schala/schala-lang/language/src/symbol_table/mod.rs

#![allow(clippy::enum_variant_names)]

use std::{
    collections::{hash_map::Entry, HashMap, HashSet},
    fmt,
    rc::Rc,
};

use crate::{
    ast,
    ast::{
        Declaration, ItemId, ModuleSpecifier, Statement, StatementKind, TypeBody, TypeSingletonName, Variant,
        VariantKind,
    },
    builtin::Builtin,
    tokenizing::Location,
    type_inference::{self, PendingType, TypeBuilder, TypeContext, TypeId, VariantBuilder},
};

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>;

/// Fully-qualified symbol name
#[derive(Debug, Clone, Eq, PartialEq, Hash, PartialOrd, Ord)]
pub struct Fqsn {
    //TODO Fqsn's need to be cheaply cloneable
    scopes: Vec<Scope>, //TODO rename to ScopeSegment
}

impl Fqsn {
    fn from_scope_stack(scopes: &[Scope], new_name: Rc<String>) -> Self {
        let mut v = Vec::new();
        for s in scopes {
            v.push(s.clone());
        }
        v.push(Scope::Name(new_name));
        Fqsn { scopes: v }
    }

    fn from_strs(strs: &[&str]) -> Fqsn {
        let mut scopes = vec![];
        for s in strs {
            scopes.push(Scope::Name(Rc::new(s.to_string())));
        }
        Fqsn { scopes }
    }

    fn local_name(&self) -> Rc<String> {
        let Scope::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)]
enum Scope {
    Name(Rc<String>),
}

impl fmt::Display for Scope {
    fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
        let Scope::Name(name) = self;
        write!(f, "{}", name)
    }
}

#[allow(dead_code)]
#[derive(Debug, Clone)]
pub enum SymbolError {
    DuplicateName { prev_name: Fqsn, location: Location },
    DuplicateVariant { type_fqsn: Fqsn, name: String },
    DuplicateRecord { type_name: Fqsn, location: Location, member: String },
}

#[allow(dead_code)]
#[derive(Debug)]
struct NameSpec<K> {
    location: Location,
    kind: K,
}

#[derive(Debug)]
enum NameKind {
    Module,
    Function,
    Binding,
}

#[derive(Debug)]
struct TypeKind;

/// 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>,

    /// A map of the Fqsn of an AST definition to a Symbol data structure, which contains
    /// some basic information about what that symbol is and (ideally) references to other tables
    /// (e.g. typechecking tables) with more information about that symbol.
    fqsn_to_symbol: HashMap<Fqsn, Rc<Symbol>>,

    id_to_symbol: HashMap<ItemId, Rc<Symbol>>,
    def_to_symbol: HashMap<DefId, Rc<Symbol>>,
}

impl SymbolTable {
    pub fn new() -> SymbolTable {
        let mut table = SymbolTable {
            def_id_store: IdStore::new(),
            symbol_trie: SymbolTrie::new(),
            fq_names: NameTable::new(),
            types: NameTable::new(),

            fqsn_to_symbol: HashMap::new(),
            id_to_symbol: HashMap::new(),
            def_to_symbol: HashMap::new(),
        };

        table.populate_builtins();
        table
    }

    /// 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 runner = SymbolTableRunner { type_context, table: self };

        let errs = runner.populate_name_tables(ast);
        if !errs.is_empty() {
            return Err(errs);
        }
        runner.resolve_scopes(ast);
        Ok(())
    }

    pub fn lookup_symbol(&self, id: &ItemId) -> Option<&Symbol> {
        self.id_to_symbol.get(id).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, sym) in self.id_to_symbol.iter() {
            println!("{} => {}", id, sym);
        }
    }

    /// 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 symbol = Rc::new(Symbol { fully_qualified_name: fqsn.clone(), spec, def_id });
        self.symbol_trie.insert(&fqsn);
        self.fqsn_to_symbol.insert(fqsn, symbol.clone());
        self.id_to_symbol.insert(*id, symbol.clone());
        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 symbol = Rc::new(Symbol { fully_qualified_name: fqsn.clone(), spec, def_id });

        self.symbol_trie.insert(&fqsn);
        self.fqsn_to_symbol.insert(fqsn, symbol.clone());
        self.def_to_symbol.insert(def_id, symbol);
    }

    fn populate_builtins(&mut self) {
        let fqsn = Fqsn::from_strs(&["println"]);
        self.populate_single_builtin(fqsn, Builtin::IOPrintLn);

        let fqsn = Fqsn::from_strs(&["print"]);
        self.populate_single_builtin(fqsn, Builtin::IOPrint);
    }
}

struct SymbolTableRunner<'a> {
    type_context: &'a mut TypeContext,
    table: &'a mut SymbolTable,
}

#[allow(dead_code)]
#[derive(Debug, Clone)]
pub struct Symbol {
    fully_qualified_name: Fqsn,
    spec: SymbolSpec,
    def_id: DefId,
}

impl Symbol {
    pub fn local_name(&self) -> Rc<String> {
        self.fully_qualified_name.local_name()
    }

    pub fn def_id(&self) -> Option<DefId> {
        Some(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,
    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),
        }
    }
}

impl<'a> SymbolTableRunner<'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)
    }

    /// Walks the AST, matching the ID of an identifier used in some expression to
    /// the corresponding Symbol.
    fn resolve_scopes(&mut self, ast: &ast::AST) {
        let mut resolver = resolver::ScopeResolver::new(self.table);
        resolver.resolve(ast);
    }

    /// 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
    fn populate_name_tables(&mut self, ast: &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],
        scope_stack: &mut Vec<Scope>,
        function_scope: bool,
    ) -> Vec<SymbolError> {
        let mut errors = vec![];

        for statement in statements {
            let Statement { id, kind, location } = statement; //TODO I'm not sure if I need to do anything with this ID
            let location = *location;
            if let Err(err) = self.add_single_statement(id, kind, location, scope_stack, function_scope) {
                errors.push(err);
            } else {
                // If there's an error with a name, don't recurse into subscopes of that name
                let recursive_errs = match kind {
                    StatementKind::Declaration(Declaration::FuncDecl(signature, body)) => {
                        let new_scope = Scope::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
                    }
                    StatementKind::Module(ModuleSpecifier { name, contents }) => {
                        let new_scope = Scope::Name(name.clone());
                        scope_stack.push(new_scope);
                        let output = self.add_from_scope(contents.as_ref(), scope_stack, false);
                        scope_stack.pop();
                        output
                    }
                    StatementKind::Declaration(Declaration::TypeDecl { name, body, mutable }) =>
                        self.add_type_members(name, body, mutable, location, scope_stack),
                    _ => vec![],
                };
                errors.extend(recursive_errs.into_iter());
            }
        }

        errors
    }

    fn add_single_statement(
        &mut self,
        id: &ItemId,
        kind: &StatementKind,
        location: Location,
        scope_stack: &[Scope],
        function_scope: bool,
    ) -> Result<(), SymbolError> {
        match kind {
            StatementKind::Declaration(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 })?;

                self.add_symbol(id, fq_function, SymbolSpec::Func);
            }
            StatementKind::Declaration(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 })?;

                self.add_symbol(id, fq_function, SymbolSpec::Func);
            }
            StatementKind::Declaration(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 })?;
            }
            StatementKind::Declaration(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);
                }
            }
            StatementKind::Module(ModuleSpecifier { name, .. }) => {
                let fq_module = Fqsn::from_scope_stack(scope_stack, name.clone());
                self.table.fq_names.register(fq_module, NameSpec { location, kind: NameKind::Module })?;
            }
            _ => (),
        }
        Ok(())
    }

    fn add_type_members(
        &mut self,
        type_name: &TypeSingletonName,
        type_body: &TypeBody,
        _mutable: &bool,
        location: Location,
        scope_stack: &mut Vec<Scope>,
    ) -> Vec<SymbolError> {
        let variants = match type_body {
            TypeBody::Variants(variants) => variants.clone(),
            TypeBody::ImmediateRecord(id, fields) => vec![Variant {
                id: *id,
                name: type_name.name.clone(),
                kind: VariantKind::Record(fields.clone()),
            }],
        };
        let type_fqsn = Fqsn::from_scope_stack(scope_stack, type_name.name.clone());

        let new_scope = Scope::Name(type_name.name.clone());
        scope_stack.push(new_scope);

        // 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 variant_name = Fqsn::from_scope_stack(scope_stack.as_ref(), variant.name.clone());
                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_name: variant_name.clone(),
                                location,
                                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 fqsn_id_map = HashMap::new();
        for variant in variants.iter() {
            let Variant { name, kind, id } = variant;

            fqsn_id_map.insert(Fqsn::from_scope_stack(scope_stack.as_ref(), 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 fqsn = Fqsn::from_scope_stack(scope_stack.as_ref(), Rc::new(variant.name.to_string()));
            let id = fqsn_id_map.get(&fqsn).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, fqsn, spec);
        }

        scope_stack.pop();
        vec![]
    }
}