schala/schala-lang/language/src/parsing/new.rs

use std::rc::Rc;

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() -> AST =
            __ statements:(statement() ** delimiter() ) __ { AST { id: Default::default(), 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() -> Block = "{" __ items:block_item()* __ "}" { items.into() } /
                                     "{" __ stmt:statement() __ "}" { vec![stmt].into() }

        rule block_item() -> Statement =
            stmt:statement() delimiter()+ { stmt }

        rule statement() -> Statement =
             _ pos:position!() kind:statement_kind() _ { Statement { id: Default::default(), location: pos.into(), kind } }

        rule statement_kind() -> StatementKind =
            __ import:import() { StatementKind::Import(import) } /
            __ decl:declaration() { StatementKind::Declaration(decl) } /
            __ flow:flow() { StatementKind::Flow(flow) } /
            __ expr:expression() { StatementKind::Expression(expr) }

        rule flow() -> FlowControl =
            "continue" { FlowControl::Continue } /
            "break" { FlowControl::Break } /
            "return" _ expr:expression()? { FlowControl::Return(expr) }

        rule import() -> ImportSpecifier =
            "import" _ path_components:path_components() suffix:import_suffix()? {
                ImportSpecifier {
                    id: Default::default(),
                    path_components,
                    imported_names: suffix.unwrap_or_else(|| 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(|n| rc_string(n)));
                items
            }

        rule path_component() -> &'input str = "::" ident:identifier() { ident }

        rule import_suffix() -> ImportedNames =
            "::*" { ImportedNames::All } /
            "::{" __ names:(identifier() ** (_ "," _)) __ "}" { ImportedNames::List(names.into_iter().map(rc_string).collect()) }


        rule declaration() -> Declaration =
            binding() / type_decl() / annotation() / func() / interface() / implementation() / module()

        rule module() -> Declaration =
            "module" _ name:identifier() _ items:block() { Declaration::Module { name: rc_string(name), items } }

        rule implementation() -> Declaration =
            "impl" _ interface:type_singleton_name() _ "for" _ type_name:type_identifier() _ block:decl_block() {
                Declaration::Impl { type_name, interface_name: Some(interface), block }

            } /
            "impl" _ type_name:type_identifier() _ block:decl_block() {
                Declaration::Impl { type_name, interface_name: None, block }
            }

        rule decl_block() -> Vec<Declaration> =
            "{" __ decls:(func_declaration() ** (delimiter()+)) __ "}" { decls }

        rule interface() -> Declaration =
            "interface" _ name:identifier() _ signatures:signature_block() { Declaration::Interface { name: rc_string(name), signatures } }

        rule signature_block() -> Vec<Signature> =
            "{" __  signatures:(func_signature() ** (delimiter()+)) __ "}" { signatures }

        rule func() -> Declaration =
            decl:func_declaration() { decl } /
            sig:func_signature() { Declaration::FuncSig(sig) }

        rule func_declaration() -> Declaration =
            _ sig:func_signature() __ body:block() { Declaration::FuncDecl(sig, body) }

        //TODO handle operators
        rule func_signature() -> Signature =
            _ "fn" _ name:identifier() "(" _ params:formal_params() _ ")" _ type_anno:type_anno()? { Signature {
                name: rc_string(name), operator: false, params, type_anno
            } }

        rule formal_params() -> Vec<FormalParam> = params:(formal_param() ** (_ "," _)) {? if params.len() < 256 { Ok(params) } else {
            Err("function-too-long") }
            }

        rule formal_param() -> FormalParam =
            name:identifier() _ anno:type_anno()? _ "=" expr:expression() { FormalParam { name: rc_string(name),
               default: Some(expr), anno } } /
            name:identifier() _ anno:type_anno()? { FormalParam { name: rc_string(name), default: None, anno } }


        rule annotation() -> Declaration =
            "@" name:identifier() args:annotation_args()? delimiter()+ _ inner:statement() { Declaration::Annotation {
                name: rc_string(name), arguments: if let Some(args) = args { args } else { vec![] }, inner: Box::new(inner) }
            }

        rule annotation_args() -> Vec<Expression> =
            "(" _ args:(expression() ** (_ "," _)) _ ")" { args }


        rule binding() -> Declaration =
            "let" _ mutable:"mut"? _ ident:identifier() _ type_anno:type_anno()? _ "=" _ expr:expression() {
                Declaration::Binding { name: Rc::new(ident.to_string()), constant: mutable.is_none(),
                type_anno, expr }
            }


        rule type_decl() -> Declaration =
            "type" _ "alias" _ alias:type_alias() { alias } /
            "type" _ mutable:"mut"? _ name:type_singleton_name() _ "=" _ body:type_body() {
                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() -> TypeBody =
            "{" _ items:(record_variant_item() ++ (_ "," _)) _ "}" { TypeBody::ImmediateRecord(Default::default(), items) } /
            variants:(variant_spec() ** (_ "|" _)) { TypeBody::Variants(variants) }

        rule variant_spec() -> Variant =
            name:identifier() _ "{" _ typed_identifier_list:(record_variant_item() ++ (_ "," _)) _ "}" { Variant {
                id: Default::default(), name: rc_string(name), kind: VariantKind::Record(typed_identifier_list)
            } } /
            name:identifier() "(" tuple_members:(type_identifier() ++ (_ "," _)) ")" { Variant {
                id: Default::default(), name: rc_string(name), kind: VariantKind::TupleStruct(tuple_members) } } /
            name:identifier() { Variant { id: Default::default(), 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() -> Expression =
            __ kind:expression_kind() _ type_anno:type_anno()? { Expression { id: Default::default(), type_anno, kind } }

        rule expression_no_struct() -> Expression =
            __ kind:expression_kind_no_struct() { Expression { id: Default::default(), type_anno: None, kind: kind } }

        rule expression_kind() -> ExpressionKind =
            precedence_expr(true)

        rule expression_kind_no_struct() -> ExpressionKind =
            precedence_expr(false)

        rule precedence_expr(struct_ok: bool) -> ExpressionKind =
        first:prefix_expr(struct_ok) _ next:(precedence_continuation(struct_ok))* {
            let next = next.into_iter().map(|(sigil, expr)| (BinOp::from_sigil(sigil), expr)).collect();
            BinopSequence { first, next }.do_precedence()
        }

        rule precedence_continuation(struct_ok: bool) -> (&'input str, ExpressionKind) =
            op:operator() _ expr:prefix_expr(struct_ok) _ { (op, expr) }

        rule prefix_expr(struct_ok: bool) -> ExpressionKind =
            prefix:prefix()? expr:extended_expr(struct_ok) {
                if let Some(p) = prefix {
                    let expr = Expression::new(Default::default(), 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) -> ExpressionKind =
            primary:primary(struct_ok) parts:(extended_expr_part()*) {
                let mut expression = Expression::new(Default::default(), 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(Default::default(), kind);
                }

                expression.kind
            }

        rule extended_expr_part() -> ExtendedPart<'input> =
            indexers:index_part() { ExtendedPart::Index(indexers) } /
            arguments:call_part() { ExtendedPart::Call(arguments) } /
            "." name:identifier() { ExtendedPart::Accessor(name) }

        rule index_part() -> Vec<Expression> =
            "[" indexers:(expression() ++ ",") "]" { indexers }

        rule call_part() -> Vec<InvocationArgument> =
            "(" arguments:(invocation_argument() ** ",") ")" { arguments }

        //TODO this shouldn't be an expression b/c type annotations disallowed here
        rule invocation_argument() -> InvocationArgument =
            _ "_" _ { InvocationArgument::Ignored } /
            _ ident:identifier() _ "=" _ expr:expression() { InvocationArgument::Keyword {
                name: Rc::new(ident.to_string()),
                expr
                } } /
            _ expr:expression() _ { InvocationArgument::Positional(expr) }


        rule primary(struct_ok: bool) -> ExpressionKind =
            while_expr() / for_expr() / float_literal() / nat_literal() / bool_literal() / string_literal() / paren_expr() /
            list_expr() / if_expr() / lambda_expr() /
            item:named_struct() {? if struct_ok { Ok(item) } else { Err("no-struct-allowed") } } /
            identifier_expr()

        rule lambda_expr() -> ExpressionKind =
            r#"\"# __ "(" _ params:formal_params() _ ")" _ type_anno:(type_anno()?) _ body:block()  {
                ExpressionKind::Lambda { params, type_anno, body }
            } /
            r#"\"# param:formal_param() _ type_anno:(type_anno()?) _ body:block() {
                ExpressionKind::Lambda { params: vec![param], type_anno, body }
            }

        rule for_expr() -> ExpressionKind =
            "for" _ enumerators:for_enumerators() _ body:for_body() {
                ExpressionKind::ForExpression { enumerators, body }
            }

        rule for_enumerators() -> Vec<Enumerator> =
            "{" _ enumerators:(enumerator() ++ ",") _ "}" { enumerators } /
            enumerator:enumerator() { vec![enumerator] }

        //TODO add guards, etc.
        rule enumerator() -> Enumerator =
            ident:identifier() _ "<-" _ generator:expression_no_struct() {
                Enumerator { id: Rc::new(ident.to_string()), generator }
            } /
            //TODO need to distinguish these two cases in AST
            ident:identifier() _ "=" _ generator:expression_no_struct() {
                Enumerator { id: Rc::new(ident.to_string()), generator }
            }

        rule for_body() -> Box<ForBody> =
            "return" _ expr:expression() { Box::new(ForBody::MonadicReturn(expr)) } /
            body:block() { Box::new(ForBody::StatementBlock(body)) }

        rule while_expr() -> ExpressionKind =
            "while" _ cond:expression_kind_no_struct()? _ body:block() {
                ExpressionKind::WhileExpression {
                    condition: cond.map(|kind| Box::new(Expression::new(Default::default(), kind))),
                    body,
                }
            }


        rule identifier_expr() -> ExpressionKind =
            qn:qualified_identifier() { ExpressionKind::Value(qn) }

        rule named_struct() -> ExpressionKind =
            name:qualified_identifier() _ fields:record_block() {
                ExpressionKind::NamedStruct {
                    name,
                    fields: fields.into_iter().map(|(n, exp)| (Rc::new(n.to_string()), exp)).collect(),
                }
            }


        //TODO anonymous structs, update syntax for structs
        rule record_block() -> Vec<(&'input str, Expression)> =
            "{" _ entries:(record_entry() ** ",") _ "}" { entries }

        rule record_entry() -> (&'input str, Expression) =
            _ name:identifier() _ ":" _ expr:expression() _ { (name, expr) }

        rule qualified_identifier() -> QualifiedName =
            names:(identifier() ++ "::") { QualifiedName { id: Default::default(), components: names.into_iter().map(|name| Rc::new(name.to_string())).collect() } }

        //TODO improve the definition of identifiers
        rule identifier() -> &'input str =
            !reserved() text:$(['a'..='z' | 'A'..='Z' | '_'] ['a'..='z' | 'A'..='Z' | '0'..='9' | '_']*) { text }

        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() -> ExpressionKind =
            "if" _ discriminator:(expression()?) _ body:if_expr_body() {
                ExpressionKind::IfExpression {
                    discriminator: discriminator.map(Box::new),
                    body: Box::new(body),
                }
            }

        rule if_expr_body() -> IfExpressionBody =
            cond_block() / simple_pattern_match() / simple_conditional()

        rule simple_conditional() -> IfExpressionBody =
            "then" _ then_case:expr_or_block() _ else_case:else_case() {
                IfExpressionBody::SimpleConditional { then_case, else_case }
            }

        rule simple_pattern_match() -> IfExpressionBody =
            "is" _ pattern:pattern() _ "then" _ then_case:expr_or_block() _ else_case:else_case() {
                IfExpressionBody::SimplePatternMatch { pattern, then_case, else_case }
            }

        rule cond_block() -> IfExpressionBody =
            "{" __ cond_arms:(cond_arm() ++ (delimiter()+)) __ "}" { IfExpressionBody::CondList(cond_arms) }

        rule cond_arm() -> ConditionArm =
            _ "else" _ body:expr_or_block() { ConditionArm { condition: Condition::Else, guard: None, body } } /
            _ condition:condition() _ guard:condition_guard() _ "then" _ body:expr_or_block()
                { ConditionArm { condition, guard, body } }

        rule condition() -> Condition =
            "is" _ pat:pattern() { Condition::Pattern(pat) } /
            op:operator() _ expr:expression() { Condition::TruncatedOp(BinOp::from_sigil(op), expr) }

        rule condition_guard() -> Option<Expression> =
            ("if" _ expr:expression() { expr } )?

        rule expr_or_block() -> Block = block() / pos:position!() ex:expression() {
            Statement {
                id: Default::default(), location: pos.into(),
                kind: StatementKind::Expression(ex)
            }.into()
        }

        rule else_case() -> Option<Block> =
            ("else" _ eorb:expr_or_block() { eorb })?

        rule pattern() -> Pattern =
            "(" _ variants:(pattern() ++ ",") _ ")" { Pattern::TuplePattern(variants) } /
            _ pat:simple_pattern() { pat }

        rule simple_pattern() -> Pattern =
            pattern_literal() /
            qn:qualified_identifier() "(" members:(pattern() ** ",") ")" {
                Pattern::TupleStruct(qn, members)
            } /
            qn:qualified_identifier() _ "{" _ items:(record_pattern_entry() ** ",") "}" _ {
                let items = items.into_iter().map(|(name, pat)| (Rc::new(name.to_string()), pat)).collect();
                Pattern::Record(qn, items)
            } /
            qn:qualified_identifier() { Pattern::VarOrName(qn) }

        rule record_pattern_entry() -> (&'input str, Pattern) =
            _ name:identifier() _ ":" _ pat:pattern() _ { (name, pat) } /
            _ name:identifier() _ {
                let qn = QualifiedName {
                    id: Default::default(),
                    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.to_string()))) } /
            sign:("-"?)  num:(float_literal() / nat_literal()) {
                let neg = sign.is_some();
                Pattern::Literal(PatternLiteral::NumPattern { neg, num })
            } /
            "_" { Pattern::Ignored }


        rule list_expr() -> ExpressionKind =
            "[" exprs:(expression() ** ",") "]" {
                let mut exprs = exprs;
                ExpressionKind::ListLiteral(exprs)
            }

        rule paren_expr() -> ExpressionKind =
            "(" exprs:(expression() ** ",") ")" {
                let mut exprs = exprs;
                match exprs.len() {
                    1 => exprs.pop().unwrap().kind,
                    _ => ExpressionKind::TupleLiteral(exprs),
                }
            }

        rule string_literal() -> ExpressionKind =
            s:bare_string_literal(){ ExpressionKind::StringLiteral(Rc::new(s.to_string())) }

        //TODO string escapes, prefixes
        rule bare_string_literal() -> &'input str =
            "\"" items:$([^ '"' ]*) "\"" { items }

        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() { ExpressionKind::NatLiteral(digits.parse().unwrap()) }

        rule bin_literal() -> ExpressionKind =
            "0b" digits:bin_digits() { ExpressionKind::NatLiteral(parse_binary(digits)) }

        rule hex_literal() -> ExpressionKind =
            "0x" digits:hex_digits() { ExpressionKind::NatLiteral(parse_hex(digits)) }

        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 /*, tok: Token*/) -> u64 {
    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 ParseError::new_with_token("This binary expression will overflow", tok),*/
                panic!(),
        }
    }
    //Ok(result)
    result
}

//TODO fix these two functions
fn parse_hex(digits: &str) -> u64 {
    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 => panic!(),
        }
        multiplier = match multiplier.checked_mul(16) {
            Some(m) => m,
            None => panic!(),
        }
    }
    result
}

#[derive(Debug)]
struct BinopSequence {
    first: ExpressionKind,
    next: Vec<(BinOp, ExpressionKind)>,
}

impl BinopSequence {
    fn do_precedence(self) -> ExpressionKind {
        fn helper(
            precedence: i32,
            lhs: ExpressionKind,
            rest: &mut Vec<(BinOp, ExpressionKind)>,
        ) -> Expression {
            let mut lhs = Expression::new(Default::default(), lhs);
            loop {
                let (next_op, next_rhs) = match rest.pop() {
                    Some((a, b)) => (a, b),
                    None => break,
                };
                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);
                lhs = Expression::new(
                    Default::default(),
                    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).kind
    }
}