schala/schala-lang/language/src/reduced_ast.rs

//! # Reduced AST
//! The reduced AST is a minimal AST designed to be built from the full AST after all possible
//! static checks have been done. Consequently, the AST reduction phase does very little error
//! checking itself - any errors should ideally be caught either by an earlier phase, or are
//! runtime errors that the evaluator should handle. That said, becuase it does do table lookups
//! that can in principle fail [especially at the moment with most static analysis not yet complete],
//! there is an Expr variant `ReductionError` to handle these cases.
//!
//! A design decision to make - should the ReducedAST types contain all information about
//! type/layout necessary for the evaluator to work? If so, then the evaluator should not
//! have access to the symbol table at all and ReducedAST should carry that information. If not,
//! then ReducedAST shouldn't be duplicating information that can be queried at runtime from the
//! symbol table. But I think the former might make sense since ultimately the bytecode will be
//! built from the ReducedAST.
use std::rc::Rc;
use std::str::FromStr;

use crate::ast::*;
use crate::symbol_table::{Symbol, SymbolSpec, SymbolTable};
use crate::builtin::Builtin;

#[derive(Debug)]
pub struct ReducedAST(pub Vec<Stmt>);

#[derive(Debug, Clone)]
pub enum Stmt {
  PreBinding {
    name: Rc<String>,
    func: Func,
  },
  Binding {
    name: Rc<String>,
    constant: bool,
    expr: Expr,
  },
  Expr(Expr),
  Noop,
}

#[derive(Debug, Clone)]
pub enum Expr {
  Unit,
  Lit(Lit),
  Tuple(Vec<Expr>),
  Func(Func),
  Sym(Rc<String>),
  Constructor {
    type_name: Rc<String>,
    name: Rc<String>,
    tag: usize,
    arity: usize, // n.b. arity here is always the value from the symbol table - if it doesn't match what it's being called with, that's an eval error, eval will handle it
  },
  Call {
    f: Box<Expr>,
    args: Vec<Expr>,
  },
  Assign {
    val: Box<Expr>,
    expr: Box<Expr>,
  },
  Conditional {
    cond: Box<Expr>,
    then_clause: Vec<Stmt>,
    else_clause: Vec<Stmt>,
  },
  ConditionalTargetSigilValue,
  CaseMatch {
    cond: Box<Expr>,
    alternatives: Vec<Alternative>
  },
  UnimplementedSigilValue,
  ReductionError(String),
}

pub type BoundVars = Vec<Option<Rc<String>>>; //remember that order matters here

#[derive(Debug, Clone)]
pub struct Alternative {
  pub matchable: Subpattern,
  pub item: Vec<Stmt>,
}

#[derive(Debug, Clone)]
pub struct Subpattern {
  pub tag: Option<usize>,
  pub subpatterns: Vec<Option<Subpattern>>,
  pub bound_vars: BoundVars,
  pub guard: Option<Expr>,
}

#[derive(Debug, Clone)]
pub enum Lit {
  Nat(u64),
  Int(i64),
  Float(f64),
  Bool(bool),
  StringLit(Rc<String>),
}

#[derive(Debug, Clone)]
pub enum Func {
  BuiltIn(Builtin),
  UserDefined {
    name: Option<Rc<String>>,
    params: Vec<Rc<String>>,
    body: Vec<Stmt>,
  }
}

impl AST {
  pub fn reduce(&self, symbol_table: &SymbolTable) -> ReducedAST {
    let mut output = vec![];
    for statement in self.0.iter() {
      output.push(statement.node().reduce(symbol_table));
    }
    ReducedAST(output)
  }
}

impl Statement {
  fn reduce(&self, symbol_table: &SymbolTable) -> Stmt { 
    use crate::ast::Statement::*;
    match self {
      ExpressionStatement(expr) => Stmt::Expr(expr.node().reduce(symbol_table)),
      Declaration(decl) => decl.reduce(symbol_table),
    }
  }
}

fn reduce_block(block: &Block, symbol_table: &SymbolTable) -> Vec<Stmt> {
  block.iter().map(|stmt| stmt.node().reduce(symbol_table)).collect()
}

impl InvocationArgument {
  fn reduce(&self, symbol_table: &SymbolTable) -> Expr {
    use crate::ast::InvocationArgument::*;
    match self {
      Positional(ex) => ex.reduce(symbol_table),
      Keyword { .. } => Expr::UnimplementedSigilValue,
      Ignored => Expr::UnimplementedSigilValue,
    }
  }
}

impl Expression {
  fn reduce(&self, symbol_table: &SymbolTable) -> Expr {
    use crate::ast::ExpressionKind::*;
    let ref input = self.kind;
    match input {
      NatLiteral(n) => Expr::Lit(Lit::Nat(*n)),
      FloatLiteral(f) => Expr::Lit(Lit::Float(*f)),
      StringLiteral(s) => Expr::Lit(Lit::StringLit(s.clone())),
      BoolLiteral(b) => Expr::Lit(Lit::Bool(*b)),
      BinExp(binop, lhs, rhs) => binop.reduce(symbol_table, lhs, rhs),
      PrefixExp(op, arg) => op.reduce(symbol_table, arg),
      Value(name) => match symbol_table.lookup_by_name(name) {
        Some(Symbol { spec: SymbolSpec::DataConstructor { index, type_args, type_name}, .. }) => Expr::Constructor {
          type_name: type_name.clone(),
          name: name.clone(),
          tag: index.clone(),
          arity: type_args.len(),
        },
        _ => Expr::Sym(name.clone()),
      },
      Call { f, arguments } =>  reduce_call_expression(f, arguments, symbol_table),
      TupleLiteral(exprs) => Expr::Tuple(exprs.iter().map(|e| e.node().reduce(symbol_table)).collect()),
      IfExpression { discriminator, body } => reduce_if_expression(discriminator, body, symbol_table),
      Lambda { params, body, .. } => reduce_lambda(params, body, symbol_table),
      NamedStruct { name, fields } => reduce_named_struct(name, fields, symbol_table),
      Index { .. } => Expr::UnimplementedSigilValue,
      WhileExpression { .. } => Expr::UnimplementedSigilValue,
      ForExpression { .. } => Expr::UnimplementedSigilValue,
      ListLiteral { .. } => Expr::UnimplementedSigilValue,
    }
  }
}

fn reduce_lambda(params: &Vec<FormalParam>, body: &Block, symbol_table: &SymbolTable) -> Expr {
  Expr::Func(Func::UserDefined {
    name: None,
    params: params.iter().map(|param| param.name.clone()).collect(),
    body: reduce_block(body, symbol_table),
  })
}

fn reduce_named_struct(name: &Rc<String>, fields: &Vec<(Rc<String>, Meta<Expression>)>, symbol_table: &SymbolTable) -> Expr {
  let (type_name, index, members_from_table) = match symbol_table.lookup_by_name(name) {
    Some(Symbol { spec: SymbolSpec::RecordConstructor { members, type_name, index },  .. }) => (type_name.clone(), index, members),
    _ => return Expr::ReductionError("Not a record constructor".to_string()),
  };
  let arity = members_from_table.len();

  let mut args: Vec<(Rc<String>, Expr)> = fields.iter()
    .map(|(name, expr)| (name.clone(), expr.node().reduce(symbol_table)))
    .collect();

  args.as_mut_slice()
    .sort_unstable_by(|(name1, _), (name2, _)| name1.cmp(name2)); //arbitrary - sorting by alphabetical order

  let args = args.into_iter().map(|(_, expr)| expr).collect();

  //TODO make sure this sorting actually works
  let f = box Expr::Constructor { type_name, name: name.clone(), tag: *index, arity, };
  Expr::Call { f, args }
}

fn reduce_call_expression(func: &Meta<Expression>, arguments: &Vec<Meta<InvocationArgument>>, symbol_table: &SymbolTable) -> Expr {
  Expr::Call {
    f: Box::new(func.node().reduce(symbol_table)),
    args: arguments.iter().map(|arg| arg.node().reduce(symbol_table)).collect(),
  }
}

fn reduce_if_expression(discriminator: &Discriminator, body: &IfExpressionBody, symbol_table: &SymbolTable) -> Expr {
  let cond = Box::new(match *discriminator {
    Discriminator::Simple(ref expr) => expr.reduce(symbol_table),
    Discriminator::BinOp(ref _expr, ref _binop) => panic!("Can't yet handle binop discriminators")
  });
  match *body {
    IfExpressionBody::SimpleConditional(ref then_clause, ref else_clause) => {
      let then_clause = reduce_block(then_clause, symbol_table);
      let else_clause = match else_clause {
        None => vec![],
        Some(stmts) => reduce_block(stmts, symbol_table),
      };
      Expr::Conditional { cond, then_clause, else_clause }
    },
    IfExpressionBody::SimplePatternMatch(ref pat, ref then_clause, ref else_clause) => {
      let then_clause = reduce_block(then_clause, symbol_table);
      let else_clause = match else_clause {
        None => vec![],
        Some(stmts) => reduce_block(stmts, symbol_table),
      };

      let alternatives = vec![
        pat.to_alternative(then_clause, symbol_table),
        Alternative {
          matchable: Subpattern {
            tag: None,
            subpatterns: vec![],
            bound_vars: vec![],
            guard: None,
          },
          item: else_clause
        },
      ];

      Expr::CaseMatch {
        cond,
        alternatives,
      }
    },
    IfExpressionBody::GuardList(ref guard_arms) => {
      let mut alternatives = vec![];
      for arm in guard_arms {
        match arm.guard {
          Guard::Pat(ref p) =>  {
            let item = reduce_block(&arm.body, symbol_table);
            let alt = p.to_alternative(item, symbol_table);
            alternatives.push(alt);
          },
          Guard::HalfExpr(HalfExpr { op: _, expr: _ }) => {
            return Expr::UnimplementedSigilValue
          }
        }
      }
      Expr::CaseMatch { cond, alternatives }
    }
  }
}
/*                     ig var   pat
 * x is SomeBigOldEnum(_, x, Some(t))
 */

fn handle_symbol(symbol: Option<&Symbol>, inner_patterns: &Vec<Pattern>, symbol_table: &SymbolTable) -> Subpattern {
  use self::Pattern::*;
  let tag = symbol.map(|symbol| match symbol.spec {
    SymbolSpec::DataConstructor { index, .. } => index.clone(),
    _ => panic!("Symbol is not a data constructor - this should've been caught in type-checking"),
  });
  let bound_vars = inner_patterns.iter().map(|p| match p {
    Literal(PatternLiteral::VarPattern(var)) => Some(var.clone()),
    _ => None,
  }).collect();

  let subpatterns = inner_patterns.iter().map(|p| match p {
    Ignored => None,
    Literal(PatternLiteral::VarPattern(_)) => None,
    Literal(other) => Some(other.to_subpattern(symbol_table)),
    tp @ TuplePattern(_) => Some(tp.to_subpattern(symbol_table)),
    ts @ TupleStruct(_, _) => Some(ts.to_subpattern(symbol_table)),
    Record(..) => unimplemented!(),
  }).collect();

  let guard = None;
  /*
     let guard_equality_exprs: Vec<Expr> = subpatterns.iter().map(|p| match p {
     Literal(lit) => match lit {
     _ => unimplemented!()
     },
     _ => unimplemented!()
     }).collect();
     */

  Subpattern {
    tag,
    subpatterns,
    guard,
    bound_vars,
  }
}

impl Pattern {
  fn to_alternative(&self, item: Vec<Stmt>, symbol_table: &SymbolTable) -> Alternative {
    let s = self.to_subpattern(symbol_table);
    Alternative {
      matchable: Subpattern {
        tag: s.tag,
        subpatterns: s.subpatterns,
        bound_vars: s.bound_vars,
        guard: s.guard,
      },
      item
    }
  }

  fn to_subpattern(&self, symbol_table: &SymbolTable) -> Subpattern {
    use self::Pattern::*;
    match self {
      TupleStruct(name, inner_patterns) => {
        let symbol = symbol_table.lookup_by_name(name).expect(&format!("Symbol {} not found", name));
        handle_symbol(Some(symbol), inner_patterns, symbol_table)
      },
      TuplePattern(inner_patterns) => handle_symbol(None, inner_patterns, symbol_table),
      Record(_name, _pairs) => {
        unimplemented!()
      },
      Ignored => Subpattern { tag: None, subpatterns: vec![], guard: None, bound_vars: vec![] },
      Literal(lit) => lit.to_subpattern(symbol_table),
    }
  }
}

impl PatternLiteral {
  fn to_subpattern(&self, symbol_table: &SymbolTable) -> Subpattern {
    use self::PatternLiteral::*;
    match self {
      NumPattern { neg, num } => {
        let comparison = Expr::Lit(match (neg, num) {
          (false, ExpressionKind::NatLiteral(n)) => Lit::Nat(*n),
          (false, ExpressionKind::FloatLiteral(f)) => Lit::Float(*f),
          (true, ExpressionKind::NatLiteral(n)) => Lit::Int(-1*(*n as i64)),
          (true, ExpressionKind::FloatLiteral(f)) => Lit::Float(-1.0*f),
          _ => panic!("This should never happen")
        });
        let guard = Some(Expr::Call {
          f: Box::new(Expr::Func(Func::BuiltIn(Builtin::Equality))),
          args: vec![comparison, Expr::ConditionalTargetSigilValue],
        });
        Subpattern {
          tag: None,
          subpatterns: vec![],
          guard,
          bound_vars: vec![],
        }
      },
      StringPattern(s) => {
        let guard = Some(Expr::Call {
          f: Box::new(Expr::Func(Func::BuiltIn(Builtin::Equality))),
          args: vec![Expr::Lit(Lit::StringLit(s.clone())), Expr::ConditionalTargetSigilValue]
        });

        Subpattern {
          tag: None,
          subpatterns: vec![],
          guard,
          bound_vars: vec![],
        }
      },
      BoolPattern(b) =>  {
        let guard = Some(if *b {
          Expr::ConditionalTargetSigilValue
        } else {
          Expr::Call {
            f: Box::new(Expr::Func(Func::BuiltIn(Builtin::BooleanNot))),
            args: vec![Expr::ConditionalTargetSigilValue]
          }
        });
        Subpattern {
          tag: None,
          subpatterns: vec![],
          guard,
          bound_vars: vec![],
        }
      },
      VarPattern(var) => match symbol_table.lookup_by_name(var) {
        Some(symbol) => handle_symbol(Some(symbol), &vec![], symbol_table),
        None => Subpattern {
          tag: None,
          subpatterns: vec![],
          guard: None,
          bound_vars: vec![Some(var.clone())],
        }
      }
    }
  }
}

impl Declaration {
  fn reduce(&self, symbol_table: &SymbolTable) -> Stmt {
    use self::Declaration::*;
    match self {
      Binding {name, constant, expr, .. } => Stmt::Binding { name: name.clone(), constant: *constant, expr: expr.node().reduce(symbol_table) },
      FuncDecl(Signature { name, params, .. }, statements) => Stmt::PreBinding {
        name: name.clone(),
        func: Func::UserDefined {
          name: Some(name.clone()),
          params: params.iter().map(|param| param.name.clone()).collect(),
          body: reduce_block(&statements, symbol_table),
        }
      },
      TypeDecl { .. } => Stmt::Noop,
      TypeAlias(_, _) => Stmt::Noop,
      Interface { .. } => Stmt::Noop,
      Impl { .. } => Stmt::Expr(Expr::UnimplementedSigilValue),
      _ => Stmt::Expr(Expr::UnimplementedSigilValue)
    }
  }
}

impl BinOp {
  fn reduce(&self, symbol_table: &SymbolTable, lhs: &Box<Meta<Expression>>, rhs: &Box<Meta<Expression>>) -> Expr {
    let operation = Builtin::from_str(self.sigil()).ok();
    match operation {
      Some(Builtin::Assignment) => Expr::Assign {
        val: Box::new(lhs.node().reduce(symbol_table)),
        expr: Box::new(rhs.node().reduce(symbol_table)),
      },
      Some(op) => {
        let f = Box::new(Expr::Func(Func::BuiltIn(op)));
        Expr::Call { f, args: vec![lhs.node().reduce(symbol_table), rhs.node().reduce(symbol_table)]}
      },
      None => {
        //TODO handle a user-defined operation
        Expr::UnimplementedSigilValue
      }
    }
  }
}

impl PrefixOp {
  fn reduce(&self, symbol_table: &SymbolTable, arg: &Box<Meta<Expression>>) -> Expr {
    match self.builtin {
      Some(op) => {
        let f = Box::new(Expr::Func(Func::BuiltIn(op)));
        Expr::Call { f, args: vec![arg.node().reduce(symbol_table)]}
      },
      None => { //TODO need this for custom prefix ops
        Expr::UnimplementedSigilValue
      }
    }
  }
}