rudus/src/compiler.rs

use crate::parser::Ast;
use crate::spans::Spanned;
use crate::value::*;
use chumsky::prelude::SimpleSpan;
use num_derive::{FromPrimitive, ToPrimitive};
use num_traits::FromPrimitive;

#[derive(Copy, Clone, Debug, PartialEq, Eq, FromPrimitive, ToPrimitive)]
pub enum Op {
    Nil,
    True,
    False,
    Constant,
    Jump,
    JumpIfFalse,
    Pop,
    PushBinding,
    Store,
    Load,
    ResetMatch,
    MatchNil,
    MatchTrue,
    MatchFalse,
    MatchWord,
    PanicIfNoMatch,
    MatchConstant,
    MatchTuple,
    PushTuple,
    PushList,
    PushDict,
    PushBox,
    GetKey,
    PanicNoWhen,
}

impl std::fmt::Display for Op {
    fn fmt(&self, f: &mut std::fmt::Formatter) -> std::fmt::Result {
        use Op::*;
        let rep = match self {
            Nil => "nil",
            True => "true",
            False => "false",
            Constant => "constant",
            Jump => "jump",
            JumpIfFalse => "jump_if_false",
            Pop => "pop",
            PushBinding => "push_binding",
            Store => "store",
            Load => "load",
            MatchNil => "match_nil",
            MatchTrue => "match_true",
            MatchFalse => "match_false",
            MatchWord => "match_word",
            ResetMatch => "reset_match",
            PanicIfNoMatch => "panic_if_no_match",
            MatchConstant => "match_constant",
            MatchTuple => "match_tuple",
            PushTuple => "push_tuple",
            PushList => "push_list",
            PushDict => "push_dict",
            PushBox => "push_box",
            GetKey => "get_key",
            PanicNoWhen => "panic_no_when",
        };
        write!(f, "{rep}")
    }
}

#[derive(Clone, Debug, PartialEq)]
pub struct Binding {
    name: &'static str,
    depth: isize,
}

#[derive(Clone, Debug, PartialEq)]
pub struct Chunk<'a> {
    pub bindings: Vec<Binding>,
    scope_depth: isize,
    num_bindings: usize,
    pub constants: Vec<Value>,
    pub bytecode: Vec<u8>,
    pub spans: Vec<SimpleSpan>,
    pub strings: Vec<&'static str>,
    pub keywords: Vec<&'static str>,
    pub nodes: Vec<&'a Ast>,
    pub ast: &'a Ast,
    pub span: SimpleSpan,
    pub src: &'static str,
    pub name: &'static str,
}

fn is_binding(expr: &Spanned<Ast>) -> bool {
    let (ast, _) = expr;
    use Ast::*;
    match ast {
        Let(..) | LBox(..) => true,
        Fn(name, ..) => *name != "*anon",
        _ => false,
    }
}

impl<'a> Chunk<'a> {
    pub fn new(ast: &'a Spanned<Ast>, name: &'static str, src: &'static str) -> Chunk<'a> {
        Chunk {
            bindings: vec![],
            scope_depth: -1,
            num_bindings: 0,
            constants: vec![],
            bytecode: vec![],
            spans: vec![],
            strings: vec![],
            keywords: vec![
                "nil", "bool", "number", "keyword", "string", "tuple", "list", "dict", "box", "fn",
            ],
            nodes: vec![],
            ast: &ast.0,
            span: ast.1,
            src,
            name,
        }
    }

    pub fn kw_from(&self, kw: &str) -> Option<Value> {
        self.kw_index_from(kw).map(Value::Keyword)
    }

    pub fn kw_index_from(&self, kw: &str) -> Option<usize> {
        self.keywords.iter().position(|s| *s == kw)
    }

    pub fn visit(&mut self, node: &'a Spanned<Ast>) {
        let root_node = self.ast;
        let root_span = self.span;
        let (ast, span) = node;
        self.ast = ast;
        self.span = *span;
        self.compile();
        self.ast = root_node;
        self.span = root_span;
    }

    fn emit_constant(&mut self, val: Value) {
        let constant_index = self.constants.len();
        if constant_index > u8::MAX as usize {
            panic!(
                "internal Ludus compiler error: too many constants in chunk:{}:: {}",
                self.span, self.ast
            )
        }
        self.constants.push(val);
        self.bytecode.push(Op::Constant as u8);
        self.spans.push(self.span);
        self.bytecode.push(constant_index as u8);
        self.spans.push(self.span);
    }

    fn match_constant(&mut self, val: Value) {
        let constant_index = match self.constants.iter().position(|v| *v == val) {
            Some(idx) => idx,
            None => self.constants.len(),
        };
        if constant_index > u8::MAX as usize {
            panic!(
                "internal Ludus compiler error: too many constants in chunk:{}:: {}",
                self.span, self.ast
            )
        }
        if constant_index == self.constants.len() {
            self.constants.push(val);
        }
        self.bytecode.push(Op::MatchConstant as u8);
        self.spans.push(self.span);
        self.bytecode.push(constant_index as u8);
        self.spans.push(self.span);
        self.bind("*constant");
    }

    fn emit_op(&mut self, op: Op) {
        self.bytecode.push(op as u8);
        self.spans.push(self.span);
    }

    fn bind(&mut self, name: &'static str) {
        self.bindings.push(Binding {
            name,
            depth: self.scope_depth,
        });
    }

    pub fn compile(&mut self) {
        use Ast::*;
        match self.ast {
            Nil => self.emit_op(Op::Nil),
            Number(n) => self.emit_constant(Value::Number(*n)),
            Boolean(b) => self.emit_op(if *b { Op::True } else { Op::False }),
            String(s) => {
                let existing_str = self.strings.iter().position(|e| e == s);
                let str_index = match existing_str {
                    Some(idx) => idx,
                    None => self.strings.len(),
                };
                self.strings.push(s);
                self.emit_constant(Value::Interned(str_index));
            }
            Keyword(s) => {
                let existing_kw = self.keywords.iter().position(|kw| kw == s);
                let kw_index = match existing_kw {
                    Some(index) => index,
                    None => self.keywords.len(),
                };
                if kw_index == self.keywords.len() {
                    self.keywords.push(s);
                }
                self.emit_constant(Value::Keyword(kw_index));
            }
            Block(lines) => {
                self.scope_depth += 1;
                for expr in lines.iter().take(lines.len() - 1) {
                    if is_binding(expr) {
                        self.visit(expr)
                    } else {
                        self.visit(expr);
                        self.emit_op(Op::Pop);
                    }
                }
                self.visit(lines.last().unwrap());
                self.emit_op(Op::Store);
                self.scope_depth -= 1;
                while let Some(binding) = self.bindings.last() {
                    if binding.depth > self.scope_depth {
                        self.emit_op(Op::Pop);
                        self.bindings.pop();
                    } else {
                        break;
                    }
                }
                self.emit_op(Op::Load);
            }
            If(cond, then, r#else) => {
                self.visit(cond);
                let jif_idx = self.bytecode.len();
                self.emit_op(Op::JumpIfFalse);
                self.bytecode.push(0xff);
                self.visit(then);
                let jump_idx = self.bytecode.len();
                self.emit_op(Op::Jump);
                self.bytecode.push(0xff);
                self.visit(r#else);
                let end_idx = self.bytecode.len();
                let jif_offset = jump_idx - jif_idx;
                let jump_offset = end_idx - jump_idx;
                self.bytecode[jif_idx + 1] = jif_offset as u8;
                self.bytecode[jump_idx + 1] = jump_offset as u8;
            }
            Let(patt, expr) => {
                self.emit_op(Op::ResetMatch);
                self.visit(expr);
                self.visit(patt);
                self.emit_op(Op::PanicIfNoMatch);
            }
            WordPattern(name) => {
                self.emit_op(Op::MatchWord);
                self.bind(name);
            }
            Word(name) => {
                self.emit_op(Op::PushBinding);
                let biter = self.bindings.iter().enumerate().rev();
                for (i, binding) in biter {
                    if binding.name == *name {
                        self.bytecode.push(i as u8);
                        break;
                    }
                }
            }
            PlaceholderPattern => {
                self.emit_op(Op::MatchWord);
                self.bind("_");
            }
            NilPattern => {
                self.emit_op(Op::MatchNil);
                self.bind("nil");
            }
            BooleanPattern(b) => {
                if *b {
                    self.emit_op(Op::MatchTrue);
                    self.bind("true");
                } else {
                    self.emit_op(Op::MatchFalse);
                    self.bind("false");
                }
            }
            NumberPattern(n) => {
                self.match_constant(Value::Number(*n));
            }
            KeywordPattern(s) => {
                let existing_kw = self.keywords.iter().position(|kw| kw == s);
                let kw_index = match existing_kw {
                    Some(index) => index,
                    None => self.keywords.len(),
                };
                if kw_index == self.keywords.len() {
                    self.keywords.push(s);
                }
                self.match_constant(Value::Keyword(kw_index));
            }
            StringPattern(s) => {
                let existing_str = self.strings.iter().position(|e| e == s);
                let str_index = match existing_str {
                    Some(idx) => idx,
                    None => self.strings.len(),
                };
                if str_index == self.strings.len() {
                    self.strings.push(s)
                }
                self.match_constant(Value::Interned(str_index));
            }
            Tuple(members) => {
                for member in members {
                    self.visit(member);
                }
                self.emit_op(Op::PushTuple);
                self.bytecode.push(members.len() as u8);
            }
            List(members) => {
                for member in members {
                    self.visit(member);
                }
                self.emit_op(Op::PushList);
                self.bytecode.push(members.len() as u8);
            }
            LBox(name, expr) => {
                self.visit(expr);
                self.emit_op(Op::PushBox);
                self.bind(name);
            }
            Dict(pairs) => {
                for pair in pairs {
                    self.visit(pair);
                }
                self.emit_op(Op::PushDict);
                self.bytecode.push(pairs.len() as u8);
            }
            Pair(key, value) => {
                let existing_kw = self.keywords.iter().position(|kw| kw == key);
                let kw_index = match existing_kw {
                    Some(index) => index,
                    None => self.keywords.len(),
                };
                if kw_index == self.keywords.len() {
                    self.keywords.push(key);
                }
                self.emit_constant(Value::Keyword(kw_index));
                self.visit(value);
            }
            Synthetic(first, second, rest) => {
                match (&first.0, &second.0) {
                    (Word(_), Keyword(_)) => {
                        self.visit(first);
                        self.visit(second);
                        self.emit_op(Op::GetKey);
                    }
                    (Keyword(_), Arguments(args)) => {
                        self.visit(&args[0]);
                        self.visit(first);
                        self.emit_op(Op::GetKey);
                    }
                    (Word(_), Arguments(_)) => {
                        todo!()
                    }
                    _ => unreachable!(),
                }
                for term in rest {
                    todo!()
                }
            }
            When(clauses) => {
                let mut jump_idxes = vec![];
                let mut clauses = clauses.iter();
                while let Some((WhenClause(cond, body), _)) = clauses.next() {
                    self.visit(cond.as_ref());
                    self.emit_op(Op::JumpIfFalse);
                    let jif_jump_idx = self.bytecode.len();
                    self.bytecode.push(0xff);
                    self.visit(body);
                    self.emit_op(Op::Jump);
                    jump_idxes.push(self.bytecode.len());
                    self.bytecode.push(0xff);
                    self.bytecode[jif_jump_idx] =
                        self.bytecode.len() as u8 - jif_jump_idx as u8 - 1;
                }
                self.emit_op(Op::PanicNoWhen);
                for idx in jump_idxes {
                    self.bytecode[idx] = self.bytecode.len() as u8 - idx as u8 + 1;
                }
            }
            _ => todo!(),
        }
    }

    pub fn disassemble(&self) {
        println!("=== chunk: {} ===", self.name);
        println!("IDX | CODE           | INFO");
        let mut codes = self.bytecode.iter().enumerate();
        while let Some((i, byte)) = codes.next() {
            let op = Op::from_u8(*byte).unwrap();
            use Op::*;
            match op {
                Pop | Store | Load | Nil | True | False | MatchNil | MatchTrue | MatchFalse
                | MatchWord | ResetMatch | PanicIfNoMatch | GetKey | PanicNoWhen => {
                    println!("{i:04}: {op}")
                }
                Constant | MatchConstant => {
                    let (_, next) = codes.next().unwrap();
                    let value = &self.constants[*next as usize].show(self);
                    println!("{i:04}: {:16} {next:04}: {value}", op.to_string());
                }
                PushBinding | MatchTuple | PushTuple | PushDict | PushList | PushBox => {
                    let (_, next) = codes.next().unwrap();
                    println!("{i:04}: {:16} {next:04}", op.to_string());
                }
                Jump | JumpIfFalse => {
                    let (_, next) = codes.next().unwrap();
                    println!("{i:04}: {:16} {next:04}", op.to_string())
                }
            }
        }
    }

    pub fn dissasemble_instr(&self, i: usize) {
        let op = Op::from_u8(self.bytecode[i]).unwrap();
        use Op::*;
        match op {
            Pop | Store | Load | Nil | True | False | MatchNil | MatchTrue | MatchFalse
            | PanicIfNoMatch | MatchWord | ResetMatch | GetKey | PanicNoWhen => {
                println!("{i:04}: {op}")
            }
            Constant | MatchConstant => {
                let next = self.bytecode[i + 1];
                let value = &self.constants[next as usize].show(self);
                println!("{i:04}: {:16} {next:04}: {value}", op.to_string());
            }
            PushBinding | MatchTuple | PushTuple | PushDict | PushList | PushBox => {
                let next = self.bytecode[i + 1];
                println!("{i:04}: {:16} {next:04}", op.to_string());
            }
            Jump | JumpIfFalse => {
                let next = self.bytecode[i + 1];
                println!("{i:04}: {:16} {next:04}", op.to_string())
            }
        }
    }
}