @@
#![feature(trace_macros)]
//#![feature(unrestricted_attribute_tokens)]
#![feature(box_patterns, iter_intersperse)]
//! `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 derivative;
extern crate schala_repl;
#[macro_use]
mod util;
#[macro_use]
mod type_inference;
mod ast;
mod parsing;
#[macro_use]
mod symbol_table;
mod builtin;
mod error;
mod reduced_ir;
mod tree_walk_eval;
#[macro_use]
mod identifier;
mod schala;
pub use schala::{Schala, SchalaConfig};

File diff suppressed because it is too large Load Diff

View File

@ -1,126 +0,0 @@
#![allow(clippy::upper_case_acronyms)]
pub mod combinator;
mod peg_parser;
mod test;
use std::{cell::RefCell, fmt, rc::Rc};
use combinator::Span;
#[cfg(test)]
use crate::ast::{Block, Expression};
use crate::{
ast::{ASTItem, AST},
identifier::{Id, IdStore},
};
pub(crate) type StoreRef = Rc<RefCell<IdStore<ASTItem>>>;
pub struct Parser {
id_store: StoreRef,
use_combinator: bool,
}
impl Parser {
pub(crate) fn new() -> Self {
let id_store: IdStore<ASTItem> = IdStore::new();
Self { id_store: Rc::new(RefCell::new(id_store)), use_combinator: true }
}
pub(crate) fn parse(&mut self, input: &str) -> Result<AST, ParseError> {
if self.use_combinator {
self.parse_comb(input)
} else {
self.parse_peg(input)
}
}
pub(crate) fn parse_peg(&mut self, input: &str) -> Result<AST, ParseError> {
peg_parser::schala_parser::program(input, self).map_err(ParseError::from_peg)
}
pub(crate) fn parse_comb(&mut self, input: &str) -> Result<AST, ParseError> {
let span = Span::new_extra(input, self.id_store.clone());
convert(input, combinator::program(span))
}
#[cfg(test)]
fn expression(&mut self, input: &str) -> Result<Expression, ParseError> {
peg_parser::schala_parser::expression(input, self).map_err(ParseError::from_peg)
}
#[cfg(test)]
fn expression_comb(&mut self, input: &str) -> Result<Expression, ParseError> {
let span = Span::new_extra(input, self.id_store.clone());
convert(input, combinator::expression(span))
}
#[cfg(test)]
fn block(&mut self, input: &str) -> Result<Block, ParseError> {
peg_parser::schala_parser::block(input, self).map_err(ParseError::from_peg)
}
#[cfg(test)]
fn block_comb(&mut self, input: &str) -> Result<Block, ParseError> {
let span = Span::new_extra(input, self.id_store.clone());
convert(input, combinator::block(span))
}
fn fresh(&mut self) -> Id<ASTItem> {
self.id_store.borrow_mut().fresh()
}
}
fn convert<'a, O>(input: &'a str, result: combinator::ParseResult<'a, O>) -> Result<O, ParseError> {
use nom::{error::VerboseError, Finish};
match result.finish() {
Ok((rest, output)) => {
if rest.fragment() != &"" {
return Err(ParseError {
location: Default::default(),
msg: format!("Bad parse state, remaining text: `{}`", rest.fragment()),
});
}
Ok(output)
}
Err(err) => {
let err = VerboseError {
errors: err.errors.into_iter().map(|(sp, kind)| (*sp.fragment(), kind)).collect(),
};
let msg = nom::error::convert_error(input, err);
Err(ParseError { msg, location: (0).into() })
}
}
}
/// Represents a parsing error
#[derive(Debug)]
pub struct ParseError {
pub msg: String,
pub location: Location,
}
impl ParseError {
fn from_peg(err: peg::error::ParseError<peg::str::LineCol>) -> Self {
let msg = err.to_string();
Self { msg, location: err.location.offset.into() }
}
}
#[derive(Debug, Clone, Copy, PartialEq, Default)]
pub struct Location {
pub(crate) offset: usize,
}
impl From<usize> for Location {
fn from(offset: usize) -> Self {
Self { offset }
}
}
impl fmt::Display for Location {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
write!(f, "{}", self.offset)
}
}

View File

@ -1,567 +0,0 @@
use std::rc::Rc;
use super::Parser;
use crate::ast::*;
fn rc_string(s: &str) -> Rc<String> {
Rc::new(s.to_string())
}
enum ExtendedPart<'a> {
Index(Vec<Expression>),
Accessor(&'a str),
Call(Vec<InvocationArgument>),
}
peg::parser! {
pub grammar schala_parser() for str {
rule whitespace() = [' ' | '\t' ]
rule whitespace_or_newline() = [' ' | '\t' | '\n' ]
rule _ = quiet!{ (block_comment() / line_comment() / whitespace())* }
rule __ = quiet!{ (block_comment() / line_comment() / whitespace_or_newline())* }
rule block_comment() = "/*" (block_comment() / !"*/" [_])* "*/"
rule line_comment() = "//" (!['\n'] [_])* &"\n"
pub rule program(parser: &mut Parser) -> AST =
__ statements:(statement(parser) ** (delimiter()+) ) __ { AST { id: parser.fresh(), statements: statements.into() } }
rule delimiter() = (";" / "\n")+
//Note - this is a hack, ideally the rule `rule block() -> Block = "{" _ items:(statement() **
//delimiter()) _ "}" { items.into() }` would've worked, but it doesn't.
pub rule block(parser: &mut Parser) -> Block =
"{" __ items:(statement(parser) ** delimiter()) delimiter()? __ "}" { items.into() } /
"{" __ stmt:statement(parser) __ "}" { vec![stmt].into() }
rule block_item(parser: &mut Parser) -> Statement<StatementKind> =
_ stmt:statement(parser) _ delimiter()+ { stmt }
rule statement(parser: &mut Parser) -> Statement<StatementKind> =
_ pos:position!() kind:statement_kind(parser) _ { Statement { id: parser.fresh(), location: pos.into(), kind } }
rule statement_kind(parser: &mut Parser) -> StatementKind =
__ import:import(parser) { StatementKind::Import(import) } /
__ decl:declaration(parser) { StatementKind::Declaration(decl) } /
__ flow:flow(parser) { StatementKind::Flow(flow) } /
__ expr:expression(parser) { StatementKind::Expression(expr) }
rule flow(parser: &mut Parser) -> FlowControl =
"continue" { FlowControl::Continue } /
"break" { FlowControl::Break } /
"return" _ expr:expression(parser)? { FlowControl::Return(expr) }
//TODO add the ability to rename and exclude imports
rule import(parser: &mut Parser) -> ImportSpecifier =
"import" _ path_components:path_components() suffix:import_suffix()? {
ImportSpecifier {
id: parser.fresh(),
path_components,
imported_names: suffix.unwrap_or(ImportedNames::LastOfPath)
}
}
rule path_components() -> Vec<Rc<String>> =
"::"? name:identifier() rest:path_component()* {
let mut items = vec![rc_string(name)];
items.extend(rest.into_iter().map(rc_string));
items
}
rule path_component() -> &'input str = "::" ident:identifier() { ident }
rule import_suffix() -> ImportedNames =
"::*" { ImportedNames::All } /
"::{" __ names:(identifier() ** (_ "," _)) __ "}" {?
if names.is_empty() {
Err("import groups must have at least one item")
} else {
Ok(ImportedNames::List(names.into_iter().map(rc_string).collect()))
}
}
rule declaration(parser: &mut Parser) -> Declaration =
binding(parser) / type_decl(parser) / annotation(parser) / func(parser) / interface(parser) /
implementation(parser) / module(parser)
rule module(parser: &mut Parser) -> Declaration =
"module" _ name:identifier() _ items:block(parser) { Declaration::Module { name: rc_string(name), items } }
rule implementation(parser: &mut Parser) -> Declaration =
"impl" _ interface:type_singleton_name() _ "for" _ type_name:type_identifier() _ block:decl_block(parser) {
Declaration::Impl { type_name, interface_name: Some(interface), block }
} /
"impl" _ type_name:type_identifier() _ block:decl_block(parser) {
Declaration::Impl { type_name, interface_name: None, block }
}
rule decl_block(parser: &mut Parser) -> Vec<Statement<Declaration>> =
"{" __ decls:(func_declaration_stmt(parser) ** (delimiter()+)) delimiter()? __ "}" { decls }
rule func_declaration_stmt(parser: &mut Parser) -> Statement<Declaration> =
pos:position!() decl:func_declaration(parser) { Statement { id: parser.fresh(), location: pos.into(), kind: decl } }
rule interface(parser: &mut Parser) -> Declaration =
"interface" _ name:identifier() _ signatures:signature_block(parser) { Declaration::Interface { name: rc_string(name), signatures } }
rule signature_block(parser: &mut Parser) -> Vec<Signature> =
"{" __ signatures:(func_signature(parser) ** (delimiter()+)) __ "}" { signatures }
rule func(parser: &mut Parser) -> Declaration =
decl:func_declaration(parser) { decl } /
sig:func_signature(parser) { Declaration::FuncSig(sig) }
rule func_declaration(parser: &mut Parser) -> Declaration =
_ sig:func_signature(parser) __ body:block(parser) { Declaration::FuncDecl(sig, body) }
rule func_signature(parser: &mut Parser) -> Signature =
_ "fn" _ name:identifier() "(" _ params:formal_params(parser) _ ")" _ type_anno:type_anno()? { Signature {
name: rc_string(name), operator: false, params, type_anno
} } /
_ "fn" _ "(" op:operator() ")" _ "(" _ params:formal_params(parser) _ ")" _ type_anno:type_anno()? { Signature {
name: rc_string(op), operator: true, params, type_anno
} }
rule formal_params(parser: &mut Parser) -> Vec<FormalParam> =
params:(formal_param(parser) ** (_ "," _)) {? if params.len() < 256 { Ok(params) } else {
Err("function-too-long") }
}
rule formal_param(parser: &mut Parser) -> FormalParam =
name:identifier() _ anno:type_anno()? _ "=" expr:expression(parser) { FormalParam { name: rc_string(name),
default: Some(expr), anno } } /
name:identifier() _ anno:type_anno()? { FormalParam { name: rc_string(name), default: None, anno } }
rule annotation(parser: &mut Parser) -> Declaration =
"@" name:identifier() args:annotation_args(parser)? delimiter()+ _ inner:statement(parser) { Declaration::Annotation {
name: rc_string(name), arguments: if let Some(args) = args { args } else { vec![] }, inner: Box::new(inner) }
}
rule annotation_args(parser: &mut Parser) -> Vec<Expression> =
"(" _ args:(expression(parser) ** (_ "," _)) _ ")" { args }
rule binding(parser: &mut Parser) -> Declaration =
"let" _ mutable:"mut"? _ ident:identifier() _ type_anno:type_anno()? _ "=" _ expr:expression(parser) {
Declaration::Binding { name: Rc::new(ident.to_string()), constant: mutable.is_none(),
type_anno, expr }
}
rule type_decl(parser: &mut Parser) -> Declaration =
"type" _ "alias" _ alias:type_alias() { alias } /
"type" _ mutable:"mut"? _ name:type_singleton_name() _ "=" _ body:type_body(parser) {
Declaration::TypeDecl { name, body, mutable: mutable.is_some() }
}
rule type_singleton_name() -> TypeSingletonName =
name:identifier() params:type_params()? { TypeSingletonName {
name: rc_string(name), params: if let Some(params) = params { params } else { vec![] }
} }
rule type_params() -> Vec<TypeIdentifier> =
"<" _ idents:(type_identifier() ** (_ "," _)) _ ">" { idents }
rule type_identifier() -> TypeIdentifier =
"(" _ items:(type_identifier() ** (_ "," _)) _ ")" { TypeIdentifier::Tuple(items) } /
singleton:type_singleton_name() { TypeIdentifier::Singleton(singleton) }
rule type_body(parser: &mut Parser) -> TypeBody =
"{" _ items:(record_variant_item() ** (__ "," __)) __ "}" { TypeBody::ImmediateRecord { id: parser.fresh(), fields: items } } /
variants:(variant_spec(parser) ** (__ "|" __)) { TypeBody::Variants(variants) }
rule variant_spec(parser: &mut Parser) -> Variant =
name:identifier() __ "{" __ typed_identifier_list:(record_variant_item() ** (__ "," __)) __ ","? __ "}" { Variant {
id: parser.fresh(), name: rc_string(name), kind: VariantKind::Record(typed_identifier_list)
} } /
name:identifier() "(" tuple_members:(type_identifier() ++ (__ "," __)) ")" { Variant {
id: parser.fresh(), name: rc_string(name), kind: VariantKind::TupleStruct(tuple_members) } } /
name:identifier() { Variant { id: parser.fresh(), name: rc_string(name), kind: VariantKind::UnitStruct } }
rule record_variant_item() -> (Rc<String>, TypeIdentifier) =
name:identifier() _ ":" _ ty:type_identifier() { (rc_string(name), ty) }
rule type_alias() -> Declaration =
alias:identifier() _ "=" _ name:identifier() { Declaration::TypeAlias { alias: rc_string(alias), original: rc_string(name), } }
rule type_anno() -> TypeIdentifier =
":" _ identifier:type_identifier() { identifier }
pub rule expression(parser: &mut Parser) -> Expression =
__ kind:expression_kind(true, parser) _ type_anno:type_anno()? { Expression { id: parser.fresh(), type_anno, kind } }
rule expression_no_struct(parser: &mut Parser) -> Expression =
__ kind:expression_kind(false, parser) { Expression { id: parser.fresh(), type_anno: None, kind } }
rule expression_kind(struct_ok: bool, parser: &mut Parser) -> ExpressionKind =
precedence_expr(struct_ok, parser)
rule precedence_expr(struct_ok: bool, parser: &mut Parser) -> ExpressionKind =
first:prefix_expr(struct_ok, parser) _ next:(precedence_continuation(struct_ok, parser))* {
let next = next.into_iter().map(|(sigil, expr)| (BinOp::from_sigil(sigil), expr)).collect();
BinopSequence { first, next }.do_precedence(parser)
}
rule precedence_continuation(struct_ok: bool, parser: &mut Parser) -> (&'input str, ExpressionKind) =
op:operator() _ expr:prefix_expr(struct_ok, parser) _ { (op, expr) }
rule prefix_expr(struct_ok: bool, parser: &mut Parser) -> ExpressionKind =
prefix:prefix()? expr:extended_expr(struct_ok, parser) {
if let Some(p) = prefix {
let expr = Expression::new(parser.fresh(), expr);
let prefix = PrefixOp::from_sigil(p);
ExpressionKind::PrefixExp(prefix, Box::new(expr))
} else {
expr
}
}
rule prefix() -> &'input str =
$(['+' | '-' | '!' ])
//TODO make the definition of operators more complex
rule operator() -> &'input str =
quiet!{!"*/" s:$( ['+' | '-' | '*' | '/' | '%' | '<' | '>' | '=' | '!' | '$' | '&' | '|' | '?' | '^' | '`']+ ) { s } } /
expected!("operator")
rule extended_expr(struct_ok: bool, parser: &mut Parser) -> ExpressionKind =
primary:primary(struct_ok, parser) parts:(extended_expr_part(parser)*) {
let mut expression = Expression::new(parser.fresh(), primary);
for part in parts.into_iter() {
let kind = match part {
ExtendedPart::Index(indexers) => {
ExpressionKind::Index { indexee: Box::new(expression), indexers }
},
ExtendedPart::Accessor(name) => {
let name = rc_string(name);
ExpressionKind::Access { name, expr: Box::new(expression) }
},
ExtendedPart::Call(arguments) => {
ExpressionKind::Call { f: Box::new(expression), arguments }
}
};
expression = Expression::new(parser.fresh(), kind);
}
expression.kind
}
rule extended_expr_part(parser: &mut Parser) -> ExtendedPart<'input> =
indexers:index_part(parser) { ExtendedPart::Index(indexers) } /
arguments:call_part(parser) { ExtendedPart::Call(arguments) } /
"." name:identifier() { ExtendedPart::Accessor(name) }
rule index_part(parser: &mut Parser) -> Vec<Expression> =
"[" indexers:(expression(parser) ++ ",") "]" { indexers }
rule call_part(parser: &mut Parser) -> Vec<InvocationArgument> =
"(" arguments:(invocation_argument(parser) ** ",") ")" { arguments }
rule invocation_argument(parser: &mut Parser) -> InvocationArgument =
_ "_" _ { InvocationArgument::Ignored } /
_ ident:identifier() _ "=" _ expr:expression(parser) { InvocationArgument::Keyword {
name: Rc::new(ident.to_string()),
expr
} } /
_ expr:expression(parser) _ { InvocationArgument::Positional(expr) }
rule primary(struct_ok: bool, parser: &mut Parser) -> ExpressionKind =
while_expr(parser) / for_expr(parser) / float_literal() / nat_literal() / bool_literal() /
string_literal() / paren_expr(parser) /
list_expr(parser) / if_expr(parser) / lambda_expr(parser) /
item:named_struct(parser) {? if struct_ok { Ok(item) } else { Err("no-struct-allowed") } } /
identifier_expr(parser)
rule lambda_expr(parser: &mut Parser) -> ExpressionKind =
r#"\"# __ "(" _ params:formal_params(parser) _ ")" _ type_anno:(type_anno()?) _ body:block(parser) {
ExpressionKind::Lambda { params, type_anno, body }
} /
r#"\"# param:formal_param(parser) _ type_anno:(type_anno()?) _ body:block(parser) {
ExpressionKind::Lambda { params: vec![param], type_anno, body }
}
rule for_expr(parser: &mut Parser) -> ExpressionKind =
"for" _ enumerators:for_enumerators(parser) _ body:for_body(parser) {
ExpressionKind::ForExpression { enumerators, body }
}
rule for_enumerators(parser: &mut Parser) -> Vec<Enumerator> =
"{" _ enumerators:(enumerator(parser) ++ ",") _ "}" { enumerators } /
enumerator:enumerator(parser) { vec![enumerator] }
//TODO add guards, etc.
rule enumerator(parser: &mut Parser) -> Enumerator =
ident:identifier() _ "<-" _ generator:expression_no_struct(parser) {
Enumerator { identifier: Rc::new(ident.to_string()), generator, assignment: false }
} /
//TODO need to distinguish these two cases in AST
ident:identifier() _ "=" _ generator:expression_no_struct(parser) {
Enumerator { identifier: Rc::new(ident.to_string()), generator, assignment: true }
}
rule for_body(parser: &mut Parser) -> Box<ForBody> =
"return" _ expr:expression(parser) { Box::new(ForBody::MonadicReturn(expr)) } /
body:block(parser) { Box::new(ForBody::StatementBlock(body)) }
rule while_expr(parser: &mut Parser) -> ExpressionKind =
"while" _ cond:expression_kind(false, parser)? _ body:block(parser) {
ExpressionKind::WhileExpression {
condition: cond.map(|kind| Box::new(Expression::new(parser.fresh(), kind))),
body,
}
}
rule identifier_expr(parser: &mut Parser) -> ExpressionKind =
qn:qualified_identifier(parser) { ExpressionKind::Value(qn) }
rule named_struct(parser: &mut Parser) -> ExpressionKind =
name:qualified_identifier(parser) _ fields:record_block(parser) {
ExpressionKind::NamedStruct {
name,
fields: fields.into_iter().map(|(n, exp)| (Rc::new(n.to_string()), exp)).collect(),
}
}
//TODO support anonymous structs and Elm-style update syntax for structs
rule record_block(parser: &mut Parser) -> Vec<(&'input str, Expression)> =
"{" _ entries:(record_entry(parser) ** ",") _ "}" { entries }
rule record_entry(parser: &mut Parser) -> (&'input str, Expression) =
_ name:identifier() _ ":" _ expr:expression(parser) _ { (name, expr) }
rule qualified_identifier(parser: &mut Parser) -> QualifiedName =
names:(identifier() ++ "::") { QualifiedName { id: parser.fresh(), components: names.into_iter().map(|name| Rc::new(name.to_string())).collect() } }
//TODO improve the definition of identifiers
rule identifier() -> &'input str =
!(reserved() !(ident_continuation())) text:$(['a'..='z' | 'A'..='Z' | '_'] ident_continuation()*) { text }
rule ident_continuation() -> &'input str =
text:$(['a'..='z' | 'A'..='Z' | '0'..='9' | '_'])
rule reserved() = "if" / "then" / "else" / "is" / "fn" / "for" / "while" / "let" / "in" / "mut" / "return" /
"break" / "alias" / "type" / "self" / "Self" / "interface" / "impl" / "true" / "false" / "module" / "import"
rule if_expr(parser: &mut Parser) -> ExpressionKind =
"if" _ discriminator:(expression(parser)?) _ body:if_expr_body(parser) {
ExpressionKind::IfExpression {
discriminator: discriminator.map(Box::new),
body: Box::new(body),
}
}
rule if_expr_body(parser: &mut Parser) -> IfExpressionBody =
cond_block(parser) / simple_pattern_match(parser) / simple_conditional(parser)
rule simple_conditional(parser: &mut Parser) -> IfExpressionBody =
"then" _ then_case:expr_or_block(parser) _ else_case:else_case(parser) {
IfExpressionBody::SimpleConditional { then_case, else_case }
}
rule simple_pattern_match(parser: &mut Parser) -> IfExpressionBody =
"is" _ pattern:pattern(parser) _ "then" _ then_case:expr_or_block(parser) _ else_case:else_case(parser) {
IfExpressionBody::SimplePatternMatch { pattern, then_case, else_case }
}
rule cond_block(parser: &mut Parser) -> IfExpressionBody =
"{" __ cond_arms:(cond_arm(parser) ++ (delimiter()+)) __ "}" { IfExpressionBody::CondList(cond_arms) }
rule cond_arm(parser: &mut Parser) -> ConditionArm =
_ "else" _ body:expr_or_block(parser) { ConditionArm { condition: Condition::Else, guard: None, body } } /
_ condition:condition(parser) _ guard:condition_guard(parser) _ "then" _ body:expr_or_block(parser)
{ ConditionArm { condition, guard, body } }
rule condition(parser: &mut Parser) -> Condition =
"is" _ pat:pattern(parser) { Condition::Pattern(pat) } /
op:operator() _ expr:expression(parser) { Condition::TruncatedOp(BinOp::from_sigil(op), expr) }
rule condition_guard(parser: &mut Parser) -> Option<Expression> =
("if" _ expr:expression(parser) { expr } )?
rule expr_or_block(parser: &mut Parser) -> Block = block(parser) / pos:position!() ex:expression(parser) {
Statement {
id: parser.fresh() , location: pos.into(),
kind: StatementKind::Expression(ex)
}.into()
}
rule else_case(parser: &mut Parser) -> Option<Block> =
("else" _ eorb:expr_or_block(parser) { eorb })?
rule pattern(parser: &mut Parser) -> Pattern =
"(" _ variants:(pattern(parser) ++ ",") _ ")" { Pattern::TuplePattern(variants) } /
_ pat:simple_pattern(parser) { pat }
rule simple_pattern(parser: &mut Parser) -> Pattern =
pattern_literal() /
qn:qualified_identifier(parser) "(" members:(pattern(parser) ** ",") ")" {
Pattern::TupleStruct(qn, members)
} /
qn:qualified_identifier(parser) _ "{" _ items:(record_pattern_entry(parser) ** ",") "}" _ {
let items = items.into_iter().map(|(name, pat)| (Rc::new(name.to_string()), pat)).collect();
Pattern::Record(qn, items)
} /
qn:qualified_identifier(parser) { Pattern::VarOrName(qn) }
rule record_pattern_entry(parser: &mut Parser) -> (&'input str, Pattern) =
_ name:identifier() _ ":" _ pat:pattern(parser) _ { (name, pat) } /
_ name:identifier() _ {
let qn = QualifiedName {
id: parser.fresh(),
components: vec![Rc::new(name.to_string())],
};
(name, Pattern::VarOrName(qn))
}
rule pattern_literal() -> Pattern =
"true" { Pattern::Literal(PatternLiteral::BoolPattern(true)) } /
"false" { Pattern::Literal(PatternLiteral::BoolPattern(false)) } /
s:bare_string_literal() { Pattern::Literal(PatternLiteral::StringPattern(Rc::new(s))) } /
sign:("-"?) num:(float_literal() / nat_literal()) {
let neg = sign.is_some();
Pattern::Literal(PatternLiteral::NumPattern { neg, num })
} /
"_" { Pattern::Ignored }
rule list_expr(parser: &mut Parser) -> ExpressionKind =
"[" exprs:(expression(parser) ** ",") "]" {
let mut exprs = exprs;
ExpressionKind::ListLiteral(exprs)
}
rule paren_expr(parser: &mut Parser) -> ExpressionKind =
"(" exprs:(expression(parser) ** ",") ")" {
let mut exprs = exprs;
match exprs.len() {
1 => exprs.pop().unwrap().kind,
_ => ExpressionKind::TupleLiteral(exprs),
}
}
rule string_literal() -> ExpressionKind =
prefix:identifier()? s:bare_string_literal(){ ExpressionKind::StringLiteral{ s: Rc::new(s),
prefix: prefix.map(rc_string)
} }
rule bare_string_literal() -> String =
"\"" chars:string_component()* "\"" { chars.into_iter().collect::<String>() }
rule string_component() -> char =
!(r#"""# / r#"\"#) ch:$([_]) { ch.chars().next().unwrap() } /
r#"\u{"# value:$(['0'..='9' | 'a'..='f' | 'A'..='F']+) "}" { char::from_u32(u32::from_str_radix(value, 16).unwrap()).unwrap() } /
r#"\n"# { '\n' } / r#"\t"# { '\t' } / r#"\""# { '"' } / r#"\\"# { '\\' } /
expected!("Valid escape sequence")
rule bool_literal() -> ExpressionKind =
"true" { ExpressionKind::BoolLiteral(true) } / "false" { ExpressionKind::BoolLiteral(false) }
rule nat_literal() -> ExpressionKind =
bin_literal() / hex_literal() / unmarked_literal()
rule unmarked_literal() -> ExpressionKind =
digits:digits() { let n = digits.chars().filter(|ch| *ch != '_').collect::<String>().parse().unwrap(); ExpressionKind::NatLiteral(n) }
rule bin_literal() -> ExpressionKind =
"0b" digits:bin_digits() {? parse_binary(digits).map(ExpressionKind::NatLiteral) }
rule hex_literal() -> ExpressionKind =
"0x" digits:hex_digits() {? parse_hex(digits).map(ExpressionKind::NatLiteral) }
rule float_literal() -> ExpressionKind =
ds:$( digits() "." digits()? / "." digits() ) { ExpressionKind::FloatLiteral(ds.parse().unwrap()) }
rule digits() -> &'input str = $((digit_group() "_"*)+)
rule bin_digits() -> &'input str = $((bin_digit_group() "_"*)+)
rule hex_digits() -> &'input str = $((hex_digit_group() "_"*)+)
rule digit_group() -> &'input str = $(['0'..='9']+)
rule bin_digit_group() -> &'input str = $(['0' | '1']+)
rule hex_digit_group() -> &'input str = $(['0'..='9' | 'a'..='f' | 'A'..='F']+)
}
}
fn parse_binary(digits: &str) -> Result<u64, &'static str> {
let mut result: u64 = 0;
let mut multiplier = 1;
for d in digits.chars().rev() {
match d {
'1' => result += multiplier,
'0' => (),
'_' => continue,
_ => unreachable!(),
}
multiplier = match multiplier.checked_mul(2) {
Some(m) => m,
None => return Err("Binary expression will overflow"),
}
}
Ok(result)
}
fn parse_hex(digits: &str) -> Result<u64, &'static str> {
let mut result: u64 = 0;
let mut multiplier: u64 = 1;
for d in digits.chars().rev() {
if d == '_' {
continue;
}
match d.to_digit(16) {
Some(n) => result += n as u64 * multiplier,
None => return Err("Internal parser error: invalid hex digit"),
}
multiplier = match multiplier.checked_mul(16) {
Some(m) => m,
None => return Err("Hexadecimal expression will overflow"),
}
}
Ok(result)
}
#[derive(Debug)]
struct BinopSequence {
first: ExpressionKind,
next: Vec<(BinOp, ExpressionKind)>,
}
impl BinopSequence {
fn do_precedence(self, parser: &mut Parser) -> ExpressionKind {
fn helper(
precedence: i32,
lhs: ExpressionKind,
rest: &mut Vec<(BinOp, ExpressionKind)>,
parser: &mut Parser,
) -> Expression {
let mut lhs = Expression::new(parser.fresh(), lhs);
while let Some((next_op, next_rhs)) = rest.pop() {
let new_precedence = next_op.get_precedence();
if precedence >= new_precedence {
rest.push((next_op, next_rhs));
break;
}
let rhs = helper(new_precedence, next_rhs, rest, parser);
lhs = Expression::new(
parser.fresh(),
ExpressionKind::BinExp(next_op, Box::new(lhs), Box::new(rhs)),
);
}
lhs
}
let mut as_stack = self.next.into_iter().rev().collect();
helper(BinOp::min_precedence(), self.first, &mut as_stack, parser).kind
}
}

File diff suppressed because it is too large Load Diff

View File

@ -1,484 +0,0 @@
use std::{collections::HashMap, rc::Rc, str::FromStr};
use crate::{
ast,
builtin::Builtin,
symbol_table::{DefId, SymbolSpec, SymbolTable},
type_inference::{TypeContext, TypeId},
};
mod test;
mod types;
pub use types::*;
pub fn reduce(ast: &ast::AST, symbol_table: &SymbolTable, type_context: &TypeContext) -> ReducedIR {
let reducer = Reducer::new(symbol_table, type_context);
reducer.reduce(ast)
}
struct Reducer<'a, 'b> {
symbol_table: &'a SymbolTable,
functions: HashMap<DefId, FunctionDefinition>,
type_context: &'b TypeContext,
}
impl<'a, 'b> Reducer<'a, 'b> {
fn new(symbol_table: &'a SymbolTable, type_context: &'b TypeContext) -> Self {
Self { symbol_table, functions: HashMap::new(), type_context }
}
fn reduce(mut self, ast: &ast::AST) -> ReducedIR {
// First reduce all functions
// TODO once this works, maybe rewrite it using the Visitor
for statement in ast.statements.statements.iter() {
self.top_level_definition(statement);
}
// Then compute the entrypoint statements (which may reference previously-computed
// functions by ID)
let mut entrypoint = vec![];
for statement in ast.statements.statements.iter() {
let ast::Statement { id: item_id, kind, .. } = statement;
match &kind {
ast::StatementKind::Expression(expr) => {
entrypoint.push(Statement::Expression(self.expression(expr)));
}
ast::StatementKind::Declaration(ast::Declaration::Binding {
name: _,
constant,
expr,
..
}) => {
let symbol = self.symbol_table.lookup_symbol(item_id).unwrap();
entrypoint.push(Statement::Binding {
id: symbol.def_id(),
constant: *constant,
expr: self.expression(expr),
});
}
_ => (),
}
}
ReducedIR { functions: self.functions, entrypoint }
}
fn top_level_definition(&mut self, statement: &ast::Statement<ast::StatementKind>) {
let ast::Statement { id: item_id, kind, .. } = statement;
match kind {
ast::StatementKind::Expression(_expr) => {
//TODO expressions can in principle contain definitions, but I won't worry
//about it now
}
ast::StatementKind::Declaration(decl) => match decl {
ast::Declaration::FuncDecl(_, statements) => {
self.insert_function_definition(item_id, statements);
}
ast::Declaration::Impl { type_name: _, interface_name: _, block } =>
for item in block {
if let ast::Statement {
id: item_id,
kind: ast::Declaration::FuncDecl(_, statements),
..
} = item
{
self.insert_function_definition(item_id, statements);
}
},
_ => (),
},
// Imports should have already been processed by the symbol table and are irrelevant
// for this representation.
ast::StatementKind::Import(..) => (),
ast::StatementKind::Flow(..) => {
//TODO this should be an error
}
}
}
fn function_internal_statement(
&mut self,
statement: &ast::Statement<ast::StatementKind>,
) -> Option<Statement> {
let ast::Statement { id: item_id, kind, .. } = statement;
match kind {
ast::StatementKind::Expression(expr) => Some(Statement::Expression(self.expression(expr))),
ast::StatementKind::Declaration(decl) => match decl {
ast::Declaration::FuncDecl(_, statements) => {
self.insert_function_definition(item_id, statements);
None
}
ast::Declaration::Binding { constant, expr, .. } => {
let symbol = self.symbol_table.lookup_symbol(item_id).unwrap();
Some(Statement::Binding {
id: symbol.def_id(),
constant: *constant,
expr: self.expression(expr),
})
}
_ => None,
},
ast::StatementKind::Import(_) => None,
ast::StatementKind::Flow(ast::FlowControl::Return(expr)) =>
if let Some(expr) = expr {
Some(Statement::Return(self.expression(expr)))
} else {
Some(Statement::Return(Expression::unit()))
},
ast::StatementKind::Flow(ast::FlowControl::Break) => Some(Statement::Break),
ast::StatementKind::Flow(ast::FlowControl::Continue) => Some(Statement::Continue),
}
}
fn insert_function_definition(&mut self, item_id: &ast::ItemId, statements: &ast::Block) {
let symbol = self.symbol_table.lookup_symbol(item_id).unwrap();
let function_def = FunctionDefinition { body: self.function_internal_block(statements) };
self.functions.insert(symbol.def_id(), function_def);
}
//TODO this needs to be type-aware to work correctly
fn lookup_method(&mut self, name: &str) -> Option<DefId> {
for (def_id, function) in self.functions.iter() {
let symbol = self.symbol_table.lookup_symbol_by_def(def_id)?;
println!("Def Id: {} symbol: {:?}", def_id, symbol);
if symbol.local_name() == name {
return Some(*def_id);
}
}
None
}
fn expression(&mut self, expr: &ast::Expression) -> Expression {
use crate::ast::ExpressionKind::*;
match &expr.kind {
SelfValue => Expression::Lookup(Lookup::SelfParam),
NatLiteral(n) => Expression::Literal(Literal::Nat(*n)),
FloatLiteral(f) => Expression::Literal(Literal::Float(*f)),
//TODO implement handling string literal prefixes
StringLiteral { s, prefix: _ } => Expression::Literal(Literal::StringLit(s.clone())),
BoolLiteral(b) => Expression::Literal(Literal::Bool(*b)),
BinExp(binop, lhs, rhs) => self.binop(binop, lhs, rhs),
PrefixExp(op, arg) => self.prefix(op, arg),
Value(qualified_name) => self.value(qualified_name),
Call { f, arguments } => {
let f = self.expression(f);
let args = arguments.iter().map(|arg| self.invocation_argument(arg)).collect();
//TODO need to have full type availability at this point to do this method lookup
//correctly
if let Expression::Access { name, expr } = f {
let def_id = self.lookup_method(&name).unwrap();
let method = Expression::Lookup(Lookup::Function(def_id));
Expression::CallMethod { f: Box::new(method), args, self_expr: expr }
} else {
Expression::Call { f: Box::new(f), args }
}
}
TupleLiteral(exprs) => Expression::Tuple(exprs.iter().map(|e| self.expression(e)).collect()),
IfExpression { discriminator, body } =>
self.reduce_if_expression(discriminator.as_ref().map(|x| x.as_ref()), body),
Lambda { params, body, .. } => Expression::Callable(Callable::Lambda {
arity: params.len() as u8,
body: self.function_internal_block(body),
}),
NamedStruct { name, fields } => {
let symbol = match self.symbol_table.lookup_symbol(&name.id) {
Some(symbol) => symbol,
None => return Expression::ReductionError(format!("No symbol found for {}", name)),
};
let (tag, type_id) = match symbol.spec() {
SymbolSpec::RecordConstructor { tag, type_id } => (tag, type_id),
e => return Expression::ReductionError(format!("Bad symbol for NamedStruct: {:?}", e)),
};
let field_order = compute_field_orderings(self.type_context, &type_id, tag).unwrap();
let mut field_map = HashMap::new();
for (name, expr) in fields.iter() {
field_map.insert(name.as_ref(), expr);
}
let mut ordered_args = vec![];
for field in field_order.iter() {
let expr = match field_map.get(&field) {
Some(expr) => expr,
None =>
return Expression::ReductionError(format!(
"Field {} not specified for record {}",
field, name
)),
};
ordered_args.push(self.expression(expr));
}
let constructor =
Expression::Callable(Callable::RecordConstructor { type_id, tag, field_order });
Expression::Call { f: Box::new(constructor), args: ordered_args }
}
Index { indexee, indexers } => self.reduce_index(indexee.as_ref(), indexers.as_slice()),
WhileExpression { condition, body } => {
let cond = Box::new(if let Some(condition) = condition {
self.expression(condition)
} else {
Expression::Literal(Literal::Bool(true))
});
let statements = self.function_internal_block(body);
Expression::Loop { cond, statements }
}
ForExpression { .. } => Expression::ReductionError("For expr not implemented".to_string()),
ListLiteral(items) => Expression::List(items.iter().map(|item| self.expression(item)).collect()),
Access { name, expr } =>
Expression::Access { name: name.as_ref().to_string(), expr: Box::new(self.expression(expr)) },
}
}
//TODO figure out the semantics of multiple indexers - for now, just ignore them
fn reduce_index(&mut self, indexee: &ast::Expression, indexers: &[ast::Expression]) -> Expression {
if indexers.len() != 1 {
return Expression::ReductionError("Invalid index expression".to_string());
}
let indexee = self.expression(indexee);
let indexer = self.expression(&indexers[0]);
Expression::Index { indexee: Box::new(indexee), indexer: Box::new(indexer) }
}
fn reduce_if_expression(
&mut self,
discriminator: Option<&ast::Expression>,
body: &ast::IfExpressionBody,
) -> Expression {
use ast::IfExpressionBody::*;
let cond = Box::new(match discriminator {
Some(expr) => self.expression(expr),
None => return Expression::ReductionError("blank cond if-expr not supported".to_string()),
});
match body {
SimpleConditional { then_case, else_case } => {
let then_clause = self.function_internal_block(then_case);
let else_clause = match else_case.as_ref() {
None => vec![],
Some(stmts) => self.function_internal_block(stmts),
};
Expression::Conditional { cond, then_clause, else_clause }
}
SimplePatternMatch { pattern, then_case, else_case } => {
let alternatives = vec![
Alternative {
pattern: match pattern.reduce(self.symbol_table) {
Ok(p) => p,
Err(e) => return Expression::ReductionError(format!("Bad pattern: {:?}", e)),
},
item: self.function_internal_block(then_case),
},
Alternative {
pattern: Pattern::Ignored,
item: match else_case.as_ref() {
Some(else_case) => self.function_internal_block(else_case),
None => vec![],
},
},
];
Expression::CaseMatch { cond, alternatives }
}
CondList(ref condition_arms) => {
let mut alternatives = vec![];
for arm in condition_arms {
match arm.condition {
ast::Condition::Pattern(ref pat) => {
let alt = Alternative {
pattern: match pat.reduce(self.symbol_table) {
Ok(p) => p,
Err(e) =>
return Expression::ReductionError(format!("Bad pattern: {:?}", e)),
},
item: self.function_internal_block(&arm.body),
};
alternatives.push(alt);
}
ast::Condition::TruncatedOp(_, _) =>
return Expression::ReductionError("case-expression-trunc-op".to_string()),
ast::Condition::Else =>
return Expression::ReductionError("case-expression-else".to_string()),
}
}
Expression::CaseMatch { cond, alternatives }
}
}
}
fn invocation_argument(&mut self, invoc: &ast::InvocationArgument) -> Expression {
use crate::ast::InvocationArgument::*;
match invoc {
Positional(ex) => self.expression(ex),
Keyword { .. } => Expression::ReductionError("Keyword arguments not supported".to_string()),
Ignored => Expression::ReductionError("Ignored arguments not supported".to_string()),
}
}
fn function_internal_block(&mut self, block: &ast::Block) -> Vec<Statement> {
block.statements.iter().filter_map(|stmt| self.function_internal_statement(stmt)).collect()
}
fn prefix(&mut self, prefix: &ast::PrefixOp, arg: &ast::Expression) -> Expression {
let builtin: Option<Builtin> = TryFrom::try_from(prefix).ok();
match builtin {
Some(op) => Expression::Call {
f: Box::new(Expression::Callable(Callable::Builtin(op))),
args: vec![self.expression(arg)],
},
None => {
//TODO need this for custom prefix ops
Expression::ReductionError("User-defined prefix ops not supported".to_string())
}
}
}
fn binop(&mut self, binop: &ast::BinOp, lhs: &ast::Expression, rhs: &ast::Expression) -> Expression {
use Expression::ReductionError;
let operation = Builtin::from_str(binop.sigil()).ok();
match operation {
Some(Builtin::Assignment) => {
let lval = match &lhs.kind {
ast::ExpressionKind::Value(qualified_name) => {
if let Some(symbol) = self.symbol_table.lookup_symbol(&qualified_name.id) {
symbol.def_id()
} else {
return ReductionError(format!("Couldn't look up name: {:?}", qualified_name));
}
}
_ => return ReductionError("Trying to assign to a non-name".to_string()),
};
Expression::Assign { lval, rval: Box::new(self.expression(rhs)) }
}
Some(op) => Expression::Call {
f: Box::new(Expression::Callable(Callable::Builtin(op))),
args: vec![self.expression(lhs), self.expression(rhs)],
},
//TODO handle a user-defined operation
None => ReductionError("User-defined operations not supported".to_string()),
}
}
fn value(&mut self, qualified_name: &ast::QualifiedName) -> Expression {
use SymbolSpec::*;
let symbol = match self.symbol_table.lookup_symbol(&qualified_name.id) {
Some(s) => s,
None =>
return Expression::ReductionError(format!("No symbol found for name: `{}`", qualified_name)),
};
let def_id = symbol.def_id();
match symbol.spec() {
Builtin(b) => Expression::Callable(Callable::Builtin(b)),
Func { .. } => Expression::Lookup(Lookup::Function(def_id)),
GlobalBinding => Expression::Lookup(Lookup::GlobalVar(def_id)),
LocalVariable => Expression::Lookup(Lookup::LocalVar(def_id)),
FunctionParam(n) => Expression::Lookup(Lookup::Param(n)),
DataConstructor { tag, type_id } =>
Expression::Callable(Callable::DataConstructor { type_id, tag }),
RecordConstructor { .. } => Expression::ReductionError(format!(
"The symbol for value {:?} is unexpectdly a RecordConstructor",
qualified_name
)),
}
}
}
impl ast::Pattern {
fn reduce(&self, symbol_table: &SymbolTable) -> Result<Pattern, PatternError> {
Ok(match self {
ast::Pattern::Ignored => Pattern::Ignored,
ast::Pattern::TuplePattern(subpatterns) => {
let items: Result<Vec<Pattern>, PatternError> =
subpatterns.iter().map(|pat| pat.reduce(symbol_table)).into_iter().collect();
let items = items?;
Pattern::Tuple { tag: None, subpatterns: items }
}
ast::Pattern::Literal(lit) => Pattern::Literal(match lit {
ast::PatternLiteral::NumPattern { neg, num } => match (neg, num) {
(false, ast::ExpressionKind::NatLiteral(n)) => Literal::Nat(*n),
(false, ast::ExpressionKind::FloatLiteral(f)) => Literal::Float(*f),
(true, ast::ExpressionKind::NatLiteral(n)) => Literal::Int(-(*n as i64)),
(true, ast::ExpressionKind::FloatLiteral(f)) => Literal::Float(-f),
(_, e) =>
return Err(format!("Internal error, unexpected pattern literal: {:?}", e).into()),
},
ast::PatternLiteral::StringPattern(s) => Literal::StringLit(s.clone()),
ast::PatternLiteral::BoolPattern(b) => Literal::Bool(*b),
}),
ast::Pattern::TupleStruct(name, subpatterns) => {
let symbol = symbol_table.lookup_symbol(&name.id).unwrap();
if let SymbolSpec::DataConstructor { tag, type_id: _ } = symbol.spec() {
let items: Result<Vec<Pattern>, PatternError> =
subpatterns.iter().map(|pat| pat.reduce(symbol_table)).into_iter().collect();
let items = items?;
Pattern::Tuple { tag: Some(tag), subpatterns: items }
} else {
return Err(
"Internal error, trying to match something that's not a DataConstructor".into()
);
}
}
ast::Pattern::VarOrName(name) => {
let symbol = symbol_table.lookup_symbol(&name.id).unwrap();
match symbol.spec() {
SymbolSpec::DataConstructor { tag, type_id: _ } =>
Pattern::Tuple { tag: Some(tag), subpatterns: vec![] },
SymbolSpec::LocalVariable => {
let def_id = symbol.def_id();
Pattern::Binding(def_id)
}
spec => return Err(format!("Unexpected VarOrName symbol: {:?}", spec).into()),
}
}
ast::Pattern::Record(name, specified_members) => {
let symbol = symbol_table.lookup_symbol(&name.id).unwrap();
if let SymbolSpec::RecordConstructor { tag, type_id: _ } = symbol.spec() {
//TODO do this computation from the type_id
/*
if specified_members.iter().any(|(member, _)| !members.contains_key(member)) {
return Err(format!("Unknown key in record pattern").into());
}
*/
let subpatterns: Result<Vec<(Rc<String>, Pattern)>, PatternError> = specified_members
.iter()
.map(|(name, pat)| {
pat.reduce(symbol_table).map(|reduced_pat| (name.clone(), reduced_pat))
})
.into_iter()
.collect();
let subpatterns = subpatterns?;
Pattern::Record { tag, subpatterns }
} else {
return Err(format!("Unexpected Record pattern symbol: {:?}", symbol.spec()).into());
}
}
})
}
}
/// Given the type context and a variant, compute what order the fields on it were stored.
/// This needs to be public until type-checking is fully implemented because the type information
/// is only available at runtime.
pub fn compute_field_orderings(
type_context: &TypeContext,
type_id: &TypeId,
tag: u32,
) -> Option<Vec<String>> {
// Eventually, the ReducedIR should decide what field ordering is optimal.
// For now, just do it alphabetically.
let record_members = type_context.lookup_record_members(type_id, tag)?;
let mut field_order: Vec<String> =
record_members.iter().map(|(field, _type_id)| field).cloned().collect();
field_order.sort_unstable();
Some(field_order)
}

View File

@ -1,61 +0,0 @@
#![cfg(test)]
use super::*;
use crate::{symbol_table::SymbolTable, type_inference::TypeContext};
fn build_ir(input: &str) -> ReducedIR {
let ast = crate::util::quick_ast(input);
let mut symbol_table = SymbolTable::new();
let mut type_context = TypeContext::new();
symbol_table.process_ast(&ast, &mut type_context).unwrap();
let reduced = reduce(&ast, &symbol_table, &type_context);
reduced.debug(&symbol_table);
reduced
}
#[test]
fn test_ir() {
let src = r#"
let global_one = 10 + 20
let global_two = "the string hello"
fn a_function(i, j, k) {
fn nested(x) {
x + 10
}
i + j * nested(k)
}
fn another_function(e) {
let local_var = 420
e * local_var
}
another_function()
"#;
let reduced = build_ir(src);
assert_eq!(reduced.functions.len(), 3);
}
#[test]
fn test_methods() {
let src = r#"
type Thing = Thing
impl Thing {
fn a_method() {
20
}
}
let a = Thing
4 + a.a_method()
"#;
let reduced = build_ir(src);
assert_eq!(reduced.functions.len(), 1);
}

View File

@ -1,137 +0,0 @@
use std::{collections::HashMap, convert::From, rc::Rc};
use crate::{
builtin::Builtin,
symbol_table::{DefId, SymbolTable},
type_inference::TypeId,
};
//TODO most of these Clone impls only exist to support function application, because the
//tree-walking evaluator moves the reduced IR members.
/// The reduced intermediate representation consists of a list of function definitions, and a block
/// of entrypoint statements. In a repl or script context this can be an arbitrary list of
/// statements, in an executable context will likely just be a pointer to the main() function.
#[derive(Debug)]
pub struct ReducedIR {
pub functions: HashMap<DefId, FunctionDefinition>,
pub entrypoint: Vec<Statement>,
}
impl ReducedIR {
#[allow(dead_code)]
pub fn debug(&self, symbol_table: &SymbolTable) {
println!("Reduced IR:");
println!("Functions:");
println!("-----------");
for (id, callable) in self.functions.iter() {
let name = &symbol_table.lookup_symbol_by_def(id).unwrap().local_name();
println!("{}({}) -> {:?}", id, name, callable);
}
println!();
println!("Entrypoint:");
println!("-----------");
for stmt in self.entrypoint.iter() {
println!("{:?}", stmt);
}
println!("-----------");
}
}
#[derive(Debug, Clone)]
pub enum Statement {
Expression(Expression),
Binding { id: DefId, constant: bool, expr: Expression },
Return(Expression),
Continue,
Break,
}
#[derive(Debug, Clone)]
pub enum Expression {
Literal(Literal),
Tuple(Vec<Expression>),
List(Vec<Expression>),
Lookup(Lookup),
Assign { lval: DefId, rval: Box<Expression> },
Access { name: String, expr: Box<Expression> },
Callable(Callable),
Call { f: Box<Expression>, args: Vec<Expression> },
CallMethod { f: Box<Expression>, args: Vec<Expression>, self_expr: Box<Expression> },
Conditional { cond: Box<Expression>, then_clause: Vec<Statement>, else_clause: Vec<Statement> },
CaseMatch { cond: Box<Expression>, alternatives: Vec<Alternative> },
Loop { cond: Box<Expression>, statements: Vec<Statement> },
Index { indexee: Box<Expression>, indexer: Box<Expression> },
ReductionError(String),
}
impl Expression {
pub fn unit() -> Self {
Expression::Tuple(vec![])
}
}
#[derive(Debug)]
pub struct FunctionDefinition {
pub body: Vec<Statement>,
}
#[derive(Debug, Clone)]
pub enum Callable {
Builtin(Builtin),
UserDefined(DefId),
Lambda { arity: u8, body: Vec<Statement> },
DataConstructor { type_id: TypeId, tag: u32 },
RecordConstructor { type_id: TypeId, tag: u32, field_order: Vec<String> },
}
#[derive(Debug, Clone)]
pub enum Lookup {
LocalVar(DefId),
GlobalVar(DefId),
Function(DefId),
Param(u8),
SelfParam,
}
#[derive(Debug, Clone, PartialEq)]
pub enum Literal {
Nat(u64),
Int(i64),
Float(f64),
Bool(bool),
StringLit(Rc<String>),
}
#[derive(Debug, Clone)]
pub struct Alternative {
pub pattern: Pattern,
pub item: Vec<Statement>,
}
#[derive(Debug, Clone)]
pub enum Pattern {
Tuple { subpatterns: Vec<Pattern>, tag: Option<u32> },
Record { tag: u32, subpatterns: Vec<(Rc<String>, Pattern)> },
Literal(Literal),
Ignored,
Binding(DefId),
}
#[allow(dead_code)]
#[derive(Debug)]
pub struct PatternError {
msg: String,
}
impl From<&str> for PatternError {
fn from(s: &str) -> Self {
Self { msg: s.to_string() }
}
}
impl From<String> for PatternError {
fn from(msg: String) -> Self {
Self { msg }
}
}

View File

@ -1,210 +0,0 @@
use schala_repl::{
ComputationRequest, ComputationResponse, GlobalOutputStats, LangMetaRequest, LangMetaResponse,
ProgrammingLanguageInterface,
};
use stopwatch::Stopwatch;
use crate::{error::SchalaError, parsing, reduced_ir, symbol_table, tree_walk_eval, type_inference};
/// All the state necessary to parse and execute a Schala program are stored in this struct.
pub struct Schala<'a> {
/// Holds a reference to the original source code, parsed into line and character
source_reference: SourceReference,
//state: eval::State<'static>,
/// Keeps track of symbols and scopes
symbol_table: symbol_table::SymbolTable,
/// Contains information for type-checking
type_context: type_inference::TypeContext,
/// Schala Parser
active_parser: parsing::Parser,
/// Execution state for AST-walking interpreter
eval_state: tree_walk_eval::State<'a>,
timings: Vec<(&'static str, std::time::Duration)>,
}
/*
impl Schala {
//TODO implement documentation for language items
/*
fn handle_docs(&self, source: String) -> LangMetaResponse {
LangMetaResponse::Docs {
doc_string: format!("Schala item `{}` : <<Schala-lang documentation not yet implemented>>", source)
}
}
*/
}
*/
impl<'a> Schala<'a> {
/// Creates a new Schala environment *without* any prelude.
fn new_blank_env() -> Schala<'a> {
Schala {
source_reference: SourceReference::new(),
symbol_table: symbol_table::SymbolTable::new(),
type_context: type_inference::TypeContext::new(),
active_parser: parsing::Parser::new(),
eval_state: tree_walk_eval::State::new(),
timings: Vec::new(),
}
}
/// Creates a new Schala environment with the standard prelude, which is defined as ordinary
/// Schala code in the file `prelude.schala`
#[allow(clippy::new_without_default)]
pub fn new() -> Schala<'a> {
let prelude = include_str!("../source-files/prelude.schala");
let mut env = Schala::new_blank_env();
let response = env.run_pipeline(prelude, SchalaConfig::default());
if let Err(err) = response {
panic!("Error in prelude, panicking: {}", err.display());
}
env
}
/// This is where the actual action of interpreting/compilation happens.
/// Note: this should eventually use a query-based system for parallelization, cf.
/// https://rustc-dev-guide.rust-lang.org/overview.html
fn run_pipeline(&mut self, source: &str, config: SchalaConfig) -> Result<String, SchalaError> {
self.timings = vec![];
let sw = Stopwatch::start_new();
self.source_reference.load_new_source(source);
let ast = self
.active_parser
.parse(source)
.map_err(|err| SchalaError::from_parse_error(err, &self.source_reference))?;
self.timings.push(("parsing", sw.elapsed()));
let sw = Stopwatch::start_new();
//Perform all symbol table work
self.symbol_table
.process_ast(&ast, &mut self.type_context)
.map_err(SchalaError::from_symbol_table)?;
self.timings.push(("symbol_table", sw.elapsed()));
// Typechecking
let _overall_type = self.type_context.typecheck(&ast).map_err(SchalaError::from_type_error);
let sw = Stopwatch::start_new();
let reduced_ir = reduced_ir::reduce(&ast, &self.symbol_table, &self.type_context);
self.timings.push(("reduced_ir", sw.elapsed()));
let sw = Stopwatch::start_new();
let evaluation_outputs = self.eval_state.evaluate(reduced_ir, &self.type_context, config.repl);
self.timings.push(("tree-walking-evaluation", sw.elapsed()));
let text_output: Result<Vec<String>, String> = evaluation_outputs.into_iter().collect();
let text_output: Result<Vec<String>, SchalaError> =
text_output.map_err(|err| SchalaError::from_string(err, Stage::Evaluation));
let eval_output: String =
text_output.map(|v| Iterator::intersperse(v.into_iter(), "\n".to_owned()).collect())?;
Ok(eval_output)
}
}
/// Represents lines of source code
pub(crate) struct SourceReference {
last_source: Option<String>,
/// Offsets in *bytes* (not chars) representing a newline character
newline_offsets: Vec<usize>,
}
impl SourceReference {
pub(crate) fn new() -> SourceReference {
SourceReference { last_source: None, newline_offsets: vec![] }
}
pub(crate) fn load_new_source(&mut self, source: &str) {
self.newline_offsets = vec![];
for (offset, ch) in source.as_bytes().iter().enumerate() {
if *ch == b'\n' {
self.newline_offsets.push(offset);
}
}
self.last_source = Some(source.to_string());
}
// (line_start, line_num, the string itself)
pub fn get_line(&self, line: usize) -> (usize, usize, String) {
if self.newline_offsets.is_empty() {
return (0, 0, self.last_source.as_ref().cloned().unwrap());
}
//TODO make sure this is utf8-safe
let start_idx = match self.newline_offsets.binary_search(&line) {
Ok(index) | Err(index) => index,
};
let last_source = self.last_source.as_ref().unwrap();
let start = self.newline_offsets[start_idx];
let end = self.newline_offsets.get(start_idx + 1).cloned().unwrap_or_else(|| last_source.len());
let slice = &last_source.as_bytes()[start..end];
(start, start_idx, std::str::from_utf8(slice).unwrap().to_string())
}
}
#[allow(dead_code)]
#[derive(Clone, Copy, Debug)]
pub(crate) enum Stage {
Parsing,
Symbols,
ScopeResolution,
Typechecking,
AstReduction,
Evaluation,
}
fn stage_names() -> Vec<&'static str> {
vec!["parsing", "symbol-table", "typechecking", "ast-reduction", "ast-walking-evaluation"]
}
#[derive(Default, Clone)]
pub struct SchalaConfig {
pub repl: bool,
}
impl<'a> ProgrammingLanguageInterface for Schala<'a> {
//TODO flesh out Config
type Config = SchalaConfig;
fn language_name() -> String {
"Schala".to_owned()
}
fn source_file_suffix() -> String {
"schala".to_owned()
}
fn run_computation(&mut self, request: ComputationRequest<Self::Config>) -> ComputationResponse {
let ComputationRequest { source, debug_requests: _, config: _ } = request;
let sw = Stopwatch::start_new();
let main_output =
self.run_pipeline(source, request.config).map_err(|schala_err| schala_err.display());
let total_duration = sw.elapsed();
let stage_durations: Vec<_> = std::mem::take(&mut self.timings)
.into_iter()
.map(|(label, duration)| (label.to_string(), duration))
.collect();
let global_output_stats = GlobalOutputStats { total_duration, stage_durations };
ComputationResponse { main_output, global_output_stats, debug_responses: vec![] }
}
fn request_meta(&mut self, request: LangMetaRequest) -> LangMetaResponse {
match request {
LangMetaRequest::StageNames =>
LangMetaResponse::StageNames(stage_names().iter().map(|s| s.to_string()).collect()),
_ => LangMetaResponse::Custom { kind: "not-implemented".to_string(), value: "".to_string() },
}
}
}

View File

@ -1,65 +0,0 @@
use std::{fmt, rc::Rc};
/// Fully-qualified symbol name
#[derive(Debug, Clone, Eq, PartialEq, Hash, PartialOrd, Ord)]
pub struct Fqsn {
//TODO Fqsn's need to be cheaply cloneable
pub scopes: Vec<ScopeSegment>,
}
impl Fqsn {
pub fn from_scope_stack(scopes: &[ScopeSegment], new_name: Rc<String>) -> Self {
let mut v = Vec::new();
for s in scopes {
v.push(s.clone());
}
v.push(ScopeSegment::Name(new_name));
Fqsn { scopes: v }
}
pub fn extend(&self, new_item: &str) -> Self {
let mut new = self.clone();
new.scopes.push(ScopeSegment::Name(Rc::new(new_item.to_string())));
new
}
#[allow(dead_code)]
pub fn from_strs(strs: &[&str]) -> Fqsn {
let mut scopes = vec![];
for s in strs {
scopes.push(ScopeSegment::Name(Rc::new(s.to_string())));
}
Fqsn { scopes }
}
pub fn last_elem(&self) -> Rc<String> {
let ScopeSegment::Name(name) = self.scopes.last().unwrap();
name.clone()
}
}
impl fmt::Display for Fqsn {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
let delim = "::";
let Fqsn { scopes } = self;
write!(f, "FQSN<{}", scopes[0])?;
for item in scopes[1..].iter() {
write!(f, "{}{}", delim, item)?;
}
write!(f, ">")
}
}
//TODO eventually this should use ItemId's to avoid String-cloning
/// One segment within a scope.
#[derive(Debug, Clone, Eq, PartialEq, Hash, PartialOrd, Ord)]
pub enum ScopeSegment {
Name(Rc<String>),
}
impl fmt::Display for ScopeSegment {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
let ScopeSegment::Name(name) = self;
write!(f, "{}", name)
}
}

View File

@ -1,244 +0,0 @@
#![allow(clippy::enum_variant_names)]
use std::{
collections::{hash_map::Entry, HashMap},
fmt,
rc::Rc,
};
use crate::{
ast,
ast::ItemId,
builtin::Builtin,
parsing::Location,
type_inference::{TypeContext, TypeId},
};
mod populator;
use populator::SymbolTablePopulator;
mod fqsn;
pub use fqsn::{Fqsn, ScopeSegment};
mod resolver;
mod symbol_trie;
use symbol_trie::SymbolTrie;
mod test;
use crate::identifier::{define_id_kind, Id, IdStore};
define_id_kind!(DefItem);
pub type DefId = Id<DefItem>;
#[allow(dead_code)]
#[derive(Debug, Clone)]
pub enum SymbolError {
DuplicateName { prev_name: Fqsn, location: Location },
DuplicateVariant { type_fqsn: Fqsn, name: String },
DuplicateRecord { type_fqsn: Fqsn, location: Location, record: String, member: String },
UnknownAnnotation { name: String },
BadAnnotation { name: String, msg: String },
BadImplBlockEntry,
}
#[allow(dead_code)]
#[derive(Debug)]
struct NameSpec<K> {
location: Location,
kind: K,
}
#[derive(Debug)]
enum NameKind {
Module,
Function,
Binding,
}
#[derive(Debug)]
enum TypeKind {
Function,
Constructor,
}
/// Keeps track of what names were used in a given namespace.
struct NameTable<K> {
table: HashMap<Fqsn, NameSpec<K>>,
}
impl<K> NameTable<K> {
fn new() -> Self {
Self { table: HashMap::new() }
}
fn register(&mut self, name: Fqsn, spec: NameSpec<K>) -> Result<(), SymbolError> {
match self.table.entry(name.clone()) {
Entry::Occupied(o) =>
Err(SymbolError::DuplicateName { prev_name: name, location: o.get().location }),
Entry::Vacant(v) => {
v.insert(spec);
Ok(())
}
}
}
}
//cf. p. 150 or so of Language Implementation Patterns
pub struct SymbolTable {
def_id_store: IdStore<DefItem>,
/// Used for import resolution.
symbol_trie: SymbolTrie,
/// These tables are responsible for preventing duplicate names.
fq_names: NameTable<NameKind>, //Note that presence of two tables implies that a type and other binding with the same name can co-exist
types: NameTable<TypeKind>,
id_to_def: HashMap<ItemId, DefId>,
def_to_symbol: HashMap<DefId, Rc<Symbol>>,
}
impl SymbolTable {
/// Create a new, empty SymbolTable
pub fn new() -> Self {
Self {
def_id_store: IdStore::new(),
symbol_trie: SymbolTrie::new(),
fq_names: NameTable::new(),
types: NameTable::new(),
id_to_def: HashMap::new(),
def_to_symbol: HashMap::new(),
}
}
/// The main entry point into the symbol table. This will traverse the AST in several
/// different ways and populate subtables with information that will be used further in the
/// compilation process.
pub fn process_ast(
&mut self,
ast: &ast::AST,
type_context: &mut TypeContext,
) -> Result<(), Vec<SymbolError>> {
let mut populator = SymbolTablePopulator { type_context, table: self };
let errs = populator.populate_definition_tables(ast);
if !errs.is_empty() {
return Err(errs);
}
// Walks the AST, matching the ID of an identifier used in some expression to
// the corresponding Symbol.
let mut resolver = resolver::ScopeResolver::new(self);
resolver.resolve(ast);
Ok(())
}
pub fn lookup_symbol(&self, id: &ItemId) -> Option<&Symbol> {
let def = self.id_to_def.get(id)?;
self.def_to_symbol.get(def).map(|s| s.as_ref())
}
pub fn lookup_symbol_by_def(&self, def: &DefId) -> Option<&Symbol> {
self.def_to_symbol.get(def).map(|s| s.as_ref())
}
#[allow(dead_code)]
pub fn debug(&self) {
println!("Symbol table:");
println!("----------------");
for (id, def) in self.id_to_def.iter() {
if let Some(symbol) = self.def_to_symbol.get(def) {
println!("{} => {}: {}", id, def, symbol);
} else {
println!("{} => {} <NO SYMBOL FOUND>", id, def);
}
}
}
/// Register a new mapping of a fully-qualified symbol name (e.g. `Option::Some`)
/// to a Symbol, a descriptor of what that name refers to.
fn add_symbol(&mut self, id: &ItemId, fqsn: Fqsn, spec: SymbolSpec) {
let def_id = self.def_id_store.fresh();
let local_name = fqsn.last_elem();
let symbol = Rc::new(Symbol { fully_qualified_name: fqsn.clone(), local_name, spec, def_id });
self.symbol_trie.insert(&fqsn, def_id);
self.id_to_def.insert(*id, def_id);
self.def_to_symbol.insert(def_id, symbol);
}
fn populate_single_builtin(&mut self, fqsn: Fqsn, builtin: Builtin) {
let def_id = self.def_id_store.fresh();
let spec = SymbolSpec::Builtin(builtin);
let local_name = fqsn.last_elem();
let symbol = Rc::new(Symbol { fully_qualified_name: fqsn.clone(), local_name, spec, def_id });
self.symbol_trie.insert(&fqsn, def_id);
self.def_to_symbol.insert(def_id, symbol);
}
}
#[allow(dead_code)]
#[derive(Debug, Clone)]
pub struct Symbol {
fully_qualified_name: Fqsn,
local_name: Rc<String>,
spec: SymbolSpec,
def_id: DefId,
}
impl Symbol {
pub fn local_name(&self) -> &str {
self.local_name.as_ref()
}
pub fn def_id(&self) -> DefId {
self.def_id
}
pub fn spec(&self) -> SymbolSpec {
self.spec.clone()
}
}
impl fmt::Display for Symbol {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
write!(f, "<Local name: {}, {}, Spec: {}>", self.local_name(), self.fully_qualified_name, self.spec)
}
}
//TODO - I think I eventually want to draw a distinction between true global items
//i.e. global vars, and items whose definitions are scoped. Right now there's a sense
//in which Func, DataConstructor, RecordConstructor, and GlobalBinding are "globals",
//whereas LocalVarible and FunctionParam have local scope. But right now, they all
//get put into a common table, and all get DefId's from a common source.
//
//It would be good if individual functions could in parallel look up their own
//local vars without interfering with other lookups. Also some type definitions
//should be scoped in a similar way.
//
//Also it makes sense that non-globals should not use DefId's, particularly not
//function parameters (even though they are currently assigned).
#[derive(Debug, Clone)]
pub enum SymbolSpec {
Builtin(Builtin),
Func { method: Option<crate::ast::TypeSingletonName> },
DataConstructor { tag: u32, type_id: TypeId },
RecordConstructor { tag: u32, type_id: TypeId },
GlobalBinding, //Only for global variables, not for function-local ones or ones within a `let` scope context
LocalVariable,
FunctionParam(u8),
}
impl fmt::Display for SymbolSpec {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
use self::SymbolSpec::*;
match self {
Builtin(b) => write!(f, "Builtin: {:?}", b),
Func { .. } => write!(f, "Func"),
DataConstructor { tag, type_id } => write!(f, "DataConstructor(tag: {}, type: {})", tag, type_id),
RecordConstructor { type_id, tag, .. } =>
write!(f, "RecordConstructor(tag: {})(<members> -> {})", tag, type_id),
GlobalBinding => write!(f, "GlobalBinding"),
LocalVariable => write!(f, "Local variable"),
FunctionParam(n) => write!(f, "Function param: {}", n),
}
}
}

View File

@ -1,352 +0,0 @@
use std::{
collections::{hash_map::Entry, HashMap, HashSet},
rc::Rc,
str::FromStr,
};
use super::{Fqsn, NameKind, NameSpec, ScopeSegment, SymbolError, SymbolSpec, SymbolTable, TypeKind};
use crate::{
ast::{
Declaration, Expression, ExpressionKind, ItemId, Statement, StatementKind, TypeBody,
TypeSingletonName, Variant, VariantKind, AST,
},
builtin::Builtin,
parsing::Location,
type_inference::{self, PendingType, TypeBuilder, TypeContext, VariantBuilder},
};
pub(super) struct SymbolTablePopulator<'a> {
pub(super) type_context: &'a mut TypeContext,
pub(super) table: &'a mut SymbolTable,
}
impl<'a> SymbolTablePopulator<'a> {
/* note: this adds names for *forward reference* but doesn't actually create any types. solve that problem
* later */
fn add_symbol(&mut self, id: &ItemId, fqsn: Fqsn, spec: SymbolSpec) {
self.table.add_symbol(id, fqsn, spec)
}
/// This function traverses the AST and adds symbol table entries for
/// constants, functions, types, and modules defined within. This simultaneously
/// checks for dupicate definitions (and returns errors if discovered), and sets
/// up name tables that will be used by further parts of the compiler
pub fn populate_definition_tables(&mut self, ast: &AST) -> Vec<SymbolError> {
let mut scope_stack = vec![];
self.add_from_scope(ast.statements.as_ref(), &mut scope_stack, false)
}
fn add_from_scope(
&mut self,
statements: &[Statement<StatementKind>],
scope_stack: &mut Vec<ScopeSegment>,
function_scope: bool,
) -> Vec<SymbolError> {
let mut errors = vec![];
for statement in statements {
let Statement { id, kind, location } = statement;
let location = *location;
if let Err(err) = self.add_single_statement(id, kind, location, scope_stack, function_scope) {
errors.push(err);
} else {
let decl = match kind {
StatementKind::Declaration(decl) => decl,
_ => continue,
};
// If there's an error with a name, don't recurse into subscopes of that name
let recursive_errs = match decl {
Declaration::FuncDecl(signature, body) => {
let new_scope = ScopeSegment::Name(signature.name.clone());
scope_stack.push(new_scope);
let output = self.add_from_scope(body.as_ref(), scope_stack, true);
scope_stack.pop();
output
}
Declaration::Module { name, items } => {
let new_scope = ScopeSegment::Name(name.clone());
scope_stack.push(new_scope);
let output = self.add_from_scope(items.as_ref(), scope_stack, false);
scope_stack.pop();
output
}
Declaration::TypeDecl { name, body, mutable } => {
let type_fqsn = Fqsn::from_scope_stack(scope_stack, name.name.clone());
self.add_type_members(name, body, mutable, location, type_fqsn)
}
Declaration::Impl { type_name, interface_name: _, block } => {
let mut errors = vec![];
let new_scope = ScopeSegment::Name(Rc::new(format!("<impl-block>{}", type_name)));
scope_stack.push(new_scope);
for decl_stmt in block.iter() {
let Statement { id, kind, location } = decl_stmt;
let location = *location;
match kind {
decl @ Declaration::FuncDecl(signature, body) => {
let output =
self.add_single_declaration(id, decl, location, scope_stack, true);
if let Err(e) = output {
errors.push(e);
};
let new_scope = ScopeSegment::Name(signature.name.clone());
scope_stack.push(new_scope);
let output = self.add_from_scope(body.as_ref(), scope_stack, true);
scope_stack.pop();
errors.extend(output.into_iter());
}
_other => errors.push(SymbolError::BadImplBlockEntry),
};
}
scope_stack.pop();
errors
}
_ => vec![],
};
errors.extend(recursive_errs.into_iter());
}
}
errors
}
fn add_single_statement(
&mut self,
id: &ItemId,
kind: &StatementKind,
location: Location,
scope_stack: &[ScopeSegment],
function_scope: bool,
) -> Result<(), SymbolError> {
match kind {
StatementKind::Declaration(decl) =>
self.add_single_declaration(id, decl, location, scope_stack, function_scope),
_ => return Ok(()),
}
}
fn add_single_declaration(
&mut self,
id: &ItemId,
decl: &Declaration,
location: Location,
scope_stack: &[ScopeSegment],
function_scope: bool,
) -> Result<(), SymbolError> {
match decl {
Declaration::FuncSig(signature) => {
let fq_function = Fqsn::from_scope_stack(scope_stack, signature.name.clone());
self.table
.fq_names
.register(fq_function.clone(), NameSpec { location, kind: NameKind::Function })?;
self.table
.types
.register(fq_function.clone(), NameSpec { location, kind: TypeKind::Function })?;
self.add_symbol(id, fq_function, SymbolSpec::Func { method: None });
}
Declaration::FuncDecl(signature, ..) => {
let fn_name = &signature.name;
let fq_function = Fqsn::from_scope_stack(scope_stack, fn_name.clone());
self.table
.fq_names
.register(fq_function.clone(), NameSpec { location, kind: NameKind::Function })?;
self.table
.types
.register(fq_function.clone(), NameSpec { location, kind: TypeKind::Function })?;
self.add_symbol(id, fq_function, SymbolSpec::Func { method: None });
}
Declaration::TypeDecl { name, .. } => {
let fq_type = Fqsn::from_scope_stack(scope_stack, name.name.clone());
self.table.types.register(fq_type, NameSpec { location, kind: TypeKind::Constructor })?;
}
//TODO handle type aliases
Declaration::TypeAlias { .. } => (),
Declaration::Binding { name, .. } => {
let fq_binding = Fqsn::from_scope_stack(scope_stack, name.clone());
self.table
.fq_names
.register(fq_binding.clone(), NameSpec { location, kind: NameKind::Binding })?;
if !function_scope {
self.add_symbol(id, fq_binding, SymbolSpec::GlobalBinding);
}
}
//TODO implement interfaces
Declaration::Interface { .. } => (),
Declaration::Impl { .. } => (),
Declaration::Module { name, .. } => {
let fq_module = Fqsn::from_scope_stack(scope_stack, name.clone());
self.table.fq_names.register(fq_module, NameSpec { location, kind: NameKind::Module })?;
}
Declaration::Annotation { name, arguments, inner } => {
let inner = inner.as_ref();
self.add_single_statement(
&inner.id,
&inner.kind,
inner.location,
scope_stack,
function_scope,
)?;
self.process_annotation(name.as_ref(), arguments.as_slice(), scope_stack, inner)?;
}
}
Ok(())
}
fn process_annotation(
&mut self,
name: &str,
arguments: &[Expression],
scope_stack: &[ScopeSegment],
inner: &Statement<StatementKind>,
) -> Result<(), SymbolError> {
if name == "register_builtin" {
if let Statement {
id: _,
location: _,
kind: StatementKind::Declaration(Declaration::FuncDecl(sig, _)),
} = inner
{
let fqsn = Fqsn::from_scope_stack(scope_stack, sig.name.clone());
let builtin_name = match arguments {
[Expression { kind: ExpressionKind::Value(qname), .. }]
if qname.components.len() == 1 =>
qname.components[0].clone(),
_ =>
return Err(SymbolError::BadAnnotation {
name: name.to_string(),
msg: "Bad argument for register_builtin".to_string(),
}),
};
let builtin =
Builtin::from_str(builtin_name.as_str()).map_err(|_| SymbolError::BadAnnotation {
name: name.to_string(),
msg: format!("Invalid builtin: {}", builtin_name),
})?;
self.table.populate_single_builtin(fqsn, builtin);
Ok(())
} else {
Err(SymbolError::BadAnnotation {
name: name.to_string(),
msg: "register_builtin not annotating a function".to_string(),
})
}
} else {
Err(SymbolError::UnknownAnnotation { name: name.to_string() })
}
}
fn add_type_members(
&mut self,
type_name: &TypeSingletonName,
type_body: &TypeBody,
_mutable: &bool,
location: Location,
type_fqsn: Fqsn,
) -> Vec<SymbolError> {
let (variants, immediate_variant) = match type_body {
TypeBody::Variants(variants) => (variants.clone(), false),
TypeBody::ImmediateRecord { id, fields } => (
vec![Variant {
id: *id,
name: type_name.name.clone(),
kind: VariantKind::Record(fields.clone()),
}],
true,
),
};
// Check for duplicates before registering any types with the TypeContext
let mut seen_variants = HashSet::new();
let mut errors = vec![];
for variant in variants.iter() {
if seen_variants.contains(&variant.name) {
errors.push(SymbolError::DuplicateVariant {
type_fqsn: type_fqsn.clone(),
name: variant.name.as_ref().to_string(),
})
}
seen_variants.insert(variant.name.clone());
if let VariantKind::Record(ref members) = variant.kind {
let mut seen_members = HashMap::new();
for (member_name, _) in members.iter() {
match seen_members.entry(member_name.as_ref()) {
Entry::Occupied(o) => {
let location = *o.get();
errors.push(SymbolError::DuplicateRecord {
type_fqsn: type_fqsn.clone(),
location,
record: variant.name.as_ref().to_string(),
member: member_name.as_ref().to_string(),
});
}
//TODO eventually this should track meaningful locations
Entry::Vacant(v) => {
v.insert(location);
}
}
}
}
}
if !errors.is_empty() {
return errors;
}
let mut type_builder = TypeBuilder::new(type_name.name.as_ref());
let mut variant_name_map = HashMap::new();
for variant in variants.iter() {
let Variant { name, kind, id } = variant;
variant_name_map.insert(name.clone(), id);
let mut variant_builder = VariantBuilder::new(name.as_ref());
match kind {
VariantKind::UnitStruct => (),
VariantKind::TupleStruct(items) =>
for type_identifier in items {
let pending: PendingType = type_identifier.into();
variant_builder.add_member(pending);
},
VariantKind::Record(members) =>
for (field_name, type_identifier) in members.iter() {
let pending: PendingType = type_identifier.into();
variant_builder.add_record_member(field_name.as_ref(), pending);
},
}
type_builder.add_variant(variant_builder);
}
let type_id = self.type_context.register_type(type_builder);
let type_definition = self.type_context.lookup_type(&type_id).unwrap();
// This index is guaranteed to be the correct tag
for (index, variant) in type_definition.variants.iter().enumerate() {
let id = variant_name_map.get(&variant.name).unwrap();
let tag = index as u32;
let spec = match &variant.members {
type_inference::VariantMembers::Unit => SymbolSpec::DataConstructor { tag, type_id },
type_inference::VariantMembers::Tuple(..) => SymbolSpec::DataConstructor { tag, type_id },
type_inference::VariantMembers::Record(..) => SymbolSpec::RecordConstructor { tag, type_id },
};
self.table.add_symbol(id, type_fqsn.extend(&variant.name), spec);
}
if immediate_variant {
let variant = &type_definition.variants[0];
let id = variant_name_map.get(&variant.name).unwrap();
let spec = SymbolSpec::RecordConstructor { tag: 0, type_id };
self.table.add_symbol(id, type_fqsn, spec);
}
vec![]
}
}

View File

@ -1,253 +0,0 @@
use std::rc::Rc;
use crate::{
ast::*,
symbol_table::{Fqsn, ScopeSegment, SymbolSpec, SymbolTable},
util::ScopeStack,
};
#[derive(Debug)]
enum NameType {
//TODO eventually this needs to support closures
Param(u8),
LocalVariable(ItemId),
LocalFunction(ItemId),
Import(Fqsn),
}
type LexScope<'a> = ScopeStack<'a, Rc<String>, NameType, ScopeType>;
#[derive(Debug)]
enum ScopeType {
Function { name: Rc<String> },
Lambda,
PatternMatch,
ImplBlock,
//TODO add some notion of a let-like scope?
}
pub struct ScopeResolver<'a> {
symbol_table: &'a mut super::SymbolTable,
lexical_scopes: LexScope<'a>,
}
impl<'a> ScopeResolver<'a> {
pub fn new(symbol_table: &'a mut SymbolTable) -> Self {
let lexical_scopes = ScopeStack::new(None);
Self { symbol_table, lexical_scopes }
}
pub fn resolve(&mut self, ast: &AST) {
walk_ast(self, ast);
}
/// This method correctly modifies the id_to_def table (ItemId) to have the appropriate
/// mappings.
fn lookup_name_in_scope(&mut self, name: &QualifiedName) {
//TODO this method badly needs attention
let QualifiedName { id, components } = name;
let local_name = components.first().unwrap().clone();
let name_type = self.lexical_scopes.lookup(&local_name);
let fqsn = Fqsn { scopes: components.iter().map(|name| ScopeSegment::Name(name.clone())).collect() };
let def_id = self.symbol_table.symbol_trie.lookup(&fqsn);
//TODO handle a "partial" qualified name, and also handle it down in the pattern-matching
//section
if components.len() == 1 {
match name_type {
Some(NameType::Import(fqsn)) => {
let def_id = self.symbol_table.symbol_trie.lookup(fqsn);
if let Some(def_id) = def_id {
self.symbol_table.id_to_def.insert(*id, def_id);
}
}
Some(NameType::Param(n)) => {
let spec = SymbolSpec::FunctionParam(*n);
//TODO need to come up with a better solution for local variable FQSNs
let lscope = ScopeSegment::Name(Rc::new("<local-param>".to_string()));
let fqsn = Fqsn { scopes: vec![lscope, ScopeSegment::Name(local_name.clone())] };
self.symbol_table.add_symbol(id, fqsn, spec);
}
Some(NameType::LocalFunction(item_id)) => {
let def_id = self.symbol_table.id_to_def.get(item_id);
if let Some(def_id) = def_id {
let def_id = *def_id;
self.symbol_table.id_to_def.insert(*id, def_id);
}
}
Some(NameType::LocalVariable(item_id)) => {
let def_id = self.symbol_table.id_to_def.get(item_id);
if let Some(def_id) = def_id {
let def_id = *def_id;
self.symbol_table.id_to_def.insert(*id, def_id);
}
}
None =>
if let Some(def_id) = def_id {
self.symbol_table.id_to_def.insert(*id, def_id);
},
}
} else if let Some(def_id) = def_id {
self.symbol_table.id_to_def.insert(*id, def_id);
}
}
}
impl<'a> ASTVisitor for ScopeResolver<'a> {
// Import statements bring in a bunch of local names that all map to a specific FQSN.
// FQSNs map to a Symbol (or this is an error), Symbols have a DefId. So for every
// name we import, we map a local name (a string) to a NameType::ImportedDefinition(DefId).
fn import(&mut self, import_spec: &ImportSpecifier) -> Recursion {
let ImportSpecifier { ref path_components, ref imported_names, .. } = &import_spec;
match imported_names {
ImportedNames::All => {
let prefix =
Fqsn { scopes: path_components.iter().map(|c| ScopeSegment::Name(c.clone())).collect() };
let members = self.symbol_table.symbol_trie.get_children(&prefix);
for fqsn in members.into_iter() {
self.lexical_scopes.insert(fqsn.last_elem(), NameType::Import(fqsn));
}
}
ImportedNames::LastOfPath => {
let fqsn =
Fqsn { scopes: path_components.iter().map(|c| ScopeSegment::Name(c.clone())).collect() };
self.lexical_scopes.insert(fqsn.last_elem(), NameType::Import(fqsn));
}
ImportedNames::List(ref names) => {
let fqsn_prefix: Vec<ScopeSegment> =
path_components.iter().map(|c| ScopeSegment::Name(c.clone())).collect();
for name in names.iter() {
let mut scopes = fqsn_prefix.clone();
scopes.push(ScopeSegment::Name(name.clone()));
let fqsn = Fqsn { scopes };
self.lexical_scopes.insert(fqsn.last_elem(), NameType::Import(fqsn));
}
}
};
Recursion::Continue
}
fn declaration(&mut self, declaration: &Declaration, id: &ItemId) -> Recursion {
let cur_function_name = match self.lexical_scopes.get_name() {
//TODO this needs to be a fqsn
Some(ScopeType::Function { name }) => Some(name.clone()),
_ => None,
};
match declaration {
Declaration::FuncDecl(signature, block) => {
let param_names = signature.params.iter().map(|param| param.name.clone());
//TODO I'm 90% sure this is right, until I get to closures
//let mut new_scope = self.lexical_scopes.new_scope(Some(ScopeType::Function { name: signature.name.clone() }));
//TODO this will recurse unwantedly into scopes; need to pop an outer function
//scope off first before going into a non-closure scope
let mut new_scope =
ScopeStack::new(Some(ScopeType::Function { name: signature.name.clone() }));
for (n, param) in param_names.enumerate() {
new_scope.insert(param, NameType::Param(n as u8));
}
self.lexical_scopes.insert(signature.name.clone(), NameType::LocalFunction(*id));
let mut new_resolver =
ScopeResolver { symbol_table: self.symbol_table, lexical_scopes: new_scope };
walk_block(&mut new_resolver, block);
Recursion::Stop
}
Declaration::Binding { name, .. } => {
if let Some(fn_name) = cur_function_name {
// We are within a function scope
let fqsn =
Fqsn { scopes: vec![ScopeSegment::Name(fn_name), ScopeSegment::Name(name.clone())] };
self.symbol_table.add_symbol(id, fqsn, SymbolSpec::LocalVariable);
self.lexical_scopes.insert(name.clone(), NameType::LocalVariable(*id));
}
Recursion::Continue
}
Declaration::Impl { block, .. } => {
let new_scope = ScopeStack::new(Some(ScopeType::ImplBlock));
let mut new_resolver =
ScopeResolver { symbol_table: self.symbol_table, lexical_scopes: new_scope };
for stmt in block.iter() {
walk_declaration(&mut new_resolver, &stmt.kind, &stmt.id);
}
Recursion::Stop
}
_ => Recursion::Continue,
}
}
fn expression(&mut self, expression: &Expression) -> Recursion {
use ExpressionKind::*;
match &expression.kind {
Value(name) => {
self.lookup_name_in_scope(name);
}
NamedStruct { name, fields: _ } => {
self.lookup_name_in_scope(name);
}
Lambda { params, body, .. } => {
let param_names = params.iter().map(|param| param.name.clone());
//TODO need to properly handle closure scope, this is currently broken
//let mut new_scope = self.lexical_scopes.new_scope(Some(ScopeType::Function { name: signature.name.clone() }));
let mut new_scope = ScopeStack::new(Some(ScopeType::Lambda));
for (n, param) in param_names.enumerate() {
new_scope.insert(param, NameType::Param(n as u8));
}
let mut new_resolver =
ScopeResolver { symbol_table: self.symbol_table, lexical_scopes: new_scope };
walk_block(&mut new_resolver, body);
return Recursion::Stop;
}
IfExpression { discriminator, body } => {
if let Some(d) = discriminator.as_ref() {
walk_expression(self, d);
}
let mut resolver = ScopeResolver {
lexical_scopes: self.lexical_scopes.new_scope(Some(ScopeType::PatternMatch)),
symbol_table: self.symbol_table,
};
walk_if_expr_body(&mut resolver, body);
return Recursion::Stop;
}
_ => (),
}
Recursion::Continue
}
fn pattern(&mut self, pat: &Pattern) -> Recursion {
use Pattern::*;
match pat {
Literal(..) | Ignored | TuplePattern(..) => (),
TupleStruct(name, _) | Record(name, _) => {
self.lookup_name_in_scope(name);
}
//TODO this isn't really the right syntax for a VarOrName
VarOrName(QualifiedName { id, components }) => {
if components.len() == 1 {
//TODO need a better way to construct a FQSN from a QualifiedName
let local_name: Rc<String> = components[0].clone();
let lscope = ScopeSegment::Name(Rc::new("<local-case-match>".to_string()));
let fqsn = Fqsn { scopes: vec![lscope, ScopeSegment::Name(local_name.clone())] };
self.symbol_table.add_symbol(id, fqsn, SymbolSpec::LocalVariable);
self.lexical_scopes.insert(local_name, NameType::LocalVariable(*id));
} else {
let fqsn = Fqsn {
scopes: components.iter().map(|name| ScopeSegment::Name(name.clone())).collect(),
};
let def_id = self.symbol_table.symbol_trie.lookup(&fqsn);
if let Some(def_id) = def_id {
self.symbol_table.id_to_def.insert(*id, def_id);
}
}
}
};
Recursion::Continue
}
}

View File

@ -1,70 +0,0 @@
use std::{
collections::hash_map::DefaultHasher,
hash::{Hash, Hasher},
};
use radix_trie::{Trie, TrieCommon, TrieKey};
use super::{DefId, Fqsn, ScopeSegment};
#[derive(Debug)]
pub struct SymbolTrie(Trie<Fqsn, DefId>);
impl TrieKey for Fqsn {
fn encode_bytes(&self) -> Vec<u8> {
let mut hasher = DefaultHasher::new();
let mut output = vec![];
for segment in self.scopes.iter() {
let ScopeSegment::Name(s) = segment;
s.as_bytes().hash(&mut hasher);
output.extend_from_slice(&hasher.finish().to_be_bytes());
}
output
}
}
impl SymbolTrie {
pub fn new() -> SymbolTrie {
SymbolTrie(Trie::new())
}
pub fn insert(&mut self, fqsn: &Fqsn, def_id: DefId) {
self.0.insert(fqsn.clone(), def_id);
}
pub fn lookup(&self, fqsn: &Fqsn) -> Option<DefId> {
self.0.get(fqsn).cloned()
}
pub fn get_children(&self, fqsn: &Fqsn) -> Vec<Fqsn> {
let subtrie = match self.0.subtrie(fqsn) {
Some(s) => s,
None => return vec![],
};
let output: Vec<Fqsn> = subtrie.keys().filter(|cur_key| **cur_key != *fqsn).cloned().collect();
output
}
}
#[cfg(test)]
mod test {
use super::*;
use crate::symbol_table::Fqsn;
fn make_fqsn(strs: &[&str]) -> Fqsn {
Fqsn::from_strs(strs)
}
#[test]
fn test_trie_insertion() {
let id = DefId::default();
let mut trie = SymbolTrie::new();
trie.insert(&make_fqsn(&["unrelated", "thing"]), id);
trie.insert(&make_fqsn(&["outer", "inner"]), id);
trie.insert(&make_fqsn(&["outer", "inner", "still_inner"]), id);
let children = trie.get_children(&make_fqsn(&["outer", "inner"]));
assert_eq!(children.len(), 1);
}
}

View File

@ -1,314 +0,0 @@
#![cfg(test)]
use assert_matches::assert_matches;
use super::*;
use crate::util::quick_ast;
fn add_symbols(src: &str) -> (SymbolTable, Result<(), Vec<SymbolError>>) {
let ast = quick_ast(src);
let mut symbol_table = SymbolTable::new();
let mut type_context = crate::type_inference::TypeContext::new();
let result = symbol_table.process_ast(&ast, &mut type_context);
(symbol_table, result)
}
fn make_fqsn(strs: &[&str]) -> Fqsn {
Fqsn::from_strs(strs)
}
#[test]
fn basic_symbol_table() {
let src = "let a = 10; fn b() { 20 }";
let (symbols, _) = add_symbols(src);
fn make_fqsn(strs: &[&str]) -> Fqsn {
Fqsn::from_strs(strs)
}
symbols.fq_names.table.get(&make_fqsn(&["b"])).unwrap();
let src = "type Option<T> = Some(T) | None";
let (symbols, _) = add_symbols(src);
symbols.types.table.get(&make_fqsn(&["Option"])).unwrap();
}
#[test]
fn no_function_definition_duplicates() {
let source = r#"
fn a() { 1 }
fn b() { 2 }
fn a() { 3 }
"#;
let (_, output) = add_symbols(source);
let errs = output.unwrap_err();
assert_matches!(&errs[..], [
SymbolError::DuplicateName { prev_name, ..}
] if prev_name == &Fqsn::from_strs(&["a"])
);
}
#[test]
fn no_variable_definition_duplicates() {
let source = r#"
let x = 9
let a = 20
let q = 39
let a = 30
let x = 34
"#;
let (_, output) = add_symbols(source);
let errs = output.unwrap_err();
assert_matches!(&errs[..], [
SymbolError::DuplicateName { prev_name: pn1, ..},
SymbolError::DuplicateName { prev_name: pn2, ..}
] if pn1 == &Fqsn::from_strs(&["a"]) && pn2 == &Fqsn::from_strs(&["x"])
);
}
#[test]
fn no_type_definition_duplicates() {
let source = r#"
let x = 9
type Food = Japchae | Burrito | Other
type Food = GoodJapchae | Breadfruit
"#;
let (_, output) = add_symbols(source);
let errs = output.unwrap_err();
let err = &errs[0];
match err {
SymbolError::DuplicateName { location: _, prev_name } => {
assert_eq!(prev_name, &Fqsn::from_strs(&["Food"]));
//TODO restore this Location test
//assert_eq!(location, &Location { line_num: 2, char_num: 2 });
}
_ => panic!(),
}
}
#[test]
fn no_variant_duplicates() {
let source = r#"
type Panda = FoolsGold | Kappa(i32) | Remix | Kappa | Thursday | Remix
"#;
let (_, output) = add_symbols(source);
let errs = output.unwrap_err();
assert_eq!(errs.len(), 2);
assert_matches!(&errs[0], SymbolError::DuplicateVariant {
type_fqsn, name } if *type_fqsn == Fqsn::from_strs(&["Panda"]) &&
name == "Kappa");
assert_matches!(&errs[1], SymbolError::DuplicateVariant {
type_fqsn, name } if *type_fqsn == Fqsn::from_strs(&["Panda"]) &&
name == "Remix");
}
#[test]
fn no_variable_definition_duplicates_in_function() {
let source = r#"
fn a() {
let a = 20
let b = 40
a + b
}
fn q() {
let a = 29
let x = 30
let x = 33
}
"#;
let (_, output) = add_symbols(source);
let errs = output.unwrap_err();
assert_matches!(&errs[..], [
SymbolError::DuplicateName { prev_name: pn1, ..},
] if pn1 == &Fqsn::from_strs(&["q", "x"])
);
}
#[test]
fn dont_falsely_detect_duplicates() {
let source = r#"
let a = 20;
fn some_func() {
let a = 40;
77
}
let q = 39
"#;
let (symbols, _) = add_symbols(source);
assert!(symbols.fq_names.table.get(&make_fqsn(&["a"])).is_some());
assert!(symbols.fq_names.table.get(&make_fqsn(&["some_func", "a"])).is_some());
}
#[test]
fn enclosing_scopes() {
let source = r#"
fn outer_func(x) {
fn inner_func(arg) {
arg
}
x + inner_func(x)
}"#;
let (symbols, _) = add_symbols(source);
assert!(symbols.fq_names.table.get(&make_fqsn(&["outer_func"])).is_some());
assert!(symbols.fq_names.table.get(&make_fqsn(&["outer_func", "inner_func"])).is_some());
}
#[test]
fn enclosing_scopes_2() {
let source = r#"
fn outer_func(x) {
fn inner_func(arg) {
arg
}
fn second_inner_func() {
fn another_inner_func() {
}
}
inner_func(x)
}
"#;
let (symbols, _) = add_symbols(source);
assert!(symbols.fq_names.table.get(&make_fqsn(&["outer_func"])).is_some());
assert!(symbols.fq_names.table.get(&make_fqsn(&["outer_func", "inner_func"])).is_some());
assert!(symbols.fq_names.table.get(&make_fqsn(&["outer_func", "second_inner_func"])).is_some());
assert!(symbols
.fq_names
.table
.get(&make_fqsn(&["outer_func", "second_inner_func", "another_inner_func"]))
.is_some());
}
#[test]
fn enclosing_scopes_3() {
let source = r#"
fn outer_func(x) {
fn inner_func(arg) {
arg
}
fn second_inner_func() {
fn another_inner_func() {
}
fn another_inner_func() {
}
}
inner_func(x)
}"#;
let (_, output) = add_symbols(source);
let _err = output.unwrap_err();
}
#[test]
fn modules() {
let source = r#"
module stuff {
fn item() {
}
}
fn item()
"#;
let (symbols, _) = add_symbols(source);
symbols.fq_names.table.get(&make_fqsn(&["stuff"])).unwrap();
symbols.fq_names.table.get(&make_fqsn(&["item"])).unwrap();
symbols.fq_names.table.get(&make_fqsn(&["stuff", "item"])).unwrap();
}
#[test]
fn duplicate_modules() {
let source = r#"
module q {
fn foo() { 4 }
}
module a {
fn foo() { 334 }
}
module a {
fn sarat() { 39 }
fn foo() { 256.1 }
}
"#;
let (_, output) = add_symbols(source);
let errs = output.unwrap_err();
assert_matches!(&errs[..], [
SymbolError::DuplicateName { prev_name: pn1, ..},
] if pn1 == &Fqsn::from_strs(&["a"])
);
}
#[test]
fn duplicate_struct_members() {
let source = r#"
type Tarak = Tarak {
loujet: i32
,
mets: i32,
mets: i32
,
}
"#;
let (_, output) = add_symbols(source);
let errs = dbg!(output.unwrap_err());
assert_matches!(&errs[..], [
SymbolError::DuplicateRecord {
type_fqsn, member, record, ..},
] if type_fqsn == &Fqsn::from_strs(&["Tarak"]) && member == "mets" && record == "Tarak"
);
}
#[test]
fn method_definition_added_to_symbol_table() {
let source = r#"
type Foo = { x: Int, y: Int }
impl Foo {
fn hella() {
let a = 50
self.x + a
}
}
"#;
let (symbols, _) = add_symbols(source);
symbols.debug();
assert!(symbols.fq_names.table.get(&make_fqsn(&["<impl-block>Foo", "hella"])).is_some());
assert!(symbols.fq_names.table.get(&make_fqsn(&["<impl-block>Foo", "hella", "a"])).is_some());
}
#[test]
fn duplicate_method_definitions_detected() {
let source = r#"
type Foo = { x: Int, y: Int }
impl Foo {
fn hella() {
self.x + 50
}
fn hella() {
self.x + 40
}
}
"#;
let (_symbols, output) = add_symbols(source);
let errs = output.unwrap_err();
assert_matches!(&errs[..], [
SymbolError::DuplicateName { prev_name: pn1, ..},
] if pn1 == &Fqsn::from_strs(&["<impl-block>Foo", "hella"]));
}

View File

@ -1,513 +0,0 @@
use std::rc::Rc;
use super::{EvalResult, Memory, MemoryValue, Primitive, State};
use crate::{
builtin::Builtin,
reduced_ir::{
Alternative, Callable, Expression, FunctionDefinition, Literal, Lookup, Pattern, ReducedIR, Statement,
},
type_inference::TypeContext,
util::ScopeStack,
};
#[derive(Debug)]
enum StatementOutput {
Primitive(Primitive),
Nothing,
}
#[derive(Debug, Clone, Copy)]
enum LoopControlFlow {
Break,
Continue,
}
pub struct Evaluator<'a, 'b> {
type_context: &'b TypeContext,
state: &'b mut State<'a>,
early_returning: bool,
loop_control: Option<LoopControlFlow>,
}
impl<'a, 'b> Evaluator<'a, 'b> {
pub(crate) fn new(state: &'b mut State<'a>, type_context: &'b TypeContext) -> Self {
Self { state, type_context, early_returning: false, loop_control: None }
}
pub fn evaluate(&mut self, reduced: ReducedIR, repl: bool) -> Vec<Result<String, String>> {
let mut acc = vec![];
for (def_id, function) in reduced.functions.into_iter() {
let mem = (&def_id).into();
self.state.memory.insert(mem, MemoryValue::Function(function));
}
for statement in reduced.entrypoint.into_iter() {
match self.statement(statement) {
Ok(StatementOutput::Primitive(output)) if repl =>
acc.push(Ok(output.to_repl(self.type_context))),
Ok(_) => (),
Err(error) => {
acc.push(Err(error.msg));
return acc;
}
}
}
acc
}
fn block(&mut self, statements: Vec<Statement>) -> EvalResult<Primitive> {
let mut retval = None;
for stmt in statements.into_iter() {
match self.statement(stmt)? {
StatementOutput::Nothing => (),
StatementOutput::Primitive(prim) => {
retval = Some(prim);
}
};
if self.early_returning {
break;
}
if self.loop_control.is_some() {
break;
}
}
Ok(if let Some(ret) = retval { ret } else { self.expression(Expression::unit())? })
}
fn statement(&mut self, stmt: Statement) -> EvalResult<StatementOutput> {
match stmt {
Statement::Binding { ref id, expr, constant: _ } => {
let evaluated = self.expression(expr)?;
self.state.memory.insert(id.into(), evaluated.into());
Ok(StatementOutput::Nothing)
}
Statement::Expression(expr) => {
let evaluated = self.expression(expr)?;
Ok(StatementOutput::Primitive(evaluated))
}
Statement::Return(expr) => {
let evaluated = self.expression(expr)?;
self.early_returning = true;
Ok(StatementOutput::Primitive(evaluated))
}
Statement::Break => {
self.loop_control = Some(LoopControlFlow::Break);
Ok(StatementOutput::Nothing)
}
Statement::Continue => {
self.loop_control = Some(LoopControlFlow::Continue);
Ok(StatementOutput::Nothing)
}
}
}
fn expression(&mut self, expression: Expression) -> EvalResult<Primitive> {
Ok(match expression {
Expression::Literal(lit) => Primitive::Literal(lit),
Expression::Tuple(items) => Primitive::Tuple(
items
.into_iter()
.map(|expr| self.expression(expr))
.collect::<EvalResult<Vec<Primitive>>>()?,
),
Expression::List(items) => Primitive::List(
items
.into_iter()
.map(|expr| self.expression(expr))
.collect::<EvalResult<Vec<Primitive>>>()?,
),
Expression::Lookup(kind) => match kind {
Lookup::Function(ref id) => {
let mem = id.into();
match self.state.memory.lookup(&mem) {
// This just checks that the function exists in "memory" by ID, we don't
// actually retrieve it until `apply_function()`
Some(MemoryValue::Function(_)) => Primitive::Callable(Callable::UserDefined(*id)),
x => return Err(format!("Function not found for id: {} : {:?}", id, x).into()),
}
}
Lookup::Param(n) => {
let mem = n.into();
match self.state.memory.lookup(&mem) {
Some(MemoryValue::Primitive(prim)) => prim.clone(),
e => return Err(format!("Param lookup error, got {:?}", e).into()),
}
}
Lookup::SelfParam => {
let mem = Memory::self_param();
match self.state.memory.lookup(&mem) {
Some(MemoryValue::Primitive(prim)) => prim.clone(),
e => return Err(format!("SelfParam lookup error, got {:?}", e).into()),
}
}
Lookup::LocalVar(ref id) | Lookup::GlobalVar(ref id) => {
let mem = id.into();
match self.state.memory.lookup(&mem) {
Some(MemoryValue::Primitive(expr)) => expr.clone(),
_ =>
return Err(
format!("Nothing found for local/gloval variable lookup {}", id).into()
),
}
}
},
Expression::Assign { ref lval, box rval } => {
let mem = lval.into();
let evaluated = self.expression(rval)?;
println!("Inserting {:?} into {:?}", evaluated, mem);
self.state.memory.insert(mem, MemoryValue::Primitive(evaluated));
Primitive::unit()
}
Expression::Call { box f, args } => self.call_expression(f, args, None)?,
Expression::CallMethod { box f, args, box self_expr } =>
self.call_expression(f, args, Some(self_expr))?,
Expression::Callable(Callable::DataConstructor { type_id, tag }) => {
let arity = self.type_context.lookup_variant_arity(&type_id, tag).unwrap();
if arity == 0 {
Primitive::Object { type_id, tag, items: vec![], ordered_fields: None }
} else {
Primitive::Callable(Callable::DataConstructor { type_id, tag })
}
}
Expression::Callable(func) => Primitive::Callable(func),
Expression::Conditional { box cond, then_clause, else_clause } => {
let cond = self.expression(cond)?;
match cond {
Primitive::Literal(Literal::Bool(true)) => self.block(then_clause)?,
Primitive::Literal(Literal::Bool(false)) => self.block(else_clause)?,
v => return Err(format!("Non-boolean value {:?} in if-statement", v).into()),
}
}
Expression::CaseMatch { box cond, alternatives } =>
self.case_match_expression(cond, alternatives)?,
Expression::Index { box indexee, box indexer } => {
let indexee = self.expression(indexee)?;
let indexer = self.expression(indexer)?;
match (indexee, indexer) {
(Primitive::List(items), Primitive::Literal(Literal::Nat(n))) =>
match items.get(n as usize) {
Some(item) => item.clone(),
None => return Err(format!("Invalid index {} for this value", n).into()),
},
_ => return Err("Invalid index type".to_string().into()),
}
}
Expression::Loop { box cond, statements } => self.loop_expression(cond, statements)?,
Expression::ReductionError(e) => return Err(e.into()),
Expression::Access { name, box expr } => {
let expr = self.expression(expr)?;
match expr {
Primitive::Object { items, ordered_fields: Some(ordered_fields), .. } => {
let idx = match ordered_fields.iter().position(|s| s == &name) {
Some(idx) => idx,
None => return Err(format!("Field `{}` not found", name).into()),
};
let item = match items.get(idx) {
Some(item) => item,
None => return Err(format!("Field lookup `{}` failed", name).into()),
};
item.clone()
}
e =>
return Err(
format!("Trying to do a field lookup on a non-object value: {:?}", e).into()
),
}
}
})
}
fn loop_expression(&mut self, cond: Expression, statements: Vec<Statement>) -> EvalResult<Primitive> {
let existing = self.loop_control;
let output = self.loop_expression_inner(cond, statements);
self.loop_control = existing;
output
}
fn loop_expression_inner(
&mut self,
cond: Expression,
statements: Vec<Statement>,
) -> EvalResult<Primitive> {
loop {
let cond = self.expression(cond.clone())?;
println!("COND: {:?}", cond);
match cond {
Primitive::Literal(Literal::Bool(true)) => (),
Primitive::Literal(Literal::Bool(false)) => break,
e => return Err(format!("Loop condition evaluates to non-boolean: {:?}", e).into()),
};
//TODO eventually loops shoudl be able to return something
let _output = self.block(statements.clone())?;
match self.loop_control {
None => (),
Some(LoopControlFlow::Continue) => {
self.loop_control = None;
}
Some(LoopControlFlow::Break) => {
break;
}
}
}
Ok(Primitive::unit())
}
fn case_match_expression(
&mut self,
cond: Expression,
alternatives: Vec<Alternative>,
) -> EvalResult<Primitive> {
fn matches(scrut: &Primitive, pat: &Pattern, scope: &mut ScopeStack<Memory, MemoryValue>) -> bool {
match pat {
Pattern::Ignored => true,
Pattern::Binding(ref def_id) => {
let mem = def_id.into();
scope.insert(mem, MemoryValue::Primitive(scrut.clone())); //TODO make sure this doesn't cause problems with nesting
true
}
Pattern::Literal(pat_literal) =>
if let Primitive::Literal(scrut_literal) = scrut {
pat_literal == scrut_literal
} else {
false
},
Pattern::Tuple { subpatterns, tag } => match tag {
None => match scrut {
Primitive::Tuple(items) if items.len() == subpatterns.len() => items
.iter()
.zip(subpatterns.iter())
.all(|(item, subpat)| matches(item, subpat, scope)),
_ => false, //TODO should be a type error
},
Some(pattern_tag) => match scrut {
//TODO should test type_ids for runtime type checking, once those work
Primitive::Object { tag, items, .. }
if tag == pattern_tag && items.len() == subpatterns.len() =>
items
.iter()
.zip(subpatterns.iter())
.all(|(item, subpat)| matches(item, subpat, scope)),
_ => false,
},
},
Pattern::Record { tag: pattern_tag, subpatterns } => match scrut {
//TODO several types of possible error here
Primitive::Object { tag, items, ordered_fields: Some(ordered_fields), .. }
if tag == pattern_tag =>
subpatterns.iter().all(|(field_name, subpat)| {
let idx = ordered_fields
.iter()
.position(|field| field.as_str() == field_name.as_ref())
.unwrap();
let item = &items[idx];
matches(item, subpat, scope)
}),
_ => false,
},
}
}
let cond = self.expression(cond)?;
for alt in alternatives.into_iter() {
let mut new_scope = self.state.memory.new_scope(None);
if matches(&cond, &alt.pattern, &mut new_scope) {
let mut new_state = State { memory: new_scope };
let mut evaluator = Evaluator::new(&mut new_state, self.type_context);
let output = evaluator.block(alt.item);
self.early_returning = evaluator.early_returning;
return output;
}
}
Err("No valid match in match expression".into())
}
//TODO need to do something with self_expr to make method invocations actually work
fn call_expression(
&mut self,
f: Expression,
args: Vec<Expression>,
self_expr: Option<Expression>,
) -> EvalResult<Primitive> {
let func = match self.expression(f)? {
Primitive::Callable(func) => func,
other => return Err(format!("Trying to call non-function value: {:?}", other).into()),
};
match func {
Callable::Builtin(builtin) => self.apply_builtin(builtin, args),
Callable::UserDefined(def_id) => {
let mem = (&def_id).into();
match self.state.memory.lookup(&mem) {
Some(MemoryValue::Function(FunctionDefinition { body })) => {
let body = body.clone(); //TODO ideally this clone would not happen
self.apply_function(body, args, self_expr)
}
e => Err(format!("Error looking up function with id {}: {:?}", def_id, e).into()),
}
}
Callable::Lambda { arity, body } => {
if arity as usize != args.len() {
return Err(format!(
"Lambda expression requries {} arguments, only {} provided",
arity,
args.len()
)
.into());
}
self.apply_function(body, args, None)
}
Callable::DataConstructor { type_id, tag } => {
let arity = self.type_context.lookup_variant_arity(&type_id, tag).unwrap();
if arity as usize != args.len() {
return Err(format!(
"Constructor expression requries {} arguments, only {} provided",
arity,
args.len()
)
.into());
}
let mut items: Vec<Primitive> = vec![];
for arg in args.into_iter() {
items.push(self.expression(arg)?);
}
Ok(Primitive::Object { type_id, tag, items, ordered_fields: None })
}
Callable::RecordConstructor { type_id, tag, field_order } => {
//TODO maybe I'll want to do a runtime check of the evaluated fields
/*
let record_members = self.type_context.lookup_record_members(type_id, tag)
.ok_or(format!("Runtime record lookup for: {} {} not found", type_id, tag).into())?;
*/
let mut items: Vec<Primitive> = vec![];
for arg in args.into_iter() {
items.push(self.expression(arg)?);
}
Ok(Primitive::Object { type_id, tag, items, ordered_fields: Some(field_order) })
}
}
}
fn apply_builtin(&mut self, builtin: Builtin, args: Vec<Expression>) -> EvalResult<Primitive> {
use Builtin::*;
use Literal::*;
use Primitive::Literal as Lit;
let evaled_args: EvalResult<Vec<Primitive>> =
args.into_iter().map(|arg| self.expression(arg)).collect();
let evaled_args = evaled_args?;
Ok(match (builtin, evaled_args.as_slice()) {
/* builtin functions */
(IOPrint, &[ref anything]) => {
print!("{}", anything.to_repl(self.type_context));
Primitive::Tuple(vec![])
}
(IOPrintLn, &[ref anything]) => {
println!("{}", anything.to_repl(self.type_context));
Primitive::Tuple(vec![])
}
(IOGetLine, &[]) => {
let mut buf = String::new();
std::io::stdin().read_line(&mut buf).expect("Error readling line in 'getline'");
StringLit(Rc::new(buf.trim().to_string())).into()
}
/* Binops */
(binop, &[ref lhs, ref rhs]) => match (binop, lhs, rhs) {
// TODO need a better way of handling these literals
(Add, Lit(Nat(l)), Lit(Nat(r))) => Nat(l + r).into(),
(Add, Lit(Int(l)), Lit(Int(r))) => Int(l + r).into(),
(Add, Lit(Nat(l)), Lit(Int(r))) => Int((*l as i64) + (*r as i64)).into(),
(Add, Lit(Int(l)), Lit(Nat(r))) => Int((*l as i64) + (*r as i64)).into(),
(Concatenate, Lit(StringLit(ref s1)), Lit(StringLit(ref s2))) =>
StringLit(Rc::new(format!("{}{}", s1, s2))).into(),
(Subtract, Lit(Nat(l)), Lit(Nat(r))) => Nat(l - r).into(),
(Multiply, Lit(Nat(l)), Lit(Nat(r))) => Nat(l * r).into(),
(Divide, Lit(Nat(l)), Lit(Nat(r))) => Float((*l as f64) / (*r as f64)).into(),
(Quotient, Lit(Nat(l)), Lit(Nat(r))) =>
if *r == 0 {
return Err("Divide-by-zero error".into());
} else {
Nat(l / r).into()
},
(Modulo, Lit(Nat(l)), Lit(Nat(r))) => Nat(l % r).into(),
(Exponentiation, Lit(Nat(l)), Lit(Nat(r))) => Nat(l ^ r).into(),
(BitwiseAnd, Lit(Nat(l)), Lit(Nat(r))) => Nat(l & r).into(),
(BitwiseOr, Lit(Nat(l)), Lit(Nat(r))) => Nat(l | r).into(),
/* comparisons */
(Equality, Lit(Nat(l)), Lit(Nat(r))) => Bool(l == r).into(),
(Equality, Lit(Int(l)), Lit(Int(r))) => Bool(l == r).into(),
(Equality, Lit(Float(l)), Lit(Float(r))) => Bool(l == r).into(),
(Equality, Lit(Bool(l)), Lit(Bool(r))) => Bool(l == r).into(),
(Equality, Lit(StringLit(ref l)), Lit(StringLit(ref r))) => Bool(l == r).into(),
(NotEqual, Lit(Nat(l)), Lit(Nat(r))) => Bool(l != r).into(),
(NotEqual, Lit(Int(l)), Lit(Int(r))) => Bool(l != r).into(),
(NotEqual, Lit(Float(l)), Lit(Float(r))) => Bool(l != r).into(),
(NotEqual, Lit(Bool(l)), Lit(Bool(r))) => Bool(l != r).into(),
(NotEqual, Lit(StringLit(ref l)), Lit(StringLit(ref r))) => Bool(l != r).into(),
(LessThan, Lit(Nat(l)), Lit(Nat(r))) => Bool(l < r).into(),
(LessThan, Lit(Int(l)), Lit(Int(r))) => Bool(l < r).into(),
(LessThan, Lit(Float(l)), Lit(Float(r))) => Bool(l < r).into(),
(LessThanOrEqual, Lit(Nat(l)), Lit(Nat(r))) => Bool(l <= r).into(),
(LessThanOrEqual, Lit(Int(l)), Lit(Int(r))) => Bool(l <= r).into(),
(LessThanOrEqual, Lit(Float(l)), Lit(Float(r))) => Bool(l <= r).into(),
(GreaterThan, Lit(Nat(l)), Lit(Nat(r))) => Bool(l > r).into(),
(GreaterThan, Lit(Int(l)), Lit(Int(r))) => Bool(l > r).into(),
(GreaterThan, Lit(Float(l)), Lit(Float(r))) => Bool(l > r).into(),
(GreaterThanOrEqual, Lit(Nat(l)), Lit(Nat(r))) => Bool(l >= r).into(),
(GreaterThanOrEqual, Lit(Int(l)), Lit(Int(r))) => Bool(l >= r).into(),
(GreaterThanOrEqual, Lit(Float(l)), Lit(Float(r))) => Bool(l >= r).into(),
(binop, lhs, rhs) =>
return Err(format!("Invalid binop expression {:?} {:?} {:?}", lhs, binop, rhs).into()),
},
(prefix, &[ref arg]) => match (prefix, arg) {
(BooleanNot, Lit(Bool(true))) => Bool(false),
(BooleanNot, Lit(Bool(false))) => Bool(true),
(Negate, Lit(Nat(n))) => Int(-(*n as i64)),
(Negate, Lit(Int(n))) => Int(-(*n as i64)),
(Negate, Lit(Float(f))) => Float(-(*f as f64)),
(Increment, Lit(Int(n))) => Int(*n),
(Increment, Lit(Nat(n))) => Nat(*n),
_ => return Err("No valid prefix op".into()),
}
.into(),
(x, args) => return Err(format!("bad or unimplemented builtin {:?} | {:?}", x, args).into()),
})
}
fn apply_function(
&mut self,
body: Vec<Statement>,
args: Vec<Expression>,
self_expr: Option<Expression>,
) -> EvalResult<Primitive> {
let self_expr = if let Some(expr) = self_expr { Some(self.expression(expr)?) } else { None };
let mut evaluated_args: Vec<Primitive> = vec![];
for arg in args.into_iter() {
evaluated_args.push(self.expression(arg)?);
}
let mut frame_state = State { memory: self.state.memory.new_scope(None) };
let mut evaluator = Evaluator::new(&mut frame_state, self.type_context);
if let Some(evaled) = self_expr {
let mem = Memory::self_param();
evaluator.state.memory.insert(mem, MemoryValue::Primitive(evaled));
}
for (n, evaled) in evaluated_args.into_iter().enumerate() {
let n = n as u8;
let mem = n.into();
evaluator.state.memory.insert(mem, MemoryValue::Primitive(evaled));
}
evaluator.block(body)
}
}

View File

@ -1,173 +0,0 @@
use std::{convert::From, fmt::Write};
use crate::{
reduced_ir::{Callable, Expression, FunctionDefinition, Literal, ReducedIR},
symbol_table::DefId,
type_inference::{TypeContext, TypeId},
util::{delim_wrapped, ScopeStack},
};
mod evaluator;
mod test;
type EvalResult<T> = Result<T, RuntimeError>;
#[derive(Debug)]
pub struct State<'a> {
memory: ScopeStack<'a, Memory, MemoryValue>,
}
//TODO - eh, I dunno, maybe it doesn't matter exactly how memory works in the tree-walking
//evaluator
#[derive(Debug, PartialEq, Eq, Hash, Clone)]
enum Memory {
Index(u32),
}
impl Memory {
fn self_param() -> Self {
Memory::Index(3_999_999)
}
}
// This is for function param lookups, and is a hack
impl From<u8> for Memory {
fn from(n: u8) -> Self {
Memory::Index(4_000_000 + (n as u32))
}
}
impl From<&DefId> for Memory {
fn from(id: &DefId) -> Self {
Self::Index(id.as_u32())
}
}
#[derive(Debug)]
struct RuntimeError {
msg: String,
}
impl From<String> for RuntimeError {
fn from(msg: String) -> Self {
Self { msg }
}
}
impl From<&str> for RuntimeError {
fn from(msg: &str) -> Self {
Self { msg: msg.to_string() }
}
}
impl RuntimeError {
#[allow(dead_code)]
fn get_msg(&self) -> String {
format!("Runtime error: {}", self.msg)
}
}
/// Anything that can be stored in memory; that is, a function definition, or a fully-evaluated
/// program value.
#[derive(Debug)]
enum MemoryValue {
Function(FunctionDefinition),
Primitive(Primitive),
}
impl From<Primitive> for MemoryValue {
fn from(prim: Primitive) -> Self {
Self::Primitive(prim)
}
}
#[derive(Debug)]
enum RuntimeValue {
Expression(Expression),
Evaluated(Primitive),
}
impl From<Expression> for RuntimeValue {
fn from(expr: Expression) -> Self {
Self::Expression(expr)
}
}
impl From<Primitive> for RuntimeValue {
fn from(prim: Primitive) -> Self {
Self::Evaluated(prim)
}
}
/// A fully-reduced value
#[derive(Debug, Clone)]
enum Primitive {
Tuple(Vec<Primitive>),
List(Vec<Primitive>),
Literal(Literal),
Callable(Callable),
Object { type_id: TypeId, tag: u32, ordered_fields: Option<Vec<String>>, items: Vec<Primitive> },
}
impl Primitive {
fn to_repl(&self, type_context: &TypeContext) -> String {
match self {
Primitive::Object { type_id, items, tag, ordered_fields: _ } if items.is_empty() =>
type_context.variant_local_name(type_id, *tag).unwrap().to_string(),
Primitive::Object { type_id, items, tag, ordered_fields: None } => {
format!(
"{}{}",
type_context.variant_local_name(type_id, *tag).unwrap(),
delim_wrapped('(', ')', items.iter().map(|item| item.to_repl(type_context)))
)
}
Primitive::Object { type_id, items, tag, ordered_fields: Some(fields) } => {
let mut buf = format!("{} {{ ", type_context.variant_local_name(type_id, *tag).unwrap());
for item in fields.iter().zip(items.iter()).map(Some).intersperse(None) {
match item {
Some((name, val)) => write!(buf, "{}: {}", name, val.to_repl(type_context)).unwrap(),
None => write!(buf, ", ").unwrap(),
}
}
write!(buf, " }}").unwrap();
buf
}
Primitive::Literal(lit) => match lit {
Literal::Nat(n) => format!("{}", n),
Literal::Int(i) => format!("{}", i),
Literal::Float(f) => format!("{}", f),
Literal::Bool(b) => format!("{}", b),
Literal::StringLit(s) => format!("\"{}\"", s),
},
Primitive::Tuple(terms) => delim_wrapped('(', ')', terms.iter().map(|x| x.to_repl(type_context))),
Primitive::List(terms) => delim_wrapped('[', ']', terms.iter().map(|x| x.to_repl(type_context))),
Primitive::Callable(..) => "<some-callable>".to_string(),
}
}
fn unit() -> Self {
Primitive::Tuple(vec![])
}
}
impl From<Literal> for Primitive {
fn from(lit: Literal) -> Self {
Primitive::Literal(lit)
}
}
impl<'a> State<'a> {
pub fn new() -> Self {
Self { memory: ScopeStack::new(Some("global".to_string())) }
}
pub fn evaluate(
&mut self,
reduced: ReducedIR,
type_context: &TypeContext,
repl: bool,
) -> Vec<Result<String, String>> {
let mut evaluator = evaluator::Evaluator::new(self, type_context);
evaluator.evaluate(reduced, repl)
}
}

View File

@ -1,564 +0,0 @@
#![cfg(test)]
use pretty_assertions::assert_eq;
use test_case::test_case;
use crate::{
symbol_table::SymbolTable,
tree_walk_eval::{evaluator::Evaluator, State},
type_inference::TypeContext,
};
fn evaluate_input(input: &str) -> Result<String, String> {
let ast = crate::util::quick_ast(input);
let mut symbol_table = SymbolTable::new();
let mut type_context = TypeContext::new();
symbol_table.process_ast(&ast, &mut type_context).unwrap();
let reduced_ir = crate::reduced_ir::reduce(&ast, &symbol_table, &type_context);
reduced_ir.debug(&symbol_table);
println!("========");
symbol_table.debug();
let mut state = State::new();
let mut evaluator = Evaluator::new(&mut state, &type_context);
let mut outputs = evaluator.evaluate(reduced_ir, true);
outputs.pop().unwrap()
}
fn eval_assert(input: &str, expected: &str) {
assert_eq!(evaluate_input(input), Ok(expected.to_string()));
}
fn eval_assert_failure(input: &str, expected: &str) {
assert_eq!(evaluate_input(input), Err(expected.to_string()));
}
#[test]
fn test_basic_eval() {
eval_assert("1 + 2", "3");
eval_assert("let mut a = 1; a = 2", "()");
eval_assert("let mut a = 1; a = a + 2; a", "3");
}
#[test]
fn op_eval() {
eval_assert("-13", "-13");
eval_assert("10 - 2", "8");
}
#[test]
fn function_eval() {
eval_assert("fn oi(x) { x + 1 }; oi(4)", "5");
eval_assert("fn oi(x) { x + 1 }; oi(1+2)", "4");
}
#[test]
fn scopes() {
let scope_ok = r#"
let a = 20
fn haha() {
let something = 38
let a = 10
a
}
haha()
"#;
eval_assert(scope_ok, "10");
let scope_ok = r#"
let a = 20
fn queque() {
let a = 10
a
}
a
"#;
eval_assert(scope_ok, "20");
}
#[test]
fn eval_scopes_2() {
eval_assert(
r#"
fn trad() {
let a = 10
fn jinner() {
let b = 20
b
}
a + jinner()
}
trad()"#,
"30",
);
let err = "No symbol found for name: `a`";
eval_assert_failure(
r#"
fn trad() {
let a = 10
fn inner() {
let b = 20
a + b
}
inner()
}
trad()
"#,
err,
);
}
#[test]
fn adt_output_1() {
let source = r#"
type Option<T> = Some(T) | None
let a = Option::None
let b = Option::Some(10)
(b, a)
"#;
eval_assert(source, "(Some(10), None)");
}
#[test]
fn adt_output_2() {
let source = r#"
type Gobble = Unknown | Rufus { a: Int, torrid: Nat }
let b = Gobble::Rufus { a: 3, torrid: 99 }
b
"#;
eval_assert(source, "Rufus { a: 3, torrid: 99 }");
let source = r#"
type Gobble = Unknown | Rufus { a: Int, torrid: Nat }
let b = Gobble::Rufus { torrid: 3, a: 84 }
b
"#;
eval_assert(source, "Rufus { a: 84, torrid: 3 }");
let source = r#"
type Gobble = Unknown | Rufus { a: Int, torrid: Nat }
let b = Gobble::Rufus { a: 84 }
b
"#;
eval_assert_failure(source, "Field torrid not specified for record Gobble::Rufus");
}
#[test]
fn basic_if_statement() {
let source = r#"
let a = 10
let b = 10
if a == b then { 69 } else { 420 }
"#;
eval_assert(source, "69");
}
#[test]
fn basic_patterns_1() {
let source = r#"
let x = 10
let a = if x is 10 then { 255 } else { 256 }
let b = if 23 is 99 then { 255 } else { 256 }
let c = if true is false then { 9 } else { 10 }
let d = if "xxx" is "yyy" then { 20 } else { 30 }
(a, b, c, d)
"#;
eval_assert(source, "(255, 256, 10, 30)");
}
#[test_case("sanchez", "1")]
#[test_case("mouri", "2")]
#[test_case("hella", "3")]
#[test_case("cyrus", "4")]
fn basic_patterns_2(input: &str, expected: &str) {
let mut source = format!(r#"let x = "{}""#, input);
source.push_str(
r#"
if x {
is "sanchez" then 1
is "mouri" then 2
is "hella" then 3
is _ then 4
}
"#,
);
eval_assert(&source, expected);
}
#[test_case(r#"(45, "panda", false, 2.2)"#, r#""yes""#)]
#[test_case(r#"(99, "panda", false, -2.45)"#, r#""maybe""#)]
fn tuple_patterns(input: &str, expected: &str) {
let mut source = format!("let x = {}", input);
source.push_str(
r#"
if x {
is (45, "pablo", _, 28.4) then "no"
is (_, "panda", _, 2.2) then "yes"
is _ then "maybe"
}"#,
);
eval_assert(&source, expected);
}
#[test]
fn record_patterns_1() {
let source = r#"
type Ara = Kueh { a: Int, b: String } | Morbuk
let alpha = Ara::Kueh { a: 10, b: "sanchez" }
if alpha {
is Ara::Kueh { a, b } then (b, a)
is _ then ("nooo", 8888)
}"#;
eval_assert(source, r#"("sanchez", 10)"#);
}
#[test]
fn record_patterns_2() {
let source = r#"
type Ara = Kueh { a: Int, b: String } | Morbuk
let alpha = Ara::Kueh { a: 10, b: "sanchez" }
if alpha {
is Ara::Kueh { a, b: le_value } then (le_value, (a*2))
is _ then ("nooo", 8888)
}"#;
eval_assert(source, r#"("sanchez", 20)"#);
}
#[test]
fn record_patterns_3() {
let source = r#"
type Vstsavlobs = { tkveni: Int, b: Ia }
type Ia = { sitqva: Int, ghmerts: String }
let b = Vstsavlobs { tkveni: 3, b: Ia::Ia { sitqva: 5, ghmerts: "ooo" } }
if b {
is Vstsavlobs::Vstsavlobs { tkveni: _, b: Ia::Ia { sitqva, ghmerts } } then sitqva
is _ then 5000
}"#;
eval_assert(source, "5");
}
#[test]
fn if_is_patterns() {
let source = r#"
type Option<T> = Some(T) | None
let q = "a string"
let x = Option::Some(9); if x is Option::Some(q) then { q } else { 0 }"#;
eval_assert(source, "9");
let source = r#"
type Option<T> = Some(T) | None
let q = "a string"
let outer = 2
let x = Option::None; if x is Option::Some(q) then { q } else { -2 + outer }"#;
eval_assert(source, "0");
}
#[test]
fn full_if_matching() {
let source = r#"
type Option<T> = Some(T) | None
let a = Option::None
if a { is Option::None then 4; is Option::Some(x) then x }
"#;
eval_assert(source, "4");
let source = r#"
type Option<T> = Some(T) | None
let sara = Option::Some(99)
if sara { is Option::None then 1 + 3; is Option::Some(x) then x }
"#;
eval_assert(source, "99");
let source = r#"
let a = 10
if a { is 10 then "x"; is 4 then "y" }
"#;
eval_assert(source, "\"x\"");
let source = r#"
let a = 10
if a { is 15 then "x"; is 10 then "y" }
"#;
eval_assert(source, "\"y\"");
}
//TODO - I can probably cut down some of these
#[test]
fn string_pattern() {
let source = r#"
let a = "foo"
if a { is "foo" then "x"; is _ then "y" }
"#;
eval_assert(source, "\"x\"");
}
#[test]
fn boolean_pattern() {
let source = r#"
let a = true
if a {
is true then "x"
is false then "y"
}
"#;
eval_assert(source, "\"x\"");
}
#[test]
fn boolean_pattern_2() {
let source = r#"
let a = false
if a { is true then "x"; is false then "y" }
"#;
eval_assert(source, "\"y\"");
}
#[test]
fn ignore_pattern() {
let source = r#"
type Option<T> = Some(T) | None
if Option::Some(10) {
is _ then "hella"
}
"#;
eval_assert(source, "\"hella\"");
}
#[test]
fn tuple_pattern() {
let source = r#"
if (1, 2) {
is (1, x) then x;
is _ then 99
}
"#;
eval_assert(source, "2");
}
#[test]
fn tuple_pattern_2() {
let source = r#"
if (1, 2) {
is (10, x) then x
is (y, x) then x + y
}
"#;
eval_assert(source, "3");
}
#[test]
fn tuple_pattern_3() {
let source = r#"
if (1, 5) {
is (10, x) then x
is (1, x) then x
}
"#;
eval_assert(source, "5");
}
#[test]
fn tuple_pattern_4() {
let source = r#"
if (1, 5) {
is (10, x) then x
is (1, x) then x
}
"#;
eval_assert(source, "5");
}
#[test]
fn prim_obj_pattern() {
let source = r#"
type Stuff = Mulch(Nat) | Jugs(Nat, String) | Mardok
let a = Stuff::Mulch(20)
let b = Stuff::Jugs(1, "haha")
let c = Stuff::Mardok
let x = if a {
is Stuff::Mulch(20) then "x"
is _ then "ERR"
}
let y = if b {
is Stuff::Mulch(n) then "ERR"
is Stuff::Jugs(2, _) then "ERR"
is Stuff::Jugs(1, s) then s
is _ then "ERR"
}
let z = if c {
is Stuff::Jugs(_, _) then "ERR"
is Stuff::Mardok then "NIGH"
is _ then "ERR"
}
(x, y, z)
"#;
eval_assert(source, r#"("x", "haha", "NIGH")"#);
}
#[test]
fn basic_lambda_evaluation_1() {
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)
"#;
eval_assert(source, r"(10, 6)");
}
#[test]
fn basic_lambda_evaluation_2() {
let source = r#"
fn milta() {
\(x) { x + 33 }
}
milta()(10)
"#;
eval_assert(source, "43");
}
#[test]
fn import_all() {
let source = r#"
type Option<T> = Some(T) | None
import Option::*
let x = Some(9); if x is Some(q) then { q } else { 0 }"#;
eval_assert(source, "9");
}
#[test]
fn accessors() {
let source = r#"
type Klewos = { a: Int, b: String }
let value = Klewos::Klewos { a: 50, b: "nah" }
(value.a, value.b)
"#;
eval_assert(source, r#"(50, "nah")"#);
}
#[test]
fn early_return() {
let source = r#"
fn chnurmek(a: Int): Int {
if a == 5 then {
return 9999;
}
return (a + 2);
}
(chnurmek(5), chnurmek(0))
"#;
eval_assert(source, r#"(9999, 2)"#);
let source = r#"
fn marbuk(a: Int, b: Int): (Int, Int) {
if a == 5 then {
if b == 6 then {
return (50, 50);
}
return (a, b + 1)
}
(a * 100, b * 100)
}
let x = marbuk(1, 1)
let y = marbuk(5, 1)
let z = marbuk(5, 6)
(x, y, z)
"#;
eval_assert(source, "((100, 100), (5, 2), (50, 50))");
}
#[test]
fn loops() {
let source = r#"
let mut a = 0
let mut count = 0
while a != 5 {
a = a + 1
count = count + 100
}
count
"#;
eval_assert(source, "500");
}
#[test]
fn loops_2() {
let source = r#"
let mut a = 0
let mut acc = 0
while a < 10 {
acc = acc + 1
a = a + 1
// Without this continue, the output would be 20
if a == 5 then {
continue
}
acc = acc + 1
}
acc"#;
eval_assert(source, "19");
}
#[test]
fn list_literals() {
eval_assert(
r#"
let a = [7, 8, 9]
a
"#,
"[7, 8, 9]",
);
eval_assert(
r#"
let a = [7, 8, 9]
fn foo() { return 2 }
(a[0], a[foo()])
"#,
"(7, 9)",
);
}
#[test]
fn eval_method() {
let src = r#"
type Thing = Thing
impl Thing {
fn a_method() {
20
}
}
let a = Thing::Thing
4 + a.a_method()
"#;
eval_assert(src, "24");
}

View File

@ -1,445 +0,0 @@
use std::collections::HashMap;
use std::rc::Rc;
use parsing::{AST, Statement, Declaration, Signature, Expression, ExpressionType, Operation, Variant, TypeName, TypeSingletonName};
// from Niko's talk
/* fn type_check(expression, expected_ty) -> Ty {
let ty = bare_type_check(expression, expected_type);
if ty icompatible with expected_ty {
try_coerce(expression, ty, expected_ty)
} else {
ty
}
}
fn bare_type_check(exprssion, expected_type) -> Ty { ... }
*/
/* H-M ALGO NOTES
from https://www.youtube.com/watch?v=il3gD7XMdmA
(also check out http://dev.stephendiehl.com/fun/006_hindley_milner.html)
typeInfer :: Expr a -> Matching (Type a)
unify :: Type a -> Type b -> Matching (Type c)
(Matching a) is a monad in which unification is done
ex:
typeInfer (If e1 e2 e3) = do
t1 <- typeInfer e1
t2 <- typeInfer e2
t3 <- typeInfer e3
_ <- unify t1 BoolType
unify t2 t3 -- b/c t2 and t3 have to be the same type
typeInfer (Const (ConstInt _)) = IntType -- same for other literals
--function application
typeInfer (Apply f x) = do
tf <- typeInfer f
tx <- typeInfer x
case tf of
FunctionType t1 t2 -> do
_ <- unify t1 tx
return t2
_ -> fail "Not a function"
--type annotation
typeInfer (Typed x t) = do
tx <- typeInfer x
unify tx t
--variable and let expressions - need to pass around a map of variable names to types here
typeInfer :: [ (Var, Type Var) ] -> Expr Var -> Matching (Type Var)
typeInfer ctx (Var x) = case (lookup x ctx) of
Just t -> return t
Nothing -> fail "Unknown variable"
--let x = e1 in e2
typeInfer ctx (Let x e1 e2) = do
t1 <- typeInfer ctx e1
typeInfer ((x, t1) :: ctx) e2
--lambdas are complicated (this represents ʎx.e)
typeInfer ctx (Lambda x e) = do
t1 <- allocExistentialVariable
t2 <- typeInfer ((x, t1) :: ctx) e
return $ FunctionType t1 t2 -- ie. t1 -> t2
--to solve the problem of map :: (a -> b) -> [a] -> [b]
when we use a variable whose type has universal tvars, convert those universal
tvars to existential ones
-and each distinct universal tvar needs to map to the same existential type
-so we change typeinfer:
typeInfer ctx (Var x) = do
case (lookup x ctx) of
Nothing -> ...
Just t -> do
let uvars = nub (toList t) -- nub removes duplicates, so this gets unique universally quantified variables
evars <- mapM (const allocExistentialVariable) uvars
let varMap = zip uvars evars
let vixVar varMap v = fromJust $ lookup v varMap
return (fmap (fixVar varMap) t)
--how do we define unify??
-recall, type signature is:
unify :: Type a -> Type b -> Matching (Type c)
unify BoolType BoolType = BoolType --easy, same for all constants
unify (FunctionType t1 t2) (FunctionType t3 t4) = do
t5 <- unify t1 t3
t6 <- unify t2 t4
return $ FunctionType t5 t6
unify (TVar a) (TVar b) = if a == b then TVar a else fail
--existential types can be assigned another type at most once
--some complicated stuff about hanlding existential types
--everything else is a type error
unify a b = fail
SKOLEMIZATION - how you prevent an unassigned existential type variable from leaking!
-before a type gets to global scope, replace all unassigned existential vars w/ new unique universal
type variables
*/
#[derive(Debug, PartialEq, Clone)]
pub enum Type {
TVar(TypeVar),
TConst(TypeConst),
TFunc(Box<Type>, Box<Type>),
}
#[derive(Debug, PartialEq, Clone)]
pub enum TypeVar {
Univ(Rc<String>),
Exist(u64),
}
impl TypeVar {
fn univ(label: &str) -> TypeVar {
TypeVar::Univ(Rc::new(label.to_string()))
}
}
#[derive(Debug, PartialEq, Clone)]
pub enum TypeConst {
UserT(Rc<String>),
Integer,
Float,
StringT,
Boolean,
Unit,
Bottom,
}
type TypeCheckResult = Result<Type, String>;
#[derive(Debug, PartialEq, Eq, Hash)]
struct PathSpecifier(Rc<String>);
#[derive(Debug, PartialEq, Clone)]
struct TypeContextEntry {
ty: Type,
constant: bool
}
pub struct TypeContext {
symbol_table: HashMap<PathSpecifier, TypeContextEntry>,
evar_table: HashMap<u64, Type>,
existential_type_label_count: u64
}
impl TypeContext {
pub fn new() -> TypeContext {
TypeContext {
symbol_table: HashMap::new(),
evar_table: HashMap::new(),
existential_type_label_count: 0,
}
}
pub fn add_symbols(&mut self, ast: &AST) {
use self::Declaration::*;
use self::Type::*;
use self::TypeConst::*;
for statement in ast.0.iter() {
match *statement {
Statement::ExpressionStatement(_) => (),
Statement::Declaration(ref decl) => match *decl {
FuncSig(_) => (),
Impl { .. } => (),
TypeDecl(ref type_constructor, ref body) => {
for variant in body.0.iter() {
let (spec, ty) = match variant {
&Variant::UnitStruct(ref data_constructor) => {
let spec = PathSpecifier(data_constructor.clone());
let ty = TConst(UserT(type_constructor.name.clone()));
(spec, ty)
},
&Variant::TupleStruct(ref data_construcor, ref args) => {
//TODO fix
let arg = args.get(0).unwrap();
let type_arg = self.from_anno(arg);
let spec = PathSpecifier(data_construcor.clone());
let ty = TFunc(Box::new(type_arg), Box::new(TConst(UserT(type_constructor.name.clone()))));
(spec, ty)
},
&Variant::Record(_, _) => unimplemented!(),
};
let entry = TypeContextEntry { ty, constant: true };
self.symbol_table.insert(spec, entry);
}
},
TypeAlias { .. } => (),
Binding {ref name, ref constant, ref expr} => {
let spec = PathSpecifier(name.clone());
let ty = expr.1.as_ref()
.map(|ty| self.from_anno(ty))
.unwrap_or_else(|| { self.alloc_existential_type() }); // this call to alloc_existential is OK b/c a binding only ever has one type, so if the annotation is absent, it's fine to just make one de novo
let entry = TypeContextEntry { ty, constant: *constant };
self.symbol_table.insert(spec, entry);
},
FuncDecl(ref signature, _) => {
let spec = PathSpecifier(signature.name.clone());
let ty = self.from_signature(signature);
let entry = TypeContextEntry { ty, constant: true };
self.symbol_table.insert(spec, entry);
},
}
}
}
}
fn lookup(&mut self, binding: &Rc<String>) -> Option<TypeContextEntry> {
let key = PathSpecifier(binding.clone());
self.symbol_table.get(&key).map(|entry| entry.clone())
}
pub fn debug_symbol_table(&self) -> String {
format!("Symbol table:\n {:?}\nEvar table:\n{:?}", self.symbol_table, self.evar_table)
}
fn alloc_existential_type(&mut self) -> Type {
let ret = Type::TVar(TypeVar::Exist(self.existential_type_label_count));
self.existential_type_label_count += 1;
ret
}
fn from_anno(&mut self, anno: &TypeName) -> Type {
use self::Type::*;
use self::TypeConst::*;
match anno {
&TypeName::Singleton(TypeSingletonName { ref name, .. }) => {
match name.as_ref().as_ref() {
"Int" => TConst(Integer),
"Float" => TConst(Float),
"Bool" => TConst(Boolean),
"String" => TConst(StringT),
s => TVar(TypeVar::Univ(Rc::new(format!("{}",s)))),
}
},
&TypeName::Tuple(ref items) => {
if items.len() == 1 {
TConst(Unit)
} else {
TConst(Bottom)
}
}
}
}
fn from_signature(&mut self, sig: &Signature) -> Type {
use self::Type::*;
use self::TypeConst::*;
//TODO this won't work properly until you make sure that all (universal) type vars in the function have the same existential type var
// actually this should never even put existential types into the symbol table at all
//this will crash if more than 5 arg function is used
let names = vec!["a", "b", "c", "d", "e", "f"];
let mut idx = 0;
let mut get_type = || { let q = TVar(TypeVar::Univ(Rc::new(format!("{}", names.get(idx).unwrap())))); idx += 1; q };
let return_type = sig.type_anno.as_ref().map(|anno| self.from_anno(&anno)).unwrap_or_else(|| { get_type() });
if sig.params.len() == 0 {
TFunc(Box::new(TConst(Unit)), Box::new(return_type))
} else {
let mut output_type = return_type;
for p in sig.params.iter() {
let p_type = p.1.as_ref().map(|anno| self.from_anno(anno)).unwrap_or_else(|| { get_type() });
output_type = TFunc(Box::new(p_type), Box::new(output_type));
}
output_type
}
}
pub fn type_check(&mut self, ast: &AST) -> TypeCheckResult {
use self::Type::*;
use self::TypeConst::*;
let mut last = TConst(Unit);
for statement in ast.0.iter() {
match statement {
&Statement::Declaration(ref _decl) => {
//return Err(format!("Declarations not supported"));
},
&Statement::ExpressionStatement(ref expr) => {
last = self.infer(expr)?;
}
}
}
Ok(last)
}
fn infer(&mut self, expr: &Expression) -> TypeCheckResult {
match (&expr.0, &expr.1) {
(exprtype, &Some(ref anno)) => {
let tx = self.infer_no_anno(exprtype)?;
let ty = self.from_anno(anno);
self.unify(tx, ty)
},
(exprtype, &None) => self.infer_no_anno(exprtype),
}
}
fn infer_no_anno(&mut self, ex: &ExpressionType) -> TypeCheckResult {
use self::ExpressionType::*;
use self::Type::*;
use self::TypeConst::*;
Ok(match ex {
&IntLiteral(_) => TConst(Integer),
&FloatLiteral(_) => TConst(Float),
&StringLiteral(_) => TConst(StringT),
&BoolLiteral(_) => TConst(Boolean),
&Value(ref name, _) => {
self.lookup(name)
.map(|entry| entry.ty)
.ok_or(format!("Couldn't find {}", name))?
},
&BinExp(ref op, ref lhs, ref rhs) => {
let t_lhs = self.infer(lhs)?;
match self.infer_op(op)? {
TFunc(t1, t2) => {
let _ = self.unify(t_lhs, *t1)?;
let t_rhs = self.infer(rhs)?;
let x = *t2;
match x {
TFunc(t3, t4) => {
let _ = self.unify(t_rhs, *t3)?;
*t4
},
_ => return Err(format!("Not a function type either")),
}
},
_ => return Err(format!("Op {:?} is not a function type", op)),
}
},
&Call { ref f, ref arguments } => {
let tf = self.infer(f)?;
let targ = self.infer(arguments.get(0).unwrap())?;
match tf {
TFunc(box t1, box t2) => {
let _ = self.unify(t1, targ)?;
t2
},
_ => return Err(format!("Not a function!")),
}
},
_ => TConst(Bottom),
})
}
fn infer_op(&mut self, op: &Operation) -> TypeCheckResult {
use self::Type::*;
use self::TypeConst::*;
macro_rules! binoptype {
($lhs:expr, $rhs:expr, $out:expr) => { TFunc(Box::new($lhs), Box::new(TFunc(Box::new($rhs), Box::new($out)))) };
}
Ok(match (*op.0).as_ref() {
"+" => binoptype!(TConst(Integer), TConst(Integer), TConst(Integer)),
"++" => binoptype!(TConst(StringT), TConst(StringT), TConst(StringT)),
"-" => binoptype!(TConst(Integer), TConst(Integer), TConst(Integer)),
"*" => binoptype!(TConst(Integer), TConst(Integer), TConst(Integer)),
"/" => binoptype!(TConst(Integer), TConst(Integer), TConst(Integer)),
"%" => binoptype!(TConst(Integer), TConst(Integer), TConst(Integer)),
_ => TConst(Bottom)
})
}
fn unify(&mut self, t1: Type, t2: Type) -> TypeCheckResult {
use self::Type::*;
use self::TypeVar::*;
println!("Calling unify with `{:?}` and `{:?}`", t1, t2);
match (&t1, &t2) {
(&TConst(ref c1), &TConst(ref c2)) if c1 == c2 => Ok(TConst(c1.clone())),
(&TFunc(ref t1, ref t2), &TFunc(ref t3, ref t4)) => {
let t5 = self.unify(*t1.clone().clone(), *t3.clone().clone())?;
let t6 = self.unify(*t2.clone().clone(), *t4.clone().clone())?;
Ok(TFunc(Box::new(t5), Box::new(t6)))
},
(&TVar(Univ(ref a)), &TVar(Univ(ref b))) => {
if a == b {
Ok(TVar(Univ(a.clone())))
} else {
Err(format!("Couldn't unify universal types {} and {}", a, b))
}
},
//the interesting case!!
(&TVar(Exist(ref a)), ref t2) => {
let x = self.evar_table.get(a).map(|x| x.clone());
match x {
Some(ref t1) => self.unify(t1.clone().clone(), t2.clone().clone()),
None => {
self.evar_table.insert(*a, t2.clone().clone());
Ok(t2.clone().clone())
}
}
},
(ref t1, &TVar(Exist(ref a))) => {
let x = self.evar_table.get(a).map(|x| x.clone());
match x {
Some(ref t2) => self.unify(t2.clone().clone(), t1.clone().clone()),
None => {
self.evar_table.insert(*a, t1.clone().clone());
Ok(t1.clone().clone())
}
}
},
_ => Err(format!("Types {:?} and {:?} don't unify", t1, t2))
}
}
}
#[cfg(test)]
mod tests {
use super::{Type, TypeVar, TypeConst, TypeContext};
use super::Type::*;
use super::TypeConst::*;
use schala_lang::parsing::{parse, tokenize};
macro_rules! type_test {
($input:expr, $correct:expr) => {
{
let mut tc = TypeContext::new();
let ast = parse(tokenize($input)).0.unwrap() ;
tc.add_symbols(&ast);
assert_eq!($correct, tc.type_check(&ast).unwrap())
}
}
}
#[test]
fn basic_inference() {
type_test!("30", TConst(Integer));
type_test!("fn x(a: Int): Bool {}; x(1)", TConst(Boolean));
}
}

View File

@ -1,227 +0,0 @@
use std::{collections::HashMap, convert::From};
use crate::{
ast::{TypeIdentifier, AST},
identifier::{define_id_kind, Id, IdStore},
};
define_id_kind!(TypeItem);
pub type TypeId = Id<TypeItem>;
pub struct TypeContext {
defined_types: HashMap<TypeId, DefinedType>,
type_id_store: IdStore<TypeItem>,
}
impl TypeContext {
pub fn new() -> Self {
Self { defined_types: HashMap::new(), type_id_store: IdStore::new() }
}
pub fn register_type(&mut self, builder: TypeBuilder) -> TypeId {
let type_id = self.type_id_store.fresh();
let mut pending_variants = vec![];
for variant_builder in builder.variants.into_iter() {
let members = variant_builder.members;
if members.is_empty() {
pending_variants.push(Variant { name: variant_builder.name, members: VariantMembers::Unit });
continue;
}
let record_variant = matches!(members.get(0).unwrap(), VariantMemberBuilder::KeyVal(..));
if record_variant {
let pending_members = members.into_iter().map(|var| match var {
VariantMemberBuilder::KeyVal(name, ty) => (name, ty),
_ => panic!("Compiler internal error: variant mismatch"),
});
//TODO make this mapping meaningful
let type_ids = pending_members
.into_iter()
.map(|(name, _ty_id)| (name, self.type_id_store.fresh()))
.collect();
pending_variants
.push(Variant { name: variant_builder.name, members: VariantMembers::Record(type_ids) });
} else {
let pending_members = members.into_iter().map(|var| match var {
VariantMemberBuilder::Pending(pending_type) => pending_type,
_ => panic!("Compiler internal error: variant mismatch"),
});
//TODO make this mapping meaningful
let type_ids = pending_members.into_iter().map(|_ty_id| self.type_id_store.fresh()).collect();
pending_variants
.push(Variant { name: variant_builder.name, members: VariantMembers::Tuple(type_ids) });
}
}
// Eventually, I will want to have a better way of determining which numeric tag goes with
// which variant. For now, just sort them alphabetically.
pending_variants.sort_unstable_by(|a, b| a.name.cmp(&b.name));
let defined = DefinedType { name: builder.name, variants: pending_variants };
self.defined_types.insert(type_id, defined);
type_id
}
pub fn variant_local_name(&self, type_id: &TypeId, tag: u32) -> Option<&str> {
self.defined_types
.get(type_id)
.and_then(|defined| defined.variants.get(tag as usize))
.map(|variant| variant.name.as_ref())
}
pub fn lookup_variant_arity(&self, type_id: &TypeId, tag: u32) -> Option<u32> {
self.defined_types.get(type_id).and_then(|defined| defined.variants.get(tag as usize)).map(
|variant| match &variant.members {
VariantMembers::Unit => 0,
VariantMembers::Tuple(items) => items.len() as u32,
VariantMembers::Record(items) => items.len() as u32,
},
)
}
pub fn lookup_record_members(&self, type_id: &TypeId, tag: u32) -> Option<&[(String, TypeId)]> {
self.defined_types.get(type_id).and_then(|defined| defined.variants.get(tag as usize)).and_then(
|variant| match &variant.members {
VariantMembers::Record(items) => Some(items.as_ref()),
_ => None,
},
)
}
pub fn lookup_type(&self, type_id: &TypeId) -> Option<&DefinedType> {
self.defined_types.get(type_id)
}
//TODO return some kind of overall type later?
pub fn typecheck(&mut self, ast: &AST) -> Result<(), TypeError> {
Ok(())
}
}
/// A type defined in program source code, as opposed to a builtin.
#[allow(dead_code)]
#[derive(Debug)]
pub struct DefinedType {
pub name: String,
// the variants are in this list according to tag order
pub variants: Vec<Variant>,
}
#[derive(Debug)]
pub struct Variant {
pub name: String,
pub members: VariantMembers,
}
#[derive(Debug)]
pub enum VariantMembers {
Unit,
// Should be non-empty
Tuple(Vec<TypeId>),
Record(Vec<(String, TypeId)>),
}
/// Represents a type mentioned as a member of another type during the type registration process.
/// It may not have been registered itself in the relevant context.
#[allow(dead_code)]
#[derive(Debug)]
pub struct PendingType {
inner: TypeIdentifier,
}
impl From<&TypeIdentifier> for PendingType {
fn from(type_identifier: &TypeIdentifier) -> Self {
Self { inner: type_identifier.clone() }
}
}
#[derive(Debug)]
pub struct TypeBuilder {
name: String,
variants: Vec<VariantBuilder>,
}
impl TypeBuilder {
pub fn new(name: &str) -> Self {
Self { name: name.to_string(), variants: vec![] }
}
pub fn add_variant(&mut self, vb: VariantBuilder) {
self.variants.push(vb);
}
}
#[derive(Debug)]
pub struct VariantBuilder {
name: String,
members: Vec<VariantMemberBuilder>,
}
impl VariantBuilder {
pub fn new(name: &str) -> Self {
Self { name: name.to_string(), members: vec![] }
}
pub fn add_member(&mut self, member_ty: PendingType) {
self.members.push(VariantMemberBuilder::Pending(member_ty));
}
// You can't call this and `add_member` on the same fn, there should be a runtime error when
// that's detected.
pub fn add_record_member(&mut self, name: &str, ty: PendingType) {
self.members.push(VariantMemberBuilder::KeyVal(name.to_string(), ty));
}
}
#[derive(Debug)]
enum VariantMemberBuilder {
Pending(PendingType),
KeyVal(String, PendingType),
}
#[derive(Debug, Clone)]
pub struct TypeError {
pub msg: String,
}
#[allow(dead_code)]
#[derive(Debug, Clone, PartialEq, Eq)]
pub enum TypeConst {
Unit,
Nat,
Int,
Float,
StringT,
Bool,
Ordering,
}
#[allow(dead_code)]
#[derive(Debug, Clone, PartialEq)]
pub enum Type {
Const(TypeConst),
//Var(TypeVar),
Arrow { params: Vec<Type>, ret: Box<Type> },
Compound { ty_name: String, args: Vec<Type> },
}
macro_rules! ty {
($type_name:ident) => {
Type::Const(crate::type_inference::TypeConst::$type_name)
};
($t1:ident -> $t2:ident) => {
Type::Arrow { params: vec![ty!($t1)], ret: Box::new(ty!($t2)) }
};
($t1:ident -> $t2:ident -> $t3:ident) => {
Type::Arrow { params: vec![ty!($t1), ty!($t2)], ret: Box::new(ty!($t3)) }
};
($type_list:ident, $ret_type:ident) => {
Type::Arrow { params: $type_list, ret: Box::new($ret_type) }
};
}

View File

@ -1,522 +0,0 @@
use std::rc::Rc;
use std::convert::TryFrom;
use std::fmt;
use ena::unify::{UnifyKey, InPlaceUnificationTable, UnificationTable, EqUnifyValue};
use crate::builtin::Builtin;
use crate::ast::*;
use crate::util::ScopeStack;
use crate::util::deref_optional_box;
#[derive(Debug, Clone, PartialEq)]
pub struct TypeData {
ty: Option<Type>
}
impl TypeData {
#[allow(dead_code)]
pub fn new() -> TypeData {
TypeData { ty: None }
}
}
//TODO need to hook this into the actual typechecking system somehow
#[derive(Debug, Clone)]
pub struct TypeId {
local_name: Rc<String>
}
impl TypeId {
//TODO this is definitely incomplete
pub fn lookup_name(name: &str) -> TypeId {
TypeId {
local_name: Rc::new(name.to_string())
}
}
pub fn local_name(&self) -> &str {
self.local_name.as_ref()
}
}
impl fmt::Display for TypeId {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
write!(f, "TypeId:{}", self.local_name)
}
}
pub struct TypeContext<'a> {
variable_map: ScopeStack<'a, Rc<String>, Type>,
unification_table: InPlaceUnificationTable<TypeVar>,
}
/// `InferResult` is the monad in which type inference takes place.
type InferResult<T> = Result<T, TypeError>;
#[derive(Debug, Clone)]
pub struct TypeError { pub msg: String }
impl TypeError {
fn new<A, T>(msg: T) -> InferResult<A> where T: Into<String> {
Err(TypeError { msg: msg.into() })
}
}
#[allow(dead_code)] // avoids warning from Compound
#[derive(Debug, Clone, PartialEq)]
pub enum Type {
Const(TypeConst),
Var(TypeVar),
Arrow {
params: Vec<Type>,
ret: Box<Type>
},
Compound {
ty_name: String,
args:Vec<Type>
}
}
#[derive(Debug, Clone, Copy, PartialEq, Eq, Hash)]
pub struct TypeVar(usize);
impl UnifyKey for TypeVar {
type Value = Option<TypeConst>;
fn index(&self) -> u32 { self.0 as u32 }
fn from_index(u: u32) -> TypeVar { TypeVar(u as usize) }
fn tag() -> &'static str { "TypeVar" }
}
#[derive(Debug, Clone, PartialEq, Eq)]
pub enum TypeConst {
Unit,
Nat,
Int,
Float,
StringT,
Bool,
Ordering,
//UserDefined
}
impl TypeConst {
/*
#[allow(dead_code)]
pub fn to_string(&self) -> String {
use self::TypeConst::*;
match self {
Unit => "()".to_string(),
Nat => "Nat".to_string(),
Int => "Int".to_string(),
Float => "Float".to_string(),
StringT => "String".to_string(),
Bool => "Bool".to_string(),
Ordering => "Ordering".to_string(),
}
}
*/
}
impl EqUnifyValue for TypeConst { }
macro_rules! ty {
($type_name:ident) => { Type::Const(TypeConst::$type_name) };
($t1:ident -> $t2:ident) => { Type::Arrow { params: vec![ty!($t1)], ret: box ty!($t2) } };
($t1:ident -> $t2:ident -> $t3:ident) => { Type::Arrow { params: vec![ty!($t1), ty!($t2)], ret: box ty!($t3) } };
($type_list:ident, $ret_type:ident) => {
Type::Arrow {
params: $type_list,
ret: box $ret_type,
}
}
}
//TODO find a better way to capture the to/from string logic
impl Type {
/*
#[allow(dead_code)]
pub fn to_string(&self) -> String {
use self::Type::*;
match self {
Const(c) => c.to_string(),
Var(v) => format!("t_{}", v.0),
Arrow { params, box ref ret } => {
if params.is_empty() {
format!("-> {}", ret.to_string())
} else {
let mut buf = String::new();
for p in params.iter() {
write!(buf, "{} -> ", p.to_string()).unwrap();
}
write!(buf, "{}", ret.to_string()).unwrap();
buf
}
},
Compound { .. } => "<some compound type>".to_string()
}
}
*/
fn from_string(string: &str) -> Option<Type> {
Some(match string {
"()" | "Unit" => ty!(Unit),
"Nat" => ty!(Nat),
"Int" => ty!(Int),
"Float" => ty!(Float),
"String" => ty!(StringT),
"Bool" => ty!(Bool),
"Ordering" => ty!(Ordering),
_ => return None
})
}
}
/*
/// `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),
unification_table: UnificationTable::new(),
}
}
/*
fn new_env(&'a self, new_var: Rc<String>, ty: Type) -> TypeContext<'a> {
let mut new_context = TypeContext {
variable_map: self.variable_map.new_scope(None),
unification_table: UnificationTable::new(), //???? not sure if i want this
};
new_context.variable_map.insert(new_var, ty);
new_context
}
*/
fn get_type_from_name(&self, name: &TypeIdentifier) -> InferResult<Type> {
use self::TypeIdentifier::*;
Ok(match name {
Singleton(TypeSingletonName { name,.. }) => {
match Type::from_string(name) {
Some(ty) => ty,
None => return TypeError::new(format!("Unknown type name: {}", name))
}
},
Tuple(_) => return TypeError::new("tuples aren't ready yet"),
})
}
/// `typecheck` is the entry into the type-inference system, accepting an AST as an argument
/// Following the example of GHC, the compiler deliberately does typechecking before de-sugaring
/// the AST to ReducedAST
pub fn typecheck(&mut self, ast: &AST) -> Result<Type, TypeError> {
let mut returned_type = Type::Const(TypeConst::Unit);
for statement in ast.statements.statements.iter() {
returned_type = self.statement(statement)?;
}
Ok(returned_type)
}
fn statement(&mut self, statement: &Statement) -> InferResult<Type> {
match &statement.kind {
StatementKind::Expression(e) => self.expr(e),
StatementKind::Declaration(decl) => self.decl(decl),
StatementKind::Import(_) => Ok(ty!(Unit)),
StatementKind::Module(_) => Ok(ty!(Unit)),
}
}
fn decl(&mut self, decl: &Declaration) -> InferResult<Type> {
use self::Declaration::*;
if let Binding { name, expr, .. } = decl {
let ty = self.expr(expr)?;
self.variable_map.insert(name.clone(), ty);
}
Ok(ty!(Unit))
}
fn invoc(&mut self, invoc: &InvocationArgument) -> InferResult<Type> {
use InvocationArgument::*;
match invoc {
Positional(expr) => self.expr(expr),
_ => Ok(ty!(Nat)) //TODO this is wrong
}
}
fn expr(&mut self, expr: &Expression) -> InferResult<Type> {
match expr {
Expression { kind, type_anno: Some(anno), .. } => {
let t1 = self.expr_type(kind)?;
let t2 = self.get_type_from_name(anno)?;
self.unify(t2, t1)
},
Expression { kind, type_anno: None, .. } => self.expr_type(kind)
}
}
fn expr_type(&mut self, expr: &ExpressionKind) -> InferResult<Type> {
use self::ExpressionKind::*;
Ok(match expr {
NatLiteral(_) => ty!(Nat),
BoolLiteral(_) => ty!(Bool),
FloatLiteral(_) => ty!(Float),
StringLiteral(_) => ty!(StringT),
PrefixExp(op, expr) => self.prefix(op, expr)?,
BinExp(op, lhs, rhs) => self.binexp(op, lhs, rhs)?,
IfExpression { discriminator, body } => self.if_expr(deref_optional_box(discriminator), &**body)?,
Value(val) => self.handle_value(val)?,
Call { box ref f, arguments } => self.call(f, arguments)?,
Lambda { params, type_anno, body } => self.lambda(params, type_anno, body)?,
_ => ty!(Unit),
})
}
fn prefix(&mut self, op: &PrefixOp, expr: &Expression) -> InferResult<Type> {
let builtin: Option<Builtin> = TryFrom::try_from(op).ok();
let tf = match builtin.map(|b| b.get_type()) {
Some(ty) => ty,
None => return TypeError::new("no type found")
};
let tx = self.expr(expr)?;
self.handle_apply(tf, vec![tx])
}
fn binexp(&mut self, op: &BinOp, lhs: &Expression, rhs: &Expression) -> InferResult<Type> {
let builtin: Option<Builtin> = TryFrom::try_from(op).ok();
let tf = match builtin.map(|b| b.get_type()) {
Some(ty) => ty,
None => return TypeError::new("no type found"),
};
let t_lhs = self.expr(lhs)?;
let t_rhs = self.expr(rhs)?; //TODO is this order a problem? not sure
self.handle_apply(tf, vec![t_lhs, t_rhs])
}
fn if_expr(&mut self, discriminator: Option<&Expression>, body: &IfExpressionBody) -> InferResult<Type> {
use self::IfExpressionBody::*;
match (discriminator, body) {
(Some(expr), SimpleConditional{ then_case, else_case }) => self.handle_simple_if(expr, then_case, else_case),
_ => TypeError::new("Complex conditionals not supported".to_string())
}
}
#[allow(clippy::ptr_arg)]
fn handle_simple_if(&mut self, expr: &Expression, then_clause: &Block, else_clause: &Option<Block>) -> InferResult<Type> {
let t1 = self.expr(expr)?;
let t2 = self.block(then_clause)?;
let t3 = match else_clause {
Some(block) => self.block(block)?,
None => ty!(Unit)
};
let _ = self.unify(ty!(Bool), t1)?;
self.unify(t2, t3)
}
#[allow(clippy::ptr_arg)]
fn lambda(&mut self, params: &Vec<FormalParam>, type_anno: &Option<TypeIdentifier>, _body: &Block) -> InferResult<Type> {
let argument_types: InferResult<Vec<Type>> = params.iter().map(|param: &FormalParam| {
if let FormalParam { anno: Some(type_identifier), .. } = param {
self.get_type_from_name(type_identifier)
} else {
Ok(Type::Var(self.fresh_type_variable()))
}
}).collect();
let argument_types = argument_types?;
let ret_type = match type_anno.as_ref() {
Some(anno) => self.get_type_from_name(anno)?,
None => Type::Var(self.fresh_type_variable())
};
Ok(ty!(argument_types, ret_type))
}
fn call(&mut self, f: &Expression, args: &[ InvocationArgument ]) -> InferResult<Type> {
let tf = self.expr(f)?;
let arg_types: InferResult<Vec<Type>> = args.iter().map(|ex| self.invoc(ex)).collect();
let arg_types = arg_types?;
self.handle_apply(tf, arg_types)
}
fn handle_apply(&mut self, tf: Type, args: Vec<Type>) -> InferResult<Type> {
Ok(match tf {
Type::Arrow { ref params, ret: box ref t_ret } if params.len() == args.len() => {
for (t_param, t_arg) in params.iter().zip(args.iter()) {
let _ = self.unify(t_param.clone(), t_arg.clone())?; //TODO I think this needs to reference a sub-scope
}
t_ret.clone()
},
Type::Arrow { .. } => return TypeError::new("Wrong length"),
_ => return TypeError::new("Not a function".to_string())
})
}
#[allow(clippy::ptr_arg)]
fn block(&mut self, block: &Block) -> InferResult<Type> {
let mut output = ty!(Unit);
for statement in block.statements.iter() {
output = self.statement(statement)?;
}
Ok(output)
}
fn handle_value(&mut self, val: &QualifiedName) -> InferResult<Type> {
let QualifiedName { components: vec, .. } = val;
let var = &vec[0];
match self.variable_map.lookup(var) {
Some(ty) => Ok(ty.clone()),
None => TypeError::new(format!("Couldn't find variable: {}", &var)),
}
}
fn unify(&mut self, t1: Type, t2: Type) -> InferResult<Type> {
use self::Type::*;
match (t1, t2) {
(Const(ref c1), Const(ref c2)) if c1 == c2 => Ok(Const(c1.clone())), //choice of c1 is arbitrary I *think*
(a @ Var(_), b @ Const(_)) => self.unify(b, a),
(Const(ref c1), Var(ref v2)) => {
self.unification_table.unify_var_value(*v2, Some(c1.clone()))
.or_else(|_| TypeError::new(format!("Couldn't unify {:?} and {:?}", Const(c1.clone()), Var(*v2))))?;
Ok(Const(c1.clone()))
},
(Var(v1), Var(v2)) => {
//TODO add occurs check
self.unification_table.unify_var_var(v1, v2)
.or_else(|e| {
println!("Unify error: {:?}", e);
TypeError::new(format!("Two type variables {:?} and {:?} couldn't unify", v1, v2))
})?;
Ok(Var(v1)) //arbitrary decision I think
},
(a, b) => TypeError::new(format!("{:?} and {:?} do not unify", a, b)),
}
}
fn fresh_type_variable(&mut self) -> TypeVar {
self.unification_table.new_key(None)
}
}
#[cfg(test)]
mod typechecking_tests {
use super::*;
macro_rules! assert_type_in_fresh_context {
($string:expr, $type:expr) => {
let mut tc = TypeContext::new();
let ast = &crate::util::quick_ast($string);
let ty = tc.typecheck(ast).unwrap();
assert_eq!(ty, $type)
}
}
#[test]
fn basic_test() {
assert_type_in_fresh_context!("1", ty!(Nat));
assert_type_in_fresh_context!(r#""drugs""#, ty!(StringT));
assert_type_in_fresh_context!("true", ty!(Bool));
}
#[test]
fn operators() {
//TODO fix these with new operator regime
/*
assert_type_in_fresh_context!("-1", ty!(Int));
assert_type_in_fresh_context!("1 + 2", ty!(Nat));
assert_type_in_fresh_context!("-2", ty!(Int));
assert_type_in_fresh_context!("!true", ty!(Bool));
*/
}
}

View File

@ -1,85 +0,0 @@
use std::{cmp::Eq, collections::HashMap, fmt::Write, hash::Hash};
/// Utility function for printing a comma-delimited list of things
pub(crate) fn delim_wrapped(lhs: char, rhs: char, terms: impl Iterator<Item = String>) -> String {
let mut buf = String::new();
write!(buf, "{}", lhs).unwrap();
for term in terms.map(Some).intersperse(None) {
match term {
Some(e) => write!(buf, "{}", e).unwrap(),
None => write!(buf, ", ").unwrap(),
};
}
write!(buf, "{}", rhs).unwrap();
buf
}
#[derive(Default, Debug)]
pub struct ScopeStack<'a, T: 'a, V: 'a, N = String>
where T: Hash + Eq
{
parent: Option<&'a ScopeStack<'a, T, V, N>>,
values: HashMap<T, V>,
scope_name: Option<N>,
}
impl<'a, T, V, N> ScopeStack<'a, T, V, N>
where T: Hash + Eq
{
pub fn new(scope_name: Option<N>) -> Self
where T: Hash + Eq {
ScopeStack { parent: None, values: HashMap::new(), scope_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, scope_name: Option<N>) -> Self
where T: Hash + Eq {
ScopeStack { parent: Some(self), values: HashMap::default(), scope_name }
}
#[allow(dead_code)]
pub fn lookup_with_scope(&self, key: &T) -> Option<(&V, Option<&N>)>
where T: Hash + Eq {
match (self.values.get(key), self.parent) {
(None, None) => None,
(None, Some(parent)) => parent.lookup_with_scope(key),
(Some(value), _) => Some((value, self.scope_name.as_ref())),
}
}
pub fn get_name(&self) -> Option<&N> {
self.scope_name.as_ref()
}
}
/// Quickly create an AST from a string, with no error checking. For test use only
#[cfg(test)]
pub fn quick_ast(input: &str) -> crate::ast::AST {
let mut parser = crate::parsing::Parser::new();
let output = parser.parse(input);
match output {
Ok(output) => output,
Err(err) => {
println!("Parse error: {}", err.msg);
panic!();
}
}
}
#[allow(unused_macros)]
macro_rules! rc {
($string:tt) => {
Rc::new(stringify!($string).to_string())
};
}

BIN
schala-logo.ico Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 5.8 KiB

8
schala-main/Cargo.toml Normal file
View File

@ -0,0 +1,8 @@
[package]
name = "schala-main"
version = "0.1.0"
edition = "2021"
# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
[dependencies]

3
schala-main/src/main.rs Normal file
View File

@ -0,0 +1,3 @@
fn main() {
println!("Schala");
}

8
schala-parser/Cargo.toml Normal file
View File

@ -0,0 +1,8 @@
[package]
name = "schala-parser"
version = "0.1.0"
edition = "2021"
# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
[dependencies]

View File

@ -0,0 +1,3 @@
fn main() {
println!("Hello, world!");
}

View File

@ -1,23 +0,0 @@
[package]
name = "schala-repl"
version = "0.1.0"
authors = ["greg <greg.shuflin@protonmail.com>"]
edition = "2021"
[dependencies]
llvm-sys = "70.0.2"
take_mut = "0.2.2"
itertools = "0.10"
lazy_static = "0.2.8"
maplit = "*"
colored = "1.8"
serde = "1.0"
serde_derive = "1.0"
serde_json = "1.0"
phf = "0.7.12"
includedir = "0.2.0"
linefeed = "0.6.0"
regex = "0.2"
[build-dependencies]
includedir_codegen = "0.2.0"

View File

@ -1,7 +0,0 @@
extern crate includedir_codegen;
use includedir_codegen::Compression;
fn main() {
includedir_codegen::start("WEBFILES").dir("../static", Compression::Gzip).build("static.rs").unwrap();
}

View File

@ -1,116 +0,0 @@
use colored::*;
use crate::{
directive_actions::DirectiveAction, language::ProgrammingLanguageInterface, InterpreterDirectiveOutput,
Repl,
};
/// A CommandTree is either a `Terminal` or a `NonTerminal`. When command parsing reaches the first
/// Terminal, it will use the `DirectiveAction` found there to find an appropriate function to execute,
/// and then execute it with any remaining arguments
#[derive(Clone)]
pub enum CommandTree {
Terminal {
name: String,
children: Vec<CommandTree>,
help_msg: Option<String>,
action: DirectiveAction,
},
NonTerminal {
name: String,
children: Vec<CommandTree>,
help_msg: Option<String>,
action: DirectiveAction,
},
Top(Vec<CommandTree>),
}
impl CommandTree {
pub fn nonterm_no_further_tab_completions(s: &str, help: Option<&str>) -> CommandTree {
CommandTree::NonTerminal {
name: s.to_string(),
help_msg: help.map(|x| x.to_string()),
children: vec![],
action: DirectiveAction::Null,
}
}
pub fn terminal(
s: &str,
help: Option<&str>,
children: Vec<CommandTree>,
action: DirectiveAction,
) -> CommandTree {
CommandTree::Terminal { name: s.to_string(), help_msg: help.map(|x| x.to_string()), children, action }
}
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,
action: DirectiveAction::Null,
}
}
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("<no help text provided>"),
CommandTree::NonTerminal { help_msg, .. } =>
help_msg.as_ref().map(|s| s.as_str()).unwrap_or("<no help text provided>"),
CommandTree::Top(_) => "",
}
}
pub fn get_children(&self) -> &Vec<CommandTree> {
use CommandTree::*;
match self {
Terminal { children, .. } | NonTerminal { children, .. } | Top(children) => children,
}
}
pub fn get_subcommands(&self) -> Vec<&str> {
self.get_children().iter().map(|x| x.get_cmd()).collect()
}
pub fn perform<L: ProgrammingLanguageInterface>(
&self,
repl: &mut Repl<L>,
arguments: &[&str],
) -> InterpreterDirectiveOutput {
let mut dir_pointer: &CommandTree = self;
let mut idx = 0;
let res: Result<(DirectiveAction, usize), String> = loop {
match dir_pointer {
CommandTree::Top(subcommands) | CommandTree::NonTerminal { children: subcommands, .. } => {
let next_command = match arguments.get(idx) {
Some(cmd) => cmd,
None => break Err("Command requires arguments".to_owned()),
};
idx += 1;
match subcommands.iter().find(|sc| sc.get_cmd() == *next_command) {
Some(command_tree) => {
dir_pointer = command_tree;
}
None => break Err(format!("Command {} not found", next_command)),
};
}
CommandTree::Terminal { action, .. } => {
break Ok((action.clone(), idx));
}
}
};
match res {
Ok((action, idx)) => action.perform(repl, &arguments[idx..]),
Err(err) => Some(err.red().to_string()),
}
}
}

View File

@ -1,77 +0,0 @@
use std::fmt::Write as FmtWrite;
use crate::{
help::help,
language::{LangMetaRequest, LangMetaResponse, ProgrammingLanguageInterface},
InterpreterDirectiveOutput, Repl,
};
#[derive(Debug, Clone)]
pub enum DirectiveAction {
Null,
Help,
QuitProgram,
ListPasses,
TotalTime(bool),
StageTime(bool),
Doc,
}
impl DirectiveAction {
pub fn perform<L: ProgrammingLanguageInterface>(
&self,
repl: &mut Repl<L>,
arguments: &[&str],
) -> InterpreterDirectiveOutput {
use DirectiveAction::*;
match self {
Null => None,
Help => help(repl, arguments),
QuitProgram => {
repl.save_before_exit();
::std::process::exit(0)
}
ListPasses => {
let pass_names = match repl.language_state.request_meta(LangMetaRequest::StageNames) {
LangMetaResponse::StageNames(names) => names,
_ => vec![],
};
let mut buf = String::new();
for pass in pass_names.iter().map(Some).intersperse(None) {
match pass {
Some(pass) => write!(buf, "{}", pass).unwrap(),
None => write!(buf, " -> ").unwrap(),
}
}
Some(buf)
}
TotalTime(value) => {
repl.options.show_total_time = *value;
None
}
StageTime(value) => {
repl.options.show_stage_times = *value;
None
}
Doc => doc(repl, arguments),
}
}
}
fn doc<L: ProgrammingLanguageInterface>(
repl: &mut Repl<L>,
arguments: &[&str],
) -> InterpreterDirectiveOutput {
arguments
.get(0)
.map(|cmd| {
let source = cmd.to_string();
let meta = LangMetaRequest::Docs { source };
match repl.language_state.request_meta(meta) {
LangMetaResponse::Docs { doc_string } => Some(doc_string),
_ => Some("Invalid doc response".to_owned()),
}
})
.unwrap_or_else(|| Some(":docs needs an argument".to_owned()))
}

View File

@ -1,68 +0,0 @@
use crate::{command_tree::CommandTree, directive_actions::DirectiveAction};
pub fn directives_from_pass_names(pass_names: &[String]) -> CommandTree {
let passes_directives: Vec<CommandTree> = pass_names
.iter()
.map(|pass_name| {
if pass_name == "parsing" {
CommandTree::nonterm(
pass_name,
None,
vec![
CommandTree::nonterm_no_further_tab_completions("compact", None),
CommandTree::nonterm_no_further_tab_completions("expanded", None),
CommandTree::nonterm_no_further_tab_completions("trace", None),
],
)
} else {
CommandTree::nonterm_no_further_tab_completions(pass_name, None)
}
})
.collect();
CommandTree::Top(get_list(&passes_directives, true))
}
fn get_list(passes_directives: &[CommandTree], include_help: bool) -> Vec<CommandTree> {
use DirectiveAction::*;
vec![
CommandTree::terminal("exit", Some("exit the REPL"), vec![], QuitProgram),
//TODO there should be an alias for this
CommandTree::terminal("quit", Some("exit the REPL"), vec![], QuitProgram),
CommandTree::terminal(
"help",
Some("Print this help message"),
if include_help { get_list(passes_directives, false) } else { vec![] },
Help,
),
CommandTree::nonterm(
"debug",
Some("Configure debug information"),
vec![
CommandTree::terminal(
"list-passes",
Some("List all registered compiler passes"),
vec![],
ListPasses,
),
CommandTree::nonterm(
"total-time",
None,
vec![
CommandTree::terminal("on", None, vec![], TotalTime(true)),
CommandTree::terminal("off", None, vec![], TotalTime(false)),
],
),
CommandTree::nonterm(
"stage-times",
Some("Computation time per-stage"),
vec![
CommandTree::terminal("on", None, vec![], StageTime(true)),
CommandTree::terminal("off", None, vec![], StageTime(false)),
],
),
],
),
CommandTree::terminal("doc", Some("Get language-specific help for an item"), vec![], Doc),
]
}

View File

@ -1,63 +0,0 @@
use std::fmt::Write as FmtWrite;
use colored::*;
use crate::{
command_tree::CommandTree, language::ProgrammingLanguageInterface, InterpreterDirectiveOutput, Repl,
};
pub fn help<L: ProgrammingLanguageInterface>(
repl: &mut Repl<L>,
arguments: &[&str],
) -> InterpreterDirectiveOutput {
match arguments {
[] => global_help(repl),
commands => {
let dirs = repl.get_directives();
Some(match get_directive_from_commands(commands, &dirs) {
None => format!("Directive `{}` not found", commands.last().unwrap()),
Some(dir) => {
let mut buf = String::new();
let cmd = dir.get_cmd();
let children = dir.get_children();
writeln!(buf, "`{}` - {}", cmd, dir.get_help()).unwrap();
for sub in children.iter() {
writeln!(buf, "\t`{} {}` - {}", cmd, sub.get_cmd(), sub.get_help()).unwrap();
}
buf
}
})
}
}
}
fn get_directive_from_commands<'a>(commands: &[&str], dirs: &'a CommandTree) -> Option<&'a CommandTree> {
let mut directive_list = dirs.get_children();
let mut matched_directive = None;
for cmd in commands {
let found = directive_list.iter().find(|directive| directive.get_cmd() == *cmd);
if let Some(dir) = found {
directive_list = dir.get_children();
}
matched_directive = found;
}
matched_directive
}
fn global_help<L: ProgrammingLanguageInterface>(repl: &mut Repl<L>) -> InterpreterDirectiveOutput {
let mut buf = String::new();
writeln!(buf, "{} version {}", "Schala REPL".bright_red().bold(), crate::VERSION_STRING).unwrap();
writeln!(buf, "-----------------------").unwrap();
for directive in repl.get_directives().get_children() {
writeln!(buf, "{}{} - {}", repl.sigil, directive.get_cmd(), directive.get_help()).unwrap();
}
writeln!(buf).unwrap();
writeln!(buf, "Language-specific help for {}", <L as ProgrammingLanguageInterface>::language_name())
.unwrap();
writeln!(buf, "-----------------------").unwrap();
Some(buf)
}

View File

@ -1,56 +0,0 @@
use std::{collections::HashSet, time};
pub trait ProgrammingLanguageInterface {
type Config: Default + Clone;
fn language_name() -> String;
fn source_file_suffix() -> String;
fn run_computation(&mut self, _request: ComputationRequest<Self::Config>) -> ComputationResponse;
fn request_meta(&mut self, _request: LangMetaRequest) -> LangMetaResponse {
LangMetaResponse::Custom { kind: "not-implemented".to_owned(), value: format!("") }
}
}
pub struct ComputationRequest<'a, T> {
pub source: &'a str,
pub config: T,
pub debug_requests: HashSet<DebugAsk>,
}
pub struct ComputationResponse {
pub main_output: Result<String, String>,
pub global_output_stats: GlobalOutputStats,
pub debug_responses: Vec<DebugResponse>,
}
#[derive(Default, Debug)]
pub struct GlobalOutputStats {
pub total_duration: time::Duration,
pub stage_durations: Vec<(String, time::Duration)>,
}
#[derive(Debug, Clone, Hash, Eq, PartialEq, Deserialize, Serialize)]
pub enum DebugAsk {
Timing,
ByStage { stage_name: String, token: Option<String> },
}
pub struct DebugResponse {
pub ask: DebugAsk,
pub value: String,
}
pub enum LangMetaRequest {
StageNames,
Docs { source: String },
Custom { kind: String, value: String },
ImmediateDebug(DebugAsk),
}
pub enum LangMetaResponse {
StageNames(Vec<String>),
Docs { doc_string: String },
Custom { kind: String, value: String },
ImmediateDebug(DebugResponse),
}

View File

@ -1,249 +0,0 @@
#![feature(box_patterns, proc_macro_hygiene, decl_macro, iter_intersperse)]
#[macro_use]
extern crate serde_derive;
extern crate includedir;
extern crate phf;
extern crate serde_json;
mod command_tree;
mod language;
use self::command_tree::CommandTree;
mod repl_options;
use repl_options::ReplOptions;
mod directive_actions;
mod directives;
use directives::directives_from_pass_names;
mod help;
mod response;
use std::{collections::HashSet, sync::Arc};
use colored::*;
pub use language::{
ComputationRequest, ComputationResponse, DebugAsk, DebugResponse, GlobalOutputStats, LangMetaRequest,
LangMetaResponse, ProgrammingLanguageInterface,
};
use response::ReplResponse;
include!(concat!(env!("OUT_DIR"), "/static.rs"));
const VERSION_STRING: &str = "0.1.0";
const HISTORY_SAVE_FILE: &str = ".schala_history";
const OPTIONS_SAVE_FILE: &str = ".schala_repl";
type InterpreterDirectiveOutput = Option<String>;
pub struct Repl<L: ProgrammingLanguageInterface> {
/// If this is the first character typed by a user into the repl, the following
/// will be interpreted as a directive to the REPL rather than a command in the
/// running programming language.
sigil: char,
line_reader: ::linefeed::interface::Interface<::linefeed::terminal::DefaultTerminal>,
language_state: L,
options: ReplOptions,
}
#[derive(Clone)]
enum PromptStyle {
Normal,
Multiline,
}
impl<L: ProgrammingLanguageInterface> Repl<L> {
pub fn new(initial_state: L) -> Self {
use linefeed::Interface;
let line_reader = Interface::new("schala-repl").unwrap();
let sigil = ':';
Repl { sigil, line_reader, language_state: initial_state, options: ReplOptions::new() }
}
pub fn run_repl(&mut self, config: L::Config) {
println!("Schala meta-interpeter version {}", VERSION_STRING);
println!("Type {} for help with the REPL", format!("{}help", self.sigil).bright_green().bold());
self.load_options();
self.handle_repl_loop(config);
self.save_before_exit();
println!("Exiting...");
}
fn load_options(&mut self) {
self.line_reader.load_history(HISTORY_SAVE_FILE).unwrap_or(());
match ReplOptions::load_from_file(OPTIONS_SAVE_FILE) {
Ok(options) => {
self.options = options;
}
Err(e) => eprintln!("{}", e),
}
}
fn handle_repl_loop(&mut self, config: L::Config) {
use linefeed::ReadResult::*;
'main: loop {
macro_rules! match_or_break {
($line:expr) => {
match $line {
Err(e) => {
println!("readline IO Error: {}", e);
break 'main;
}
Ok(Eof) | Ok(Signal(_)) => break 'main,
Ok(Input(ref input)) => input,
}
};
}
self.update_line_reader();
let line = self.line_reader.read_line();
let input: &str = match_or_break!(line);
self.line_reader.add_history_unique(input.to_string());
let mut chars = input.chars().peekable();
let repl_responses = match chars.next() {
Some(ch) if ch == self.sigil =>
if chars.peek() == Some(&'{') {
let mut buf = String::new();
buf.push_str(input.get(2..).unwrap());
'multiline: loop {
self.set_prompt(PromptStyle::Multiline);
let new_line = self.line_reader.read_line();
let new_input = match_or_break!(new_line);
if new_input.starts_with(":}") {
break 'multiline;
} else {
buf.push_str(new_input);
buf.push('\n');
}
}
self.handle_input(&buf, &config)
} else {
if let Some(output) = self.handle_interpreter_directive(input.get(1..).unwrap()) {
println!("{}", output);
}
continue;
},
_ => self.handle_input(input, &config),
};
for repl_response in repl_responses.iter() {
println!("{}", repl_response);
}
}
}
fn update_line_reader(&mut self) {
let tab_complete_handler = TabCompleteHandler::new(self.sigil, self.get_directives());
self.line_reader.set_completer(Arc::new(tab_complete_handler)); //TODO fix this here
self.set_prompt(PromptStyle::Normal);
}
fn set_prompt(&mut self, prompt_style: PromptStyle) {
let prompt_str = match prompt_style {
PromptStyle::Normal => ">> ",
PromptStyle::Multiline => ">| ",
};
self.line_reader.set_prompt(prompt_str).unwrap();
}
fn save_before_exit(&self) {
self.line_reader.save_history(HISTORY_SAVE_FILE).unwrap_or(());
self.options.save_to_file(OPTIONS_SAVE_FILE);
}
fn handle_interpreter_directive(&mut self, input: &str) -> InterpreterDirectiveOutput {
let arguments: Vec<&str> = input.split_whitespace().collect();
if arguments.is_empty() {
return None;
}
let directives = self.get_directives();
directives.perform(self, &arguments)
}
fn handle_input(&mut self, input: &str, config: &L::Config) -> Vec<ReplResponse> {
let mut debug_requests = HashSet::new();
for ask in self.options.debug_asks.iter() {
debug_requests.insert(ask.clone());
}
let request = ComputationRequest { source: input, config: config.clone(), debug_requests };
let response = self.language_state.run_computation(request);
response::handle_computation_response(response, &self.options)
}
fn get_directives(&mut self) -> CommandTree {
let pass_names = match self.language_state.request_meta(LangMetaRequest::StageNames) {
LangMetaResponse::StageNames(names) => names,
_ => vec![],
};
directives_from_pass_names(&pass_names)
}
}
struct TabCompleteHandler {
sigil: char,
top_level_commands: CommandTree,
}
use linefeed::{
complete::{Completer, Completion},
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(self.sigil) {
return None;
}
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 = matches!(command_tree, Some(CommandTree::Top(_)));
let word = if top { word.get(1..).unwrap() } else { word };
for cmd in command_tree.map(|x| x.get_subcommands()).unwrap_or_default().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 { children, .. } => children.iter().find(|c| c.get_cmd() == s),
});
command_tree = new_ptr;
}
}
}
Some(completions)
}
}

View File

@ -1,43 +0,0 @@
use std::{
collections::HashSet,
fs::File,
io::{self, Read, Write},
};
use crate::language::DebugAsk;
#[derive(Serialize, Deserialize)]
pub struct ReplOptions {
pub debug_asks: HashSet<DebugAsk>,
pub show_total_time: bool,
pub show_stage_times: bool,
}
impl ReplOptions {
pub fn new() -> ReplOptions {
ReplOptions { debug_asks: HashSet::new(), show_total_time: true, show_stage_times: false }
}
pub fn save_to_file(&self, filename: &str) {
let res = File::create(filename).and_then(|mut file| {
let buf = crate::serde_json::to_string(self).unwrap();
file.write_all(buf.as_bytes())
});
if let Err(err) = res {
eprintln!("Error saving {} file {}", filename, err);
}
}
pub fn load_from_file(filename: &str) -> Result<ReplOptions, io::Error> {
File::open(filename)
.and_then(|mut file| {
let mut contents = String::new();
file.read_to_string(&mut contents)?;
Ok(contents)
})
.and_then(|contents| {
let output: ReplOptions = crate::serde_json::from_str(&contents)?;
Ok(output)
})
}
}

View File

@ -1,74 +0,0 @@
use std::{fmt, fmt::Write};
use colored::*;
use crate::{
language::{ComputationResponse, DebugAsk},
ReplOptions,
};
pub struct ReplResponse {
label: Option<String>,
text: String,
color: Option<Color>,
}
impl fmt::Display for ReplResponse {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
let mut buf = String::new();
if let Some(ref label) = self.label {
write!(buf, "({})", label).unwrap();
}
write!(buf, "=> {}", self.text).unwrap();
write!(
f,
"{}",
match self.color {
Some(c) => buf.color(c),
None => buf.normal(),
}
)
}
}
pub fn handle_computation_response(
response: ComputationResponse,
options: &ReplOptions,
) -> Vec<ReplResponse> {
let mut responses = vec![];
if options.show_total_time {
responses.push(ReplResponse {
label: Some("Total time".to_string()),
text: format!("{:?}", response.global_output_stats.total_duration),
color: None,
});
}
if options.show_stage_times {
responses.push(ReplResponse {
label: Some("Stage times".to_string()),
text: format!("{:?}", response.global_output_stats.stage_durations),
color: None,
});
}
for debug_resp in response.debug_responses {
let stage_name = match debug_resp.ask {
DebugAsk::ByStage { stage_name, .. } => stage_name,
_ => continue,
};
responses.push(ReplResponse {
label: Some(stage_name.to_string()),
text: debug_resp.value,
color: Some(Color::Red),
});
}
responses.push(match response.main_output {
Ok(s) => ReplResponse { label: None, text: s, color: None },
Err(e) => ReplResponse { label: Some("Error".to_string()), text: e, color: Some(Color::Red) },
});
responses
}

View File

@ -1,11 +0,0 @@
fn outer() {
fn inner(a) {
a + 10
}
inner(20) + 8.3
}
outer()

View File

@ -1,21 +0,0 @@
fn hella(a, b) {
a + b
}
fn paha(x, y, z) {
x * y * z
}
a = 1
c = if a {
10
} else {
20
}
q = 4
q = q + 2
q + 1 + c

View File

@ -1,8 +0,0 @@
if 20 {
a = 20
b = 30
c = 40
a + b + c
} else {
Null
}

View File

@ -1,5 +0,0 @@
(fn(q) { q * 2 }(25))
a = fn(x) { x + 5 }
a(2)

View File

@ -1,17 +0,0 @@
fn add(a, b) {
a + b
}
fn subtract(a, b) {
a - b
}
fn main() {
first_value = add(20, 20)
second_value = subtract(700, 650)
first_value + second_value
}
main()

View File

@ -1,24 +0,0 @@
fn hella(x) {
print("hey")
if x == 3 {
Null
} else {
hella(x + 1)
}
}
hella(0)
fn fib(x) {
if x < 3 {
1
} else {
fib(x - 1) + fib(x - 2)
}
}
fib(10)

View File

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

View File

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

View File

@ -1,12 +0,0 @@
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())
}
}

View File

@ -1,115 +0,0 @@
fn main() {
//comments are C-style
/* nested comments /* are cool */ */
}
@annotations use the @ sigil
// variable expressions
//variable declaration works like Rust
let a: I32 = 20
let mut b: String = 20
there(); can(); be(); multiple(); statements(); per_line();
//string interpolation
// maybe
let yolo = "I have ${a + b} people in my house"
// let expressions
let a = 10, b = 20, c = 30 in a + b + c
//list literal
let q = [1,2,3,4]
//lambda literal - uses haskell-ish syntax
q.map(\(item) { item * 100 })
fn yolo(a: MyType, b: YourType): ReturnType<Param1, Param2> {
if a == 20 {
return "early"
}
}
/* for/while loop topics */
//TODO I can probably get away with having one of `for`, `while`
//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` functions as an operator asking "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
type alias <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 } // shorthand special-case for `type MyData = 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 TODO I probably want to rename this
trait Bashable { }
trait Luggable {
fn lug(self, a: Option<Self>)
}
}
// lambdas - maybe I want to use ruby-style (not rust style) syntax
// e.g.
// Also TODO Nix uses `X: Y: Z` for in its value-level syntax, why can't I?
let a: X -> Y -> Z = {|x,y| }

View File

@ -1,17 +0,0 @@
println(sua(4))
fn sua(x): Int {
x + 10
}
//let a = getline()
/*
if a == "true" {
println("You typed true")
} else {
println("You typed something else")
}
*/

View File

@ -1,12 +0,0 @@
fn a(x) {
x + 20
}
fn x(x) {
x + a(9384)
}
a(0)
x(1)

View File

@ -1,3 +0,0 @@
(display (+ 1 2))
(display "Hello")

View File

@ -1,8 +0,0 @@
fn めんどくさい(a) {
a + 20
}
print(めんどくさい(394))

View File

@ -1,7 +0,0 @@
a = 0
while a < 100000
print("hello", a)
a = a + 1
end

View File

@ -1,71 +0,0 @@
use std::{collections::HashSet, fs::File, io::Read, path::PathBuf, process::exit};
use schala_lang::{Schala, SchalaConfig};
use schala_repl::{ComputationRequest, ProgrammingLanguageInterface, Repl};
//TODO specify multiple langs, and have a way to switch between them
fn main() {
let args: Vec<String> = std::env::args().collect();
let matches = command_line_options().parse(&args[1..]).unwrap_or_else(|e| {
eprintln!("Error parsing options: {}", e);
exit(1);
});
if matches.opt_present("help") {
println!("{}", command_line_options().usage("Schala metainterpreter"));
exit(0);
}
if matches.free.is_empty() {
let state = Schala::new();
let mut repl = Repl::new(state);
let config = SchalaConfig { repl: true };
repl.run_repl(config);
} else {
let paths: Vec<PathBuf> = matches.free.iter().map(PathBuf::from).collect();
//TODO handle more than one file
let filename = &paths[0];
let extension = filename.extension().and_then(|e| e.to_str()).unwrap_or_else(|| {
eprintln!("Source file `{}` has no extension.", filename.display());
exit(1);
});
//TODO this proably should be a macro for every supported language
if extension == Schala::source_file_suffix() {
let config = SchalaConfig { repl: false };
run_noninteractive(paths, Schala::new(), config);
} else {
eprintln!("Extension .{} not recognized", extension);
exit(1);
}
}
}
pub fn run_noninteractive<L: ProgrammingLanguageInterface>(
filenames: Vec<PathBuf>,
mut language: L,
config: L::Config,
) {
// for now, ony do something with the first filename
let filename = &filenames[0];
let mut source_file = File::open(filename).unwrap();
let mut buffer = String::new();
source_file.read_to_string(&mut buffer).unwrap();
let request = ComputationRequest { source: &buffer, config, debug_requests: HashSet::new() };
let response = language.run_computation(request);
match response.main_output {
Ok(s) => println!("{}", s),
Err(s) => eprintln!("{}", s),
};
}
fn command_line_options() -> getopts::Options {
let mut options = getopts::Options::new();
options.optflag("h", "help", "Show help text");
//options.optflag("w", "webapp", "Start up web interpreter");
options
}

View File

@ -1,17 +0,0 @@
<!DOCTYPE html>
<html>
<head>
<title>Schala Metainterpreter Web Evaluator</title>
<style>
.CodeArea {
display: flex;
flex-direction: row;
}
</style>
</head>
<body>
<div id="main">
</div>
<script src="bundle.js"></script>
</body>
</html>

View File

@ -1,64 +0,0 @@
const React = require("react");
const ReactDOM = require("react-dom");
const superagent = require("superagent");
const serverAddress = "http://localhost:8000";
class CodeArea extends React.Component {
constructor(props) {
super(props);
this.state = {value: "", lastOutput: null};
this.handleChange = this.handleChange.bind(this);
this.submit = this.submit.bind(this);
}
handleChange(event) {
this.setState({value: event.target.value});
}
submit(event) {
console.log("Event", this.state.value);
const source = this.state.value;
superagent.post(`${serverAddress}/input`)
.send({ source })
.set("accept", "json")
.end((error, response) => {
if (response) {
console.log("Resp", response);
this.setState({lastOutput: response.body.text})
} else {
console.error("Error: ", error);
}
});
}
renderOutput() {
if (!this.state.lastOutput) {
return null;
}
return <textarea readOnly value={ this.state.lastOutput } />;
}
render() {
return (<div className="CodeArea">
<div className="input">
<textarea value={ this.state.value } onChange={this.handleChange}>
</textarea>
<button onClick={ this.submit }>Run!</button>
</div>
<div className="output">
{ this.renderOutput() }
</div>
</div>);
}
}
const main = (<div>
<h1>Schala web input</h1>
<p>Write your source code here</p>
<CodeArea/>
</div>);
const rootDom = document.getElementById("main");
ReactDOM.render(main, rootDom);

View File

@ -1,27 +0,0 @@
{
"name": "static",
"version": "1.0.0",
"main": "index.js",
"license": "MIT",
"dependencies": {
"babel": "^6.23.0",
"babel-preset-es2015": "^6.24.1",
"babel-preset-react": "^6.24.1",
"babelify": "^7.3.0",
"browserify": "^14.4.0",
"react": "^15.6.1",
"react-dom": "^15.6.1",
"superagent": "^3.6.3",
"uglify-js": "^3.1.1"
},
"babel": {
"presets": [
"babel-preset-react",
"babel-preset-es2015"
]
},
"scripts": {
"build": "browserify main.jsx -t babelify -o bundle.js",
"build-minify": "browserify main.jsx -t babelify | uglifyjs > bundle.js"
}
}

File diff suppressed because it is too large Load Diff

2
subtrees/parser-combinator/.gitignore vendored Normal file
View File

@ -0,0 +1,2 @@
/target
/Cargo.lock

View File

@ -0,0 +1,13 @@
[package]
name = "parser-combinator"
version = "0.1.0"
edition = "2021"
# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
[dependencies]
arbitrary = "1.2.0"
proptest = "1.0.0"
[dev-dependencies]
rstest = "0.16.0"

View File

@ -0,0 +1,10 @@
# Rust Parser Combinator
This is a super-basic Rust parser combinator library I wrote mostly
as an exercise for myself. Inspired by [nom](https://github.com/rust-bakery/nom)
and [chumsky](https://github.com/zesterer/chumsky)
## Ideas for future work
* See if some of the ideas in [Efficient Parsing with Parser Combinators](https://research.rug.nl/en/publications/efficient-parsing-with-parser-combinators)
can be incorporated here.

View File

@ -0,0 +1,198 @@
use crate::parser::{ParseResult, Parser, ParserInput, Representation};
pub fn choice2<P1, P2, I, O, E>(parser1: P1, parser2: P2) -> impl Parser<I, O, E>
where
P1: Parser<I, O, E>,
P2: Parser<I, O, E>,
I: ParserInput + Clone,
{
choice((parser1, parser2))
}
pub fn choice<C, I, O, E>(choices: C) -> impl Parser<I, O, E>
where
C: Choice<I, O, E>,
I: ParserInput + Clone,
{
let rep = choices.representation();
(move |input| choices.parse(input), rep)
}
pub trait Choice<I: Clone, O, E> {
fn parse(&self, input: I) -> ParseResult<I, O, E>;
fn representation(&self) -> Representation;
}
impl<I, O, E, P1, P2> Choice<I, O, E> for (P1, P2)
where
P1: Parser<I, O, E>,
P2: Parser<I, O, E>,
I: ParserInput + Clone,
{
fn parse(&self, input: I) -> ParseResult<I, O, E> {
let parsers = vec![&self.0 as &dyn Parser<I, O, E>, &self.1];
choice_loop(input, parsers)
}
fn representation(&self) -> Representation {
let parsers = vec![&self.0 as &dyn Parser<I, O, E>, &self.1];
repr_loop(parsers)
}
}
impl<I, O, E, P1, P2, P3> Choice<I, O, E> for (P1, P2, P3)
where
P1: Parser<I, O, E>,
P2: Parser<I, O, E>,
P3: Parser<I, O, E>,
I: ParserInput + Clone,
{
fn parse(&self, input: I) -> ParseResult<I, O, E> {
let parsers = vec![&self.0 as &dyn Parser<I, O, E>, &self.1, &self.2];
choice_loop(input, parsers)
}
fn representation(&self) -> Representation {
let parsers = vec![&self.0 as &dyn Parser<I, O, E>, &self.1, &self.2];
repr_loop(parsers)
}
}
impl<I, O, E, P1, P2, P3, P4> Choice<I, O, E> for (P1, P2, P3, P4)
where
P1: Parser<I, O, E>,
P2: Parser<I, O, E>,
P3: Parser<I, O, E>,
P4: Parser<I, O, E>,
I: ParserInput + Clone,
{
fn parse(&self, input: I) -> ParseResult<I, O, E> {
let parsers = vec![&self.0 as &dyn Parser<I, O, E>, &self.1, &self.2, &self.3];
choice_loop(input, parsers)
}
fn representation(&self) -> Representation {
let parsers = vec![&self.0 as &dyn Parser<I, O, E>, &self.1, &self.2, &self.3];
repr_loop(parsers)
}
}
impl<I, O, E, P1, P2, P3, P4, P5> Choice<I, O, E> for (P1, P2, P3, P4, P5)
where
P1: Parser<I, O, E>,
P2: Parser<I, O, E>,
P3: Parser<I, O, E>,
P4: Parser<I, O, E>,
P5: Parser<I, O, E>,
I: ParserInput + Clone,
{
fn parse(&self, input: I) -> ParseResult<I, O, E> {
let parsers = vec![
&self.0 as &dyn Parser<I, O, E>,
&self.1,
&self.2,
&self.3,
&self.4,
];
choice_loop(input, parsers)
}
fn representation(&self) -> Representation {
let parsers = vec![
&self.0 as &dyn Parser<I, O, E>,
&self.1,
&self.2,
&self.3,
&self.4,
];
repr_loop(parsers)
}
}
impl<I, O, E, P1, P2, P3, P4, P5, P6> Choice<I, O, E> for (P1, P2, P3, P4, P5, P6)
where
P1: Parser<I, O, E>,
P2: Parser<I, O, E>,
P3: Parser<I, O, E>,
P4: Parser<I, O, E>,
P5: Parser<I, O, E>,
P6: Parser<I, O, E>,
I: ParserInput + Clone,
{
fn parse(&self, input: I) -> ParseResult<I, O, E> {
let parsers = vec![
&self.0 as &dyn Parser<I, O, E>,
&self.1,
&self.2,
&self.3,
&self.4,
&self.5,
];
choice_loop(input, parsers)
}
fn representation(&self) -> Representation {
let parsers = vec![
&self.0 as &dyn Parser<I, O, E>,
&self.1,
&self.2,
&self.3,
&self.4,
&self.5,
];
repr_loop(parsers)
}
}
fn choice_loop<I, O, E>(input: I, parsers: Vec<&dyn Parser<I, O, E>>) -> ParseResult<I, O, E>
where
I: ParserInput + Clone,
{
//TODO need a more principled way to return an error when no choices work
let mut err = None;
for parser in parsers.iter() {
match parser.parse(input.clone()) {
Ok(result) => return Ok(result),
Err(e) => {
err = Some(e);
}
}
}
Err(err.unwrap())
}
fn repr_loop<I, O, E>(parsers: Vec<&dyn Parser<I, O, E>>) -> Representation
where
I: ParserInput + Clone,
{
let mut iter = parsers.iter().map(|p| p.representation());
Representation::from_choice(&mut iter)
}
#[cfg(test)]
mod tests {
use super::*;
use crate::combinators::repeated;
use crate::primitives::literal;
#[test]
fn test_choice() {
let p = choice2(
literal("gnostika").to(1),
repeated(literal(" ")).at_least(1).to(2),
);
assert_eq!(p.parse("gnostika twentynine"), Ok((1, " twentynine")));
}
#[test]
fn test_several_choices() {
let p = choice((
literal("a").to(1),
literal("q").to(10),
repeated(literal("chutney")).to(200),
literal("banana").to(10000),
));
assert_eq!(p.parse("q drugs").unwrap(), (10, " drugs"));
}
}

View File

@ -0,0 +1,16 @@
use crate::parser::{Parser, ParserInput};
pub fn map<P, F, I, O1, O2, E>(parser: P, map_fn: F) -> impl Parser<I, O2, E>
where
I: ParserInput,
P: Parser<I, O1, E>,
F: Fn(O1) -> O2,
{
let rep = parser.representation();
let p = move |input| {
parser
.parse(input)
.map(|(result, rest)| (map_fn(result), rest))
};
(p, rep)
}

View File

@ -0,0 +1,66 @@
mod map;
mod optional;
mod repeated;
mod separated_by;
pub use map::map;
pub use optional::optional;
pub use repeated::repeated;
#[cfg(test)]
mod tests {
use super::*;
use crate::parser::Parser;
use crate::primitives::literal;
#[test]
fn test_map() {
let lit_a = literal("a");
let output = lit_a.map(|s| s.to_uppercase()).parse("a yolo");
assert_eq!(output.unwrap(), ("A".to_string(), " yolo"));
}
#[test]
fn test_one_or_more() {
let p = repeated(literal("bongo ")).at_least(1);
let input = "bongo bongo bongo bongo bongo ";
let (output, rest) = p.parse(input).unwrap();
assert_eq!(rest, "");
assert_eq!(output.len(), 5);
let (output, rest) = p.parse("bongo ecks").unwrap();
assert_eq!(output.len(), 1);
assert_eq!(rest, "ecks");
}
#[test]
fn test_separated_by() {
let p = repeated(literal("garb").to(20))
.separated_by(repeated(literal(" ")).at_least(1), false);
assert_eq!(
p.parse("garb garb garb garb").unwrap(),
(vec![20, 20, 20, 20], "")
);
assert!(p.parse("garb garb garb garb ").is_err());
let p =
repeated(literal("garb").to(20)).separated_by(repeated(literal(" ")).at_least(1), true);
assert_eq!(
p.parse("garb garb garb garb").unwrap(),
(vec![20, 20, 20, 20], "")
);
assert_eq!(
p.parse("garb garb garb garb ").unwrap(),
(vec![20, 20, 20, 20], "")
);
assert_eq!(
p.parse("garb garb garb garb q").unwrap(),
(vec![20, 20, 20, 20], "q")
);
}
}

View File

@ -0,0 +1,17 @@
use crate::parser::{Parser, ParserInput, Representation};
pub fn optional<P, I, O, E>(parser: P) -> impl Parser<I, Option<O>, E>
where
P: Parser<I, O, E>,
I: ParserInput + Clone,
{
let rep = Representation::from_choice(
&mut [parser.representation(), Representation::new("ε")].into_iter(),
);
let p = move |input: I| match parser.parse(input.clone()) {
Ok((output, rest)) => Ok((Some(output), rest)),
Err(_e) => Ok((None, input)),
};
(p, rep)
}

View File

@ -0,0 +1,94 @@
use crate::combinators::separated_by::SeparatedBy;
use crate::parser::{BoxedParser, ParseResult, Parser, ParserInput, Representation};
pub fn repeated<'a, P, I, O>(parser: P) -> Repeated<'a, I, O>
where
P: Parser<I, O, I> + 'a,
I: ParserInput + Clone + 'a,
{
Repeated {
inner_parser: BoxedParser::new(parser),
at_least: None,
at_most: None,
}
}
pub struct Repeated<'a, I, O>
where
I: ParserInput + Clone,
{
pub(super) inner_parser: BoxedParser<'a, I, O, I>,
pub(super) at_least: Option<u16>,
pub(super) at_most: Option<u16>,
}
impl<'a, I, O> Repeated<'a, I, O>
where
I: ParserInput + Clone,
{
pub fn at_least(self, n: u16) -> Self {
Self {
at_least: Some(n),
..self
}
}
pub fn at_most(self, n: u16) -> Self {
Self {
at_most: Some(n),
..self
}
}
pub fn separated_by<D, O2>(self, delimiter: D, allow_trailing: bool) -> SeparatedBy<'a, I, O>
where
D: Parser<I, O2, I> + 'a,
O2: 'a,
I: 'a,
{
SeparatedBy {
inner_repeated: self,
delimiter: BoxedParser::new(delimiter.to(())),
allow_trailing,
}
}
}
impl<'a, I, O> Parser<I, Vec<O>, I> for Repeated<'a, I, O>
where
I: ParserInput + Clone + 'a,
{
fn parse(&self, input: I) -> ParseResult<I, Vec<O>, I> {
let at_least = self.at_least.unwrap_or(0);
let at_most = self.at_most.unwrap_or(u16::MAX);
if at_most == 0 {
return Ok((vec![], input));
}
let mut results = Vec::new();
let mut count: u16 = 0;
let mut further_input = input.clone();
while let Ok((item, rest)) = self.inner_parser.parse(further_input.clone()) {
results.push(item);
further_input = rest;
count += 1;
if count >= at_most {
break;
}
}
if count < at_least {
return Err(input);
}
Ok((results, further_input))
}
fn representation(&self) -> Representation {
Representation::repeated(
self.inner_parser.representation(),
self.at_least.unwrap_or(0),
self.at_most.unwrap_or(u16::MAX),
)
}
}

View File

@ -0,0 +1,84 @@
use crate::combinators::repeated::Repeated;
use crate::parser::{BoxedParser, ParseResult, Parser, ParserInput, Representation};
pub struct SeparatedBy<'a, I, O>
where
I: ParserInput + Clone,
{
pub(super) inner_repeated: Repeated<'a, I, O>,
pub(super) delimiter: BoxedParser<'a, I, (), I>,
pub(super) allow_trailing: bool,
}
impl<'a, I, O> Parser<I, Vec<O>, I> for SeparatedBy<'a, I, O>
where
I: ParserInput + Clone + 'a,
{
fn representation(&self) -> Representation {
Representation::new("sepby")
}
fn parse(&self, input: I) -> ParseResult<I, Vec<O>, I> {
let at_least = self.inner_repeated.at_least.unwrap_or(0);
let at_most = self.inner_repeated.at_most.unwrap_or(u16::MAX);
let parser = &self.inner_repeated.inner_parser;
let delimiter = &self.delimiter;
if at_most == 0 {
return Ok((vec![], input));
}
let mut results = Vec::new();
let mut count: u16 = 0;
let mut further_input;
match parser.parse(input.clone()) {
Ok((item, rest)) => {
results.push(item);
further_input = rest;
}
Err(_e) => {
if at_least > 0 {
return Err(input);
} else {
return Ok((vec![], input));
}
}
}
loop {
match delimiter.parse(further_input.clone()) {
Ok(((), rest)) => {
further_input = rest;
}
Err(_e) => {
break;
}
}
match parser.parse(further_input.clone()) {
Ok((item, rest)) => {
results.push(item);
further_input = rest;
count += 1;
}
Err(_e) if self.allow_trailing => {
break;
}
Err(e) => {
return Err(e);
}
}
if count >= at_most {
break;
}
}
if count < at_least {
return Err(input);
}
Ok((results, further_input))
}
}

Some files were not shown because too many files have changed in this diff Show More