Changeset - 291ee7a49c03
[Not reviewed]
0 8 0
mh - 3 years ago 2022-02-15 14:58:17
contact@maxhenger.nl
Add concept of TypeId for builtin types as well
8 files changed with 137 insertions and 69 deletions:
0 comments (0 inline, 0 general)
src/collections/string_pool.rs
Show inline comments
 
use std::ptr::{null_mut, null};
 
use std::hash::{Hash, Hasher};
 
use std::marker::PhantomData;
 
use std::fmt::{Debug, Display, Formatter, Result as FmtResult};
 

	
 
const SLAB_SIZE: usize = u16::MAX as usize;
 

	
 
#[derive(Clone)]
 
pub struct StringRef<'a> {
 
    data: *const u8,
 
    length: usize,
 
    _phantom: PhantomData<&'a [u8]>,
 
}
 

	
 
// As the StringRef is an immutable thing:
 
unsafe impl Sync for StringRef<'_> {}
 
unsafe impl Send for StringRef<'_> {}
 

	
 
impl<'a> StringRef<'a> {
 
    /// `new` constructs a new StringRef whose data is not owned by the
 
    /// `StringPool`, hence cannot have a `'static` lifetime.
 
    pub(crate) fn new(data: &'a [u8]) -> StringRef<'a> {
 
        // This is an internal (compiler) function: so debug_assert that the
 
        // string is valid ascii. Most commonly the input will come from the
 
        // code's source file, which is checked for ASCII-ness anyway.
 
        debug_assert!(data.is_ascii());
 
        let length = data.len();
 
        let data = data.as_ptr();
 
        StringRef{ data, length, _phantom: PhantomData }
 
    }
 

	
 
    /// `new_empty` creates a empty StringRef. It is a null pointer with a
 
    /// length of zero.
 
    pub(crate) fn new_empty() -> StringRef<'static> {
 
    pub(crate) const fn new_empty() -> StringRef<'static> {
 
        StringRef{ data: null(), length: 0, _phantom: PhantomData }
 
    }
 

	
 
    pub fn as_str(&self) -> &'a str {
 
        unsafe {
 
            let slice = std::slice::from_raw_parts::<'a, u8>(self.data, self.length);
 
            std::str::from_utf8_unchecked(slice)
 
        }
 
    }
 

	
 
    pub fn as_bytes(&self) -> &'a [u8] {
 
        unsafe {
 
            std::slice::from_raw_parts::<'a, u8>(self.data, self.length)
 
        }
 
    }
 
}
 

	
 
impl<'a> Debug for StringRef<'a> {
 
    fn fmt(&self, f: &mut Formatter<'_>) -> FmtResult {
 
        f.write_str("StringRef{ value: ")?;
 
        f.write_str(self.as_str())?;
 
        f.write_str(" }")
 
    }
 
}
 

	
 
impl<'a> Display for StringRef<'a> {
 
    fn fmt(&self, f: &mut Formatter<'_>) -> FmtResult {
 
        f.write_str(self.as_str())
 
    }
 
}
 

	
 
impl PartialEq for StringRef<'_> {
 
    fn eq(&self, other: &StringRef) -> bool {
 
        self.as_str() == other.as_str()
 
    }
 
}
 

	
 
impl Eq for StringRef<'_> {}
 

	
 
impl Hash for StringRef<'_> {
 
    fn hash<H: Hasher>(&self, state: &mut H) {
 
        state.write(self.as_bytes());
 
    }
 
}
 

	
 
struct StringPoolSlab {
 
    prev: *mut StringPoolSlab,
 
    data: Vec<u8>,
 
    remaining: usize,
 
}
 

	
 
impl StringPoolSlab {
 
    fn new(prev: *mut StringPoolSlab) -> Self {
 
        Self{ prev, data: Vec::with_capacity(SLAB_SIZE), remaining: SLAB_SIZE }
 
    }
 
}
 

	
 
/// StringPool is a ever-growing pool of strings. Strings have a maximum size
 
/// equal to the slab size. The slabs are essentially a linked list to maintain
 
/// pointer-stability of the strings themselves.
 
/// All `StringRef` instances are invalidated when the string pool is dropped
 
pub(crate) struct StringPool {
 
    last: *mut StringPoolSlab,
 
}
 

	
 
impl StringPool {
 
    pub(crate) fn new() -> Self {
 
        // To have some stability we just turn a box into a raw ptr.
 
        let initial_slab = Box::new(StringPoolSlab::new(null_mut()));
 
        let initial_slab = Box::into_raw(initial_slab);
 
        StringPool{
 
            last: initial_slab,
 
        }
 
    }
 

	
 
    /// Interns a string to the `StringPool`, returning a reference to it. The
 
    /// pointer owned by `StringRef` is `'static` as the `StringPool` doesn't
 
    /// reallocate/deallocate until dropped (which only happens at the end of
 
    /// the program.)
 
    pub(crate) fn intern(&mut self, data: &[u8]) -> StringRef<'static> {
 
        let data_len = data.len();
 
        assert!(data_len <= SLAB_SIZE, "string is too large for slab"); // if you hit this, create logic for large-string allocations
 
        debug_assert!(std::str::from_utf8(data).is_ok(), "string to intern is not valid UTF-8 encoded");
 
        
 
        let mut last = unsafe{&mut *self.last};
 
        if data.len() > last.remaining {
 
            // Doesn't fit: allocate new slab
 
            self.alloc_new_slab();
 
            last = unsafe{&mut *self.last};
 
        }
 

	
 
        // Must fit now, compute hash and put in buffer
 
        debug_assert!(data_len <= last.remaining);
 
        let range_start = last.data.len();
 
        last.data.extend_from_slice(data);
 
        last.remaining -= data_len;
 
        debug_assert_eq!(range_start + data_len, last.data.len());
 

	
 
        unsafe {
 
            let start = last.data.as_ptr().offset(range_start as isize);
 
            StringRef{ data: start, length: data_len, _phantom: PhantomData }
 
        }
 
    }
 

	
 
    fn alloc_new_slab(&mut self) {
 
        let new_slab = Box::new(StringPoolSlab::new(self.last));
 
        let new_slab = Box::into_raw(new_slab);
 
        self.last = new_slab;
 
    }
 
}
 

	
 
impl Drop for StringPool {
 
    fn drop(&mut self) {
 
        let mut new_slab = self.last;
 
        while !new_slab.is_null() {
 
            let cur_slab = new_slab;
 
            unsafe {
 
                new_slab = (*cur_slab).prev;
 
                Box::from_raw(cur_slab); // consume and deallocate
 
            }
 
        }
 
    }
 
}
 

	
 
// String pool cannot be cloned, and the created `StringRef` instances remain
 
// allocated until the end of the program, so it is always safe to send. It is
 
// also sync in the sense that it becomes an immutable thing after compilation,
 
// but lets not derive that if we would ever become a multithreaded compiler in
 
// the future.
 
unsafe impl Send for StringPool {}
 

	
 
#[cfg(test)]
 
mod tests {
 
    use super::*;
 

	
 
    #[test]
 
    fn display_empty_string_ref() {
 
        // Makes sure that null pointer inside StringRef will not cause issues
 
        let v = StringRef::new_empty();
 
        let val = format!("{}{:?}", v, v);
 
    }
 

	
 
    #[test]
 
    fn test_string_just_fits() {
 
        let large = "0".repeat(SLAB_SIZE);
 
        let mut pool = StringPool::new();
 
        let interned = pool.intern(large.as_bytes());
 
        assert_eq!(interned.as_str(), large);
 
    }
 

	
 
    #[test]
 
    #[should_panic]
 
    fn test_string_too_large() {
 
        let large = "0".repeat(SLAB_SIZE + 1);
 
        let mut pool = StringPool::new();
 
        let _interned = pool.intern(large.as_bytes());
 
    }
 

	
 
    #[test]
 
    fn test_lots_of_small_allocations() {
 
        const NUM_PER_SLAB: usize = 32;
 
        const NUM_SLABS: usize = 4;
 

	
 
        let to_intern = "0".repeat(SLAB_SIZE / NUM_PER_SLAB);
 
        let mut pool = StringPool::new();
 

	
 
        let mut last_slab = pool.last;
 
        let mut all_refs = Vec::new();
 

	
 
        // Fill up first slab
 
        for _alloc_idx in 0..NUM_PER_SLAB {
 
            let interned = pool.intern(to_intern.as_bytes());
 
            all_refs.push(interned);
 
            assert!(std::ptr::eq(last_slab, pool.last));
 
        }
 

	
 
        for _slab_idx in 0..NUM_SLABS-1 {
 
            for alloc_idx in 0..NUM_PER_SLAB {
 
                let interned = pool.intern(to_intern.as_bytes());
 
                all_refs.push(interned);
 

	
 
                if alloc_idx == 0 {
 
                    // First allocation produces a new slab
 
                    assert!(!std::ptr::eq(last_slab, pool.last));
 
                    last_slab = pool.last;
 
                } else {
 
                    assert!(std::ptr::eq(last_slab, pool.last));
 
                }
 
            }
 
        }
 

	
 
        // All strings are still correct
src/protocol/ast.rs
Show inline comments
 
@@ -156,674 +156,679 @@ define_new_ast_id!(SelectExpressionId, ExpressionId, index(SelectExpression, Exp
 
define_new_ast_id!(LiteralExpressionId, ExpressionId, index(LiteralExpression, Expression::Literal, expressions), alloc(alloc_literal_expression));
 
define_new_ast_id!(CastExpressionId, ExpressionId, index(CastExpression, Expression::Cast, expressions), alloc(alloc_cast_expression));
 
define_new_ast_id!(CallExpressionId, ExpressionId, index(CallExpression, Expression::Call, expressions), alloc(alloc_call_expression));
 
define_new_ast_id!(VariableExpressionId, ExpressionId, index(VariableExpression, Expression::Variable, expressions), alloc(alloc_variable_expression));
 

	
 
define_aliased_ast_id!(ScopeId, Id<Scope>, index(Scope, scopes), alloc(alloc_scope));
 

	
 
#[derive(Debug)]
 
pub struct Heap {
 
    // Root arena, contains the entry point for different modules. Each root
 
    // contains lists of IDs that correspond to the other arenas.
 
    pub(crate) protocol_descriptions: Arena<Root>,
 
    // Contents of a file, these are the elements the `Root` elements refer to
 
    pragmas: Arena<Pragma>,
 
    pub(crate) imports: Arena<Import>,
 
    pub(crate) variables: Arena<Variable>,
 
    pub(crate) definitions: Arena<Definition>,
 
    pub(crate) statements: Arena<Statement>,
 
    pub(crate) expressions: Arena<Expression>,
 
    pub(crate) scopes: Arena<Scope>,
 
}
 

	
 
impl Heap {
 
    pub fn new() -> Heap {
 
        Heap {
 
            // string_alloc: StringAllocator::new(),
 
            protocol_descriptions: Arena::new(),
 
            pragmas: Arena::new(),
 
            imports: Arena::new(),
 
            variables: Arena::new(),
 
            definitions: Arena::new(),
 
            statements: Arena::new(),
 
            expressions: Arena::new(),
 
            scopes: Arena::new(),
 
        }
 
    }
 
    pub fn alloc_memory_statement(
 
        &mut self,
 
        f: impl FnOnce(MemoryStatementId) -> MemoryStatement,
 
    ) -> MemoryStatementId {
 
        MemoryStatementId(LocalStatementId(self.statements.alloc_with_id(|id| {
 
            Statement::Local(LocalStatement::Memory(
 
                f(MemoryStatementId(LocalStatementId(id)))
 
            ))
 
        })))
 
    }
 
    pub fn alloc_channel_statement(
 
        &mut self,
 
        f: impl FnOnce(ChannelStatementId) -> ChannelStatement,
 
    ) -> ChannelStatementId {
 
        ChannelStatementId(LocalStatementId(self.statements.alloc_with_id(|id| {
 
            Statement::Local(LocalStatement::Channel(
 
                f(ChannelStatementId(LocalStatementId(id)))
 
            ))
 
        })))
 
    }
 
}
 

	
 
impl Index<MemoryStatementId> for Heap {
 
    type Output = MemoryStatement;
 
    fn index(&self, index: MemoryStatementId) -> &Self::Output {
 
        &self.statements[index.0.0].as_memory()
 
    }
 
}
 

	
 
impl Index<ChannelStatementId> for Heap {
 
    type Output = ChannelStatement;
 
    fn index(&self, index: ChannelStatementId) -> &Self::Output {
 
        &self.statements[index.0.0].as_channel()
 
    }
 
}
 

	
 
#[derive(Debug, Clone)]
 
pub struct Root {
 
    pub this: RootId,
 
    // Phase 1: parser
 
    // pub position: InputPosition,
 
    pub pragmas: Vec<PragmaId>,
 
    pub imports: Vec<ImportId>,
 
    pub definitions: Vec<DefinitionId>,
 
}
 

	
 
impl Root {
 
    pub fn get_definition_ident(&self, h: &Heap, id: &[u8]) -> Option<DefinitionId> {
 
        for &def in self.definitions.iter() {
 
            if h[def].identifier().value.as_bytes() == id {
 
                return Some(def);
 
            }
 
        }
 
        None
 
    }
 
}
 

	
 
#[derive(Debug, Clone)]
 
pub enum Pragma {
 
    Version(PragmaVersion),
 
    Module(PragmaModule),
 
}
 

	
 
impl Pragma {
 
    pub(crate) fn as_module(&self) -> &PragmaModule {
 
        match self {
 
            Pragma::Module(pragma) => pragma,
 
            _ => unreachable!("Tried to obtain {:?} as PragmaModule", self),
 
        }
 
    }
 
}
 

	
 
#[derive(Debug, Clone)]
 
pub struct PragmaVersion {
 
    pub this: PragmaId,
 
    // Phase 1: parser
 
    pub span: InputSpan, // of full pragma
 
    pub version: u64,
 
}
 

	
 
#[derive(Debug, Clone)]
 
pub struct PragmaModule {
 
    pub this: PragmaId,
 
    // Phase 1: parser
 
    pub span: InputSpan, // of full pragma
 
    pub value: Identifier,
 
}
 

	
 
#[derive(Debug, Clone)]
 
pub enum Import {
 
    Module(ImportModule),
 
    Symbols(ImportSymbols)
 
}
 

	
 
impl Import {
 
    pub(crate) fn span(&self) -> InputSpan {
 
        match self {
 
            Import::Module(v) => v.span,
 
            Import::Symbols(v) => v.span,
 
        }
 
    }
 

	
 
    pub(crate) fn as_module(&self) -> &ImportModule {
 
        match self {
 
            Import::Module(m) => m,
 
            _ => unreachable!("Unable to cast 'Import' to 'ImportModule'")
 
        }
 
    }
 
    pub(crate) fn as_symbols(&self) -> &ImportSymbols {
 
        match self {
 
            Import::Symbols(m) => m,
 
            _ => unreachable!("Unable to cast 'Import' to 'ImportSymbols'")
 
        }
 
    }
 
    pub(crate) fn as_symbols_mut(&mut self) -> &mut ImportSymbols {
 
        match self {
 
            Import::Symbols(m) => m,
 
            _ => unreachable!("Unable to cast 'Import' to 'ImportSymbols'")
 
        }
 
    }
 
}
 

	
 
#[derive(Debug, Clone)]
 
pub struct ImportModule {
 
    pub this: ImportId,
 
    // Phase 1: parser
 
    pub span: InputSpan,
 
    pub module: Identifier,
 
    pub alias: Identifier,
 
    pub module_id: RootId,
 
}
 

	
 
#[derive(Debug, Clone)]
 
pub struct AliasedSymbol {
 
    pub name: Identifier,
 
    pub alias: Option<Identifier>,
 
    pub definition_id: DefinitionId,
 
}
 

	
 
#[derive(Debug, Clone)]
 
pub struct ImportSymbols {
 
    pub this: ImportId,
 
    // Phase 1: parser
 
    pub span: InputSpan,
 
    pub module: Identifier,
 
    pub module_id: RootId,
 
    pub symbols: Vec<AliasedSymbol>,
 
}
 

	
 
#[derive(Debug, Clone)]
 
pub struct Identifier {
 
    pub span: InputSpan,
 
    pub value: StringRef<'static>,
 
}
 

	
 
impl Identifier {
 
    pub(crate) fn new_empty(span: InputSpan) -> Identifier {
 
    pub(crate) const fn new_empty(span: InputSpan) -> Identifier {
 
        return Identifier{
 
            span,
 
            value: StringRef::new_empty(),
 
        };
 
    }
 
}
 

	
 
impl PartialEq for Identifier {
 
    fn eq(&self, other: &Self) -> bool {
 
        return self.value == other.value
 
    }
 
}
 

	
 
impl Display for Identifier {
 
    fn fmt(&self, f: &mut Formatter<'_>) -> fmt::Result {
 
        write!(f, "{}", self.value.as_str())
 
    }
 
}
 

	
 
#[derive(Debug, Clone, PartialEq, Eq)]
 
pub enum ParserTypeVariant {
 
    // Special builtin, only usable by the compiler and not constructable by the
 
    // programmer
 
    Void,
 
    InputOrOutput,
 
    ArrayLike,
 
    IntegerLike,
 
    // Basic builtin
 
    Message,
 
    Bool,
 
    UInt8, UInt16, UInt32, UInt64,
 
    SInt8, SInt16, SInt32, SInt64,
 
    Character, String,
 
    // Literals (need to get concrete builtin type during typechecking)
 
    IntegerLiteral,
 
    // Marker for inference
 
    Inferred,
 
    // Builtins expecting one subsequent type
 
    Array,
 
    Input,
 
    Output,
 
    // Tuple: expecting any number of elements. Note that the parser type can
 
    // have one-valued tuples, these will be filtered out later during type
 
    // checking.
 
    Tuple(u32), // u32 = number of subsequent types
 
    // User-defined types
 
    PolymorphicArgument(DefinitionId, u32), // u32 = index into polymorphic variables
 
    Definition(DefinitionId, u32), // u32 = number of subsequent types in the type tree.
 
}
 

	
 
impl ParserTypeVariant {
 
    pub(crate) fn num_embedded(&self) -> usize {
 
        use ParserTypeVariant::*;
 

	
 
        match self {
 
            Void | IntegerLike |
 
            Message | Bool |
 
            UInt8 | UInt16 | UInt32 | UInt64 |
 
            SInt8 | SInt16 | SInt32 | SInt64 |
 
            Character | String | IntegerLiteral |
 
            Inferred | PolymorphicArgument(_, _) =>
 
                0,
 
            ArrayLike | InputOrOutput | Array | Input | Output =>
 
                1,
 
            Definition(_, num) | Tuple(num) => *num as usize,
 
        }
 
    }
 
}
 

	
 
/// ParserTypeElement is an element of the type tree. An element may be
 
/// implicit, meaning that the user didn't specify the type, but it was set by
 
/// the compiler.
 
#[derive(Debug, Clone)]
 
pub struct ParserTypeElement {
 
    pub element_span: InputSpan, // span of this element, not including the child types
 
    pub variant: ParserTypeVariant,
 
}
 

	
 
/// ParserType is a specification of a type during the parsing phase and initial
 
/// linker/validator phase of the compilation process. These types may be
 
/// (partially) inferred or represent literals (e.g. a integer whose bytesize is
 
/// not yet determined).
 
///
 
/// Its contents are the depth-first serialization of the type tree. Each node
 
/// is a type that may accept polymorphic arguments. The polymorphic arguments
 
/// are then the children of the node.
 
#[derive(Debug, Clone)]
 
pub struct ParserType {
 
    pub elements: Vec<ParserTypeElement>,
 
    pub full_span: InputSpan,
 
}
 

	
 
impl ParserType {
 
    pub(crate) fn iter_embedded(&self, parent_idx: usize) -> ParserTypeIter {
 
        ParserTypeIter::new(&self.elements, parent_idx)
 
    }
 
}
 

	
 
/// Iterator over the embedded elements of a specific element.
 
pub struct ParserTypeIter<'a> {
 
    pub elements: &'a [ParserTypeElement],
 
    pub cur_embedded_idx: usize,
 
}
 

	
 
impl<'a> ParserTypeIter<'a> {
 
    fn new(elements: &'a [ParserTypeElement], parent_idx: usize) -> Self {
 
        debug_assert!(parent_idx < elements.len(), "parent index exceeds number of elements in ParserType");
 
        if elements[0].variant.num_embedded() == 0 {
 
            // Parent element does not have any embedded types, place
 
            // `cur_embedded_idx` at end so we will always return `None`
 
            Self{ elements, cur_embedded_idx: elements.len() }
 
        } else {
 
            // Parent element has an embedded type
 
            Self{ elements, cur_embedded_idx: parent_idx + 1 }
 
        }
 
    }
 
}
 

	
 
impl<'a> Iterator for ParserTypeIter<'a> {
 
    type Item = &'a [ParserTypeElement];
 

	
 
    fn next(&mut self) -> Option<Self::Item> {
 
        let elements_len = self.elements.len();
 
        if self.cur_embedded_idx >= elements_len {
 
            return None;
 
        }
 

	
 
        // Seek to the end of the subtree
 
        let mut depth = 1;
 
        let start_element = self.cur_embedded_idx;
 
        while self.cur_embedded_idx < elements_len {
 
            let cur_element = &self.elements[self.cur_embedded_idx];
 
            let depth_change = cur_element.variant.num_embedded() as i32 - 1;
 
            depth += depth_change;
 
            debug_assert!(depth >= 0, "illegally constructed ParserType: {:?}", self.elements);
 

	
 
            self.cur_embedded_idx += 1;
 
            if depth == 0 {
 
                break;
 
            }
 
        }
 

	
 
        debug_assert!(depth == 0, "illegally constructed ParserType: {:?}", self.elements);
 
        return Some(&self.elements[start_element..self.cur_embedded_idx]);
 
    }
 
}
 

	
 
/// ConcreteType is the representation of a type after the type inference and
 
/// checker is finished. These are fully typed.
 
#[derive(Debug, Clone, Copy, Eq, PartialEq, Hash)]
 
pub enum ConcreteTypePart {
 
    // Special types (cannot be explicitly constructed by the programmer)
 
    Void,
 
    // Builtin types without nested types
 
    Message,
 
    Bool,
 
    UInt8, UInt16, UInt32, UInt64,
 
    SInt8, SInt16, SInt32, SInt64,
 
    Character, String,
 
    // Builtin types with one nested type
 
    Array,
 
    Slice,
 
    Input,
 
    Output,
 
    Pointer,
 
    // Tuple: variable number of nested types, will never be 1
 
    Tuple(u32),
 
    // User defined type with any number of nested types
 
    Instance(DefinitionId, u32),    // instance of data type
 
    Function(DefinitionId, u32),    // instance of function
 
    Component(DefinitionId, u32),   // instance of a connector
 
}
 

	
 
impl ConcreteTypePart {
 
    pub(crate) fn num_embedded(&self) -> u32 {
 
        use ConcreteTypePart::*;
 

	
 
        match self {
 
            Void | Message | Bool |
 
            UInt8 | UInt16 | UInt32 | UInt64 |
 
            SInt8 | SInt16 | SInt32 | SInt64 |
 
            Character | String =>
 
                0,
 
            Array | Slice | Input | Output =>
 
            Array | Slice | Input | Output | Pointer =>
 
                1,
 
            Tuple(num_embedded) => *num_embedded,
 
            Instance(_, num_embedded) => *num_embedded,
 
            Function(_, num_embedded) => *num_embedded,
 
            Component(_, num_embedded) => *num_embedded,
 
        }
 
    }
 
}
 

	
 
#[derive(Debug, Clone, Eq, PartialEq)]
 
pub struct ConcreteType {
 
    pub(crate) parts: Vec<ConcreteTypePart>
 
}
 

	
 
impl Default for ConcreteType {
 
    fn default() -> Self {
 
        Self{ parts: Vec::new() }
 
    }
 
}
 

	
 
impl ConcreteType {
 
    /// Returns an iterator over the subtrees that are type arguments (e.g. an
 
    /// array element's type, or a polymorphic type's arguments) to the
 
    /// provided parent type (specified by its index in the `parts` array).
 
    pub(crate) fn embedded_iter(&self, parent_part_idx: usize) -> ConcreteTypeIter {
 
        return ConcreteTypeIter::new(&self.parts, parent_part_idx);
 
    }
 

	
 
    /// Construct a human-readable name for the type. Because this performs
 
    /// a string allocation don't use it for anything else then displaying the
 
    /// type to the user.
 
    pub(crate) fn display_name(&self, heap: &Heap) -> String {
 
        return Self::type_parts_display_name(self.parts.as_slice(), heap);
 
    }
 

	
 
    // --- Utilities that operate on slice of parts
 

	
 
    /// Given the starting position of a type tree, determine the exclusive
 
    /// ending index.
 
    pub(crate) fn type_parts_subtree_end_idx(parts: &[ConcreteTypePart], start_idx: usize) -> usize {
 
        let mut depth = 1;
 
        let num_parts = parts.len();
 
        debug_assert!(start_idx < num_parts);
 

	
 
        for part_idx in start_idx..parts.len() {
 
            let depth_change = parts[part_idx].num_embedded() as i32 - 1;
 
            depth += depth_change;
 
            debug_assert!(depth >= 0);
 

	
 
            if depth == 0 {
 
                return part_idx + 1;
 
            }
 
        }
 

	
 
        debug_assert!(false, "incorrectly constructed ConcreteType instance");
 
        return 0;
 
    }
 

	
 
    /// Produces a human-readable representation of the concrete type parts
 
    fn type_parts_display_name(parts: &[ConcreteTypePart], heap: &Heap) -> String {
 
        let mut name = String::with_capacity(128);
 
        let _final_idx = Self::render_type_part_at(parts, heap, 0, &mut name);
 
        debug_assert_eq!(_final_idx, parts.len());
 

	
 
        return name;
 
    }
 

	
 
    /// Produces a human-readable representation of a single type part. Lower
 
    /// level utility for `type_parts_display_name`.
 
    fn render_type_part_at(parts: &[ConcreteTypePart], heap: &Heap, mut idx: usize, target: &mut String) -> usize {
 
        use ConcreteTypePart as CTP;
 
        use crate::protocol::parser::token_parsing::*;
 

	
 
        let cur_idx = idx;
 
        idx += 1; // increment by 1, because it always happens
 

	
 
        match parts[cur_idx] {
 
            CTP::Void => { target.push_str("void"); },
 
            CTP::Message => { target.push_str(KW_TYPE_MESSAGE_STR); },
 
            CTP::Bool => { target.push_str(KW_TYPE_BOOL_STR); },
 
            CTP::UInt8 => { target.push_str(KW_TYPE_UINT8_STR); },
 
            CTP::UInt16 => { target.push_str(KW_TYPE_UINT16_STR); },
 
            CTP::UInt32 => { target.push_str(KW_TYPE_UINT32_STR); },
 
            CTP::UInt64 => { target.push_str(KW_TYPE_UINT64_STR); },
 
            CTP::SInt8 => { target.push_str(KW_TYPE_SINT8_STR); },
 
            CTP::SInt16 => { target.push_str(KW_TYPE_SINT16_STR); },
 
            CTP::SInt32 => { target.push_str(KW_TYPE_SINT32_STR); },
 
            CTP::SInt64 => { target.push_str(KW_TYPE_SINT64_STR); },
 
            CTP::Character => { target.push_str(KW_TYPE_CHAR_STR); },
 
            CTP::String => { target.push_str(KW_TYPE_STRING_STR); },
 
            CTP::Array | CTP::Slice => {
 
                idx = Self::render_type_part_at(parts, heap, idx, target);
 
                target.push_str("[]");
 
            },
 
            CTP::Input => {
 
                target.push_str(KW_TYPE_IN_PORT_STR);
 
                target.push('<');
 
                idx = Self::render_type_part_at(parts, heap, idx, target);
 
                target.push('>');
 
            },
 
            CTP::Output => {
 
                target.push_str(KW_TYPE_OUT_PORT_STR);
 
                target.push('<');
 
                idx = Self::render_type_part_at(parts, heap, idx, target);
 
                target.push('>');
 
            },
 
            CTP::Pointer => {
 
                target.push('*');
 
                idx = Self::render_type_part_at(parts, heap, idx, target);
 
            }
 
            CTP::Tuple(num_parts) => {
 
                target.push('(');
 
                if num_parts != 0 {
 
                    idx = Self::render_type_part_at(parts, heap, idx, target);
 
                    for _ in 1..num_parts {
 
                        target.push(',');
 
                        idx = Self::render_type_part_at(parts, heap, idx, target);
 
                    }
 
                }
 
                target.push(')');
 
            },
 
            CTP::Instance(definition_id, num_poly_args) |
 
            CTP::Function(definition_id, num_poly_args) |
 
            CTP::Component(definition_id, num_poly_args) => {
 
                let definition = &heap[definition_id];
 
                target.push_str(definition.identifier().value.as_str());
 

	
 
                if num_poly_args != 0 {
 
                    target.push('<');
 
                    for poly_arg_idx in 0..num_poly_args {
 
                        if poly_arg_idx != 0 {
 
                            target.push(',');
 
                        }
 
                        idx = Self::render_type_part_at(parts, heap, idx, target);
 
                    }
 
                    target.push('>');
 
                }
 
            }
 
        }
 

	
 
        idx
 
    }
 
}
 

	
 
#[derive(Debug)]
 
pub struct ConcreteTypeIter<'a> {
 
    parts: &'a [ConcreteTypePart],
 
    idx_embedded: u32,
 
    num_embedded: u32,
 
    part_idx: usize,
 
}
 

	
 
impl<'a> ConcreteTypeIter<'a> {
 
    pub(crate) fn new(parts: &'a[ConcreteTypePart], parent_idx: usize) -> Self {
 
        let num_embedded = parts[parent_idx].num_embedded();
 
        return ConcreteTypeIter{
 
            parts,
 
            idx_embedded: 0,
 
            num_embedded,
 
            part_idx: parent_idx + 1,
 
        }
 
    }
 
}
 

	
 
impl<'a> Iterator for ConcreteTypeIter<'a> {
 
    type Item = &'a [ConcreteTypePart];
 

	
 
    fn next(&mut self) -> Option<Self::Item> {
 
        if self.idx_embedded == self.num_embedded {
 
            return None;
 
        }
 

	
 
        // Retrieve the subtree of interest
 
        let start_idx = self.part_idx;
 
        let end_idx = ConcreteType::type_parts_subtree_end_idx(&self.parts, start_idx);
 

	
 
        self.idx_embedded += 1;
 
        self.part_idx = end_idx;
 

	
 
        return Some(&self.parts[start_idx..end_idx]);
 
    }
 
}
 

	
 
#[derive(Debug, Clone, Copy)]
 
pub enum ScopeAssociation {
 
    Definition(DefinitionId),
 
    Block(BlockStatementId),
 
    If(IfStatementId, bool), // if true, then body of "if", otherwise body of "else"
 
    While(WhileStatementId),
 
    Synchronous(SynchronousStatementId),
 
    SelectCase(SelectStatementId, u32), // index is select case
 
}
 

	
 
/// `ScopeNode` is a helper that links scopes in two directions. It doesn't
 
/// actually contain any information associated with the scope, this may be
 
/// found on the AST elements that `Scope` points to.
 
#[derive(Debug, Clone)]
 
pub struct Scope {
 
    // Relation to other scopes
 
    pub this: ScopeId,
 
    pub parent: Option<ScopeId>,
 
    pub nested: Vec<ScopeId>,
 
    // Locally available variables/labels
 
    pub association: ScopeAssociation,
 
    pub variables: Vec<VariableId>,
 
    pub labels: Vec<LabeledStatementId>,
 
    // Location trackers/counters
 
    pub relative_pos_in_parent: i32,
 
    pub first_unique_id_in_scope: i32,
 
    pub next_unique_id_in_scope: i32,
 
}
 

	
 
impl Scope {
 
    pub(crate) fn new(id: ScopeId, association: ScopeAssociation) -> Self {
 
        return Self{
 
            this: id,
 
            parent: None,
 
            nested: Vec::new(),
 
            association,
 
            variables: Vec::new(),
 
            labels: Vec::new(),
 
            relative_pos_in_parent: -1,
 
            first_unique_id_in_scope: -1,
 
            next_unique_id_in_scope: -1,
 
        }
 
    }
 
}
 

	
 
impl Scope {
 
    pub(crate) fn new_invalid(this: ScopeId) -> Self {
 
        return Self{
 
            this,
 
            parent: None,
 
            nested: Vec::new(),
 
            association: ScopeAssociation::Definition(DefinitionId::new_invalid()),
 
            variables: Vec::new(),
 
            labels: Vec::new(),
 
            relative_pos_in_parent: -1,
 
            first_unique_id_in_scope: -1,
 
            next_unique_id_in_scope: -1,
 
        };
 
    }
 
}
 

	
 
#[derive(Debug, Clone, PartialEq, Eq)]
 
pub enum VariableKind {
 
    Parameter,      // in parameter list of function/component
 
    Local,          // declared in function/component body
 
    Binding,        // may be bound to in a binding expression (determined in validator/linker)
 
}
 

	
 
#[derive(Debug, Clone)]
 
pub struct Variable {
 
    pub this: VariableId,
 
    // Parsing
 
    pub kind: VariableKind,
 
    pub parser_type: ParserType,
 
    pub identifier: Identifier,
 
    // Validator/linker
 
    pub relative_pos_in_parent: i32,
 
    pub unique_id_in_scope: i32, // Temporary fix until proper bytecode/asm is generated
 
}
 

	
 
#[derive(Debug, Clone)]
 
pub enum Definition {
 
    Struct(StructDefinition),
 
    Enum(EnumDefinition),
 
    Union(UnionDefinition),
 
    Component(ComponentDefinition),
 
    Function(FunctionDefinition),
 
}
 

	
 
impl Definition {
 
    pub fn is_struct(&self) -> bool {
 
        match self {
 
            Definition::Struct(_) => true,
 
            _ => false
 
        }
 
    }
 
    pub(crate) fn as_struct(&self) -> &StructDefinition {
 
        match self {
 
            Definition::Struct(result) => result,
 
            _ => panic!("Unable to cast 'Definition' to 'StructDefinition'"),
 
        }
 
    }
 
    pub(crate) fn as_struct_mut(&mut self) -> &mut StructDefinition {
 
        match self {
 
            Definition::Struct(result) => result,
 
            _ => panic!("Unable to cast 'Definition' to 'StructDefinition'"),
 
        }
 
    }
 
    pub fn is_enum(&self) -> bool {
 
        match self {
 
            Definition::Enum(_) => true,
 
            _ => false,
 
        }
 
    }
 
    pub(crate) fn as_enum(&self) -> &EnumDefinition {
 
        match self {
 
            Definition::Enum(result) => result,
 
            _ => panic!("Unable to cast 'Definition' to 'EnumDefinition'"),
 
        }
src/protocol/ast_printer.rs
Show inline comments
 
@@ -768,267 +768,268 @@ impl ASTWriter {
 
            },
 
            Expression::Cast(expr) => {
 
                self.kv(indent).with_id(PREFIX_CAST_EXPR_ID, expr.this.0.index)
 
                    .with_s_key("CallExpr");
 
                self.kv(indent2).with_s_key("UniqueId").with_disp_val(&expr.unique_id_in_definition);
 
                self.kv(indent2).with_s_key("ToType")
 
                    .with_custom_val(|t| write_parser_type(t, heap, &expr.to_type));
 
                self.kv(indent2).with_s_key("Subject");
 
                self.write_expr(heap, expr.subject, indent3);
 
                self.kv(indent2).with_s_key("Parent")
 
                    .with_custom_val(|v| write_expression_parent(v, &expr.parent));
 
            }
 
            Expression::Call(expr) => {
 
                self.kv(indent).with_id(PREFIX_CALL_EXPR_ID, expr.this.0.index)
 
                    .with_s_key("CallExpr");
 

	
 
                self.kv(indent2).with_s_key("UniqueId").with_disp_val(&expr.unique_id_in_definition);
 
                let definition = &heap[expr.definition];
 
                match definition {
 
                    Definition::Component(definition) => {
 
                        self.kv(indent2).with_s_key("BuiltIn").with_disp_val(&false);
 
                        self.kv(indent2).with_s_key("Variant").with_debug_val(&definition.variant);
 
                    },
 
                    Definition::Function(definition) => {
 
                        self.kv(indent2).with_s_key("BuiltIn").with_disp_val(&definition.builtin);
 
                        self.kv(indent2).with_s_key("Variant").with_s_val("Function");
 
                    },
 
                    _ => unreachable!()
 
                }
 
                self.kv(indent2).with_s_key("MethodName").with_identifier_val(definition.identifier());
 
                self.kv(indent2).with_s_key("ParserType")
 
                    .with_custom_val(|t| write_parser_type(t, heap, &expr.parser_type));
 

	
 
                // Arguments
 
                self.kv(indent2).with_s_key("Arguments");
 
                for arg_id in &expr.arguments {
 
                    self.write_expr(heap, *arg_id, indent3);
 
                }
 

	
 
                // Parent
 
                self.kv(indent2).with_s_key("Parent")
 
                    .with_custom_val(|v| write_expression_parent(v, &expr.parent));
 
            },
 
            Expression::Variable(expr) => {
 
                self.kv(indent).with_id(PREFIX_VARIABLE_EXPR_ID, expr.this.0.index)
 
                    .with_s_key("VariableExpr");
 
                self.kv(indent2).with_s_key("UniqueId").with_disp_val(&expr.unique_id_in_definition);
 
                self.kv(indent2).with_s_key("Name").with_identifier_val(&expr.identifier);
 
                self.kv(indent2).with_s_key("Definition")
 
                    .with_opt_disp_val(expr.declaration.as_ref().map(|v| &v.index));
 
                self.kv(indent2).with_s_key("Parent")
 
                    .with_custom_val(|v| write_expression_parent(v, &expr.parent));
 
            }
 
        }
 
    }
 

	
 
    fn write_variable(&mut self, heap: &Heap, variable_id: VariableId, indent: usize) {
 
        let var = &heap[variable_id];
 
        let indent2 = indent + 1;
 

	
 
        self.kv(indent).with_id(PREFIX_VARIABLE_ID, variable_id.index)
 
            .with_s_key("Variable");
 

	
 
        self.kv(indent2).with_s_key("Name").with_identifier_val(&var.identifier);
 
        self.kv(indent2).with_s_key("Kind").with_debug_val(&var.kind);
 
        self.kv(indent2).with_s_key("ParserType")
 
            .with_custom_val(|w| write_parser_type(w, heap, &var.parser_type));
 
        self.kv(indent2).with_s_key("RelativePos").with_disp_val(&var.relative_pos_in_parent);
 
        self.kv(indent2).with_s_key("UniqueScopeID").with_disp_val(&var.unique_id_in_scope);
 
    }
 

	
 
    //--------------------------------------------------------------------------
 
    // Printing Utilities
 
    //--------------------------------------------------------------------------
 

	
 
    fn kv(&mut self, indent: usize) -> KV {
 
        KV::new(&mut self.buffer, &mut self.temp1, &mut self.temp2, indent)
 
    }
 

	
 
    fn flush<W: IOWrite>(&mut self, w: &mut W) {
 
        w.write(self.buffer.as_bytes()).unwrap();
 
        self.buffer.clear()
 
    }
 
}
 

	
 
fn write_option<V: Display>(target: &mut String, value: Option<V>) {
 
    target.clear();
 
    match &value {
 
        Some(v) => target.push_str(&format!("Some({})", v)),
 
        None => target.push_str("None")
 
    };
 
}
 

	
 
fn write_parser_type(target: &mut String, heap: &Heap, t: &ParserType) {
 
    use ParserTypeVariant as PTV;
 

	
 
    fn write_element(target: &mut String, heap: &Heap, t: &ParserType, mut element_idx: usize) -> usize {
 
        let element = &t.elements[element_idx];
 
        match &element.variant {
 
            PTV::Void => target.push_str("void"),
 
            PTV::InputOrOutput => {
 
                target.push_str("portlike<");
 
                element_idx = write_element(target, heap, t, element_idx + 1);
 
                target.push('>');
 
            },
 
            PTV::ArrayLike => {
 
                element_idx = write_element(target, heap, t, element_idx + 1);
 
                target.push_str("[???]");
 
            },
 
            PTV::IntegerLike => target.push_str("integerlike"),
 
            PTV::Message => { target.push_str(KW_TYPE_MESSAGE_STR); },
 
            PTV::Bool => { target.push_str(KW_TYPE_BOOL_STR); },
 
            PTV::UInt8 => { target.push_str(KW_TYPE_UINT8_STR); },
 
            PTV::UInt16 => { target.push_str(KW_TYPE_UINT16_STR); },
 
            PTV::UInt32 => { target.push_str(KW_TYPE_UINT32_STR); },
 
            PTV::UInt64 => { target.push_str(KW_TYPE_UINT64_STR); },
 
            PTV::SInt8 => { target.push_str(KW_TYPE_SINT8_STR); },
 
            PTV::SInt16 => { target.push_str(KW_TYPE_SINT16_STR); },
 
            PTV::SInt32 => { target.push_str(KW_TYPE_SINT32_STR); },
 
            PTV::SInt64 => { target.push_str(KW_TYPE_SINT64_STR); },
 
            PTV::Character => { target.push_str(KW_TYPE_CHAR_STR); },
 
            PTV::String => { target.push_str(KW_TYPE_STRING_STR); },
 
            PTV::IntegerLiteral => { target.push_str("int_literal"); },
 
            PTV::Inferred => { target.push_str(KW_TYPE_INFERRED_STR); },
 
            PTV::Array => {
 
                element_idx = write_element(target, heap, t, element_idx + 1);
 
                target.push_str("[]");
 
            },
 
            PTV::Input => {
 
                target.push_str(KW_TYPE_IN_PORT_STR);
 
                target.push('<');
 
                element_idx = write_element(target, heap, t, element_idx + 1);
 
                target.push('>');
 
            },
 
            PTV::Output => {
 
                target.push_str(KW_TYPE_OUT_PORT_STR);
 
                target.push('<');
 
                element_idx = write_element(target, heap, t, element_idx + 1);
 
                target.push('>');
 
            },
 
            PTV::Tuple(num_embedded) => {
 
                target.push('(');
 
                let num_embedded = *num_embedded;
 
                for embedded_idx in 0..num_embedded {
 
                    if embedded_idx != 0 {
 
                        target.push(',');
 
                    }
 
                    element_idx = write_element(target, heap, t, element_idx + 1);
 
                }
 
                target.push(')');
 
            }
 
            PTV::PolymorphicArgument(definition_id, arg_idx) => {
 
                let definition = &heap[*definition_id];
 
                let poly_var = &definition.poly_vars()[*arg_idx as usize].value;
 
                target.push_str(poly_var.as_str());
 
            },
 
            PTV::Definition(definition_id, num_embedded) => {
 
                let definition = &heap[*definition_id];
 
                let definition_ident = definition.identifier().value.as_str();
 
                target.push_str(definition_ident);
 

	
 
                let num_embedded = *num_embedded;
 
                if num_embedded != 0 {
 
                    target.push('<');
 
                    for embedded_idx in 0..num_embedded {
 
                        if embedded_idx != 0 {
 
                            target.push(',');
 
                        }
 
                        element_idx = write_element(target, heap, t, element_idx + 1);
 
                    }
 
                    target.push('>');
 
                }
 
            }
 
        }
 

	
 
        element_idx
 
    }
 

	
 
    write_element(target, heap, t, 0);
 
}
 

	
 
fn write_concrete_type(target: &mut String, heap: &Heap, def_id: DefinitionId, t: &ConcreteType) {
 
    use ConcreteTypePart as CTP;
 

	
 
    fn write_concrete_part(target: &mut String, heap: &Heap, def_id: DefinitionId, t: &ConcreteType, mut idx: usize) -> usize {
 
        if idx >= t.parts.len() {
 
            return idx;
 
        }
 

	
 
        match &t.parts[idx] {
 
            CTP::Void => target.push_str("void"),
 
            CTP::Message => target.push_str("msg"),
 
            CTP::Bool => target.push_str("bool"),
 
            CTP::Bool => target.push_str(KW_TYPE_BOOL_STR),
 
            CTP::UInt8 => target.push_str(KW_TYPE_UINT8_STR),
 
            CTP::UInt16 => target.push_str(KW_TYPE_UINT16_STR),
 
            CTP::UInt32 => target.push_str(KW_TYPE_UINT32_STR),
 
            CTP::UInt64 => target.push_str(KW_TYPE_UINT64_STR),
 
            CTP::SInt8 => target.push_str(KW_TYPE_SINT8_STR),
 
            CTP::SInt16 => target.push_str(KW_TYPE_SINT16_STR),
 
            CTP::SInt32 => target.push_str(KW_TYPE_SINT32_STR),
 
            CTP::SInt64 => target.push_str(KW_TYPE_SINT64_STR),
 
            CTP::Character => target.push_str(KW_TYPE_CHAR_STR),
 
            CTP::String => target.push_str(KW_TYPE_STRING_STR),
 
            CTP::Pointer => target.push('*'),
 
            CTP::Array => {
 
                idx = write_concrete_part(target, heap, def_id, t, idx + 1);
 
                target.push_str("[]");
 
            },
 
            CTP::Slice => {
 
                idx = write_concrete_part(target, heap, def_id, t, idx + 1);
 
                target.push_str("[..]");
 
            }
 
            CTP::Input => {
 
                target.push_str("in<");
 
                idx = write_concrete_part(target, heap, def_id, t, idx + 1);
 
                target.push('>');
 
            },
 
            CTP::Output => {
 
                target.push_str("out<");
 
                idx = write_concrete_part(target, heap, def_id, t, idx + 1);
 
                target.push('>')
 
            },
 
            CTP::Tuple(num_embedded) => {
 
                target.push('(');
 
                for idx_embedded in 0..*num_embedded {
 
                    if idx_embedded != 0 {
 
                        target.push_str(", ");
 
                    }
 
                    idx = write_concrete_part(target, heap, def_id, t, idx + 1);
 
                }
 
                target.push(')');
 
            },
 
            CTP::Instance(definition_id, num_embedded) => {
 
                let identifier = heap[*definition_id].identifier();
 
                target.push_str(identifier.value.as_str());
 
                target.push('<');
 
                for idx_embedded in 0..*num_embedded {
 
                    if idx_embedded != 0 {
 
                        target.push_str(", ");
 
                    }
 
                    idx = write_concrete_part(target, heap, def_id, t, idx + 1);
 
                }
 
                target.push('>');
 
            },
 
            CTP::Function(_, _) => todo!("AST printer for ConcreteTypePart::Function"),
 
            CTP::Component(_, _) => todo!("AST printer for ConcreteTypePart::Component"),
 
        }
 

	
 
        idx + 1
 
    }
 

	
 
    write_concrete_part(target, heap, def_id, t, 0);
 
}
 

	
 
fn write_expression_parent(target: &mut String, parent: &ExpressionParent) {
 
    use ExpressionParent as EP;
 

	
 
    *target = match parent {
 
        EP::None => String::from("None"),
 
        EP::Memory(id) => format!("MemStmt({})", id.0.0.index),
 
        EP::If(id) => format!("IfStmt({})", id.0.index),
 
        EP::While(id) => format!("WhileStmt({})", id.0.index),
 
        EP::Return(id) => format!("ReturnStmt({})", id.0.index),
 
        EP::New(id) => format!("NewStmt({})", id.0.index),
 
        EP::ExpressionStmt(id) => format!("ExprStmt({})", id.0.index),
 
        EP::Expression(id, idx) => format!("Expr({}, {})", id.index, idx)
 
    };
 
}
 
\ No newline at end of file
src/protocol/input_source.rs
Show inline comments
 
use std::fmt;
 
use std::sync::{RwLock, RwLockReadGuard};
 
use std::fmt::Write;
 

	
 
#[derive(Debug, Clone, Copy)]
 
pub struct InputPosition {
 
    pub line: u32,
 
    pub offset: u32,
 
}
 

	
 
impl InputPosition {
 
    pub(crate) fn with_offset(&self, offset: u32) -> Self {
 
        InputPosition { line: self.line, offset: self.offset + offset }
 
    }
 
}
 

	
 
#[derive(Debug, Clone, Copy)]
 
pub struct InputSpan {
 
    pub begin: InputPosition,
 
    pub end: InputPosition,
 
}
 

	
 
impl InputSpan {
 
    // This must only be used if you're sure that the span will not be involved
 
    // in creating an error message.
 
    #[inline]
 
    pub fn new() -> InputSpan {
 
    pub const fn new() -> InputSpan {
 
        InputSpan{ begin: InputPosition{ line: 0, offset: 0 }, end: InputPosition{ line: 0, offset: 0 }}
 
    }
 

	
 
    #[inline]
 
    pub fn from_positions(begin: InputPosition, end: InputPosition) -> Self {
 
        Self { begin, end }
 
    }
 
}
 

	
 
/// Wrapper around source file with optional filename. Ensures that the file is
 
/// only scanned once.
 
pub struct InputSource {
 
    pub(crate) filename: String,
 
    pub(crate) input: Vec<u8>,
 
    // Iteration
 
    line: u32,
 
    offset: usize,
 
    // State tracking
 
    pub(crate) had_error: Option<ParseError>,
 
    // The offset_lookup is built on-demand upon attempting to report an error.
 
    // Only one procedure will actually create the lookup, afterwards only read
 
    // locks will be held.
 
    offset_lookup: RwLock<Vec<u32>>,
 
}
 

	
 
impl InputSource {
 
    pub fn new(filename: String, input: Vec<u8>) -> Self {
 
        Self{
 
            filename,
 
            input,
 
            line: 1,
 
            offset: 0,
 
            had_error: None,
 
            offset_lookup: RwLock::new(Vec::new()),
 
        }
 
    }
 

	
 
    #[inline]
 
    pub fn pos(&self) -> InputPosition {
 
        InputPosition { line: self.line, offset: self.offset as u32 }
 
    }
 

	
 
    pub fn next(&self) -> Option<u8> {
 
        if self.offset < self.input.len() {
 
            Some(self.input[self.offset])
 
        } else {
 
            None
 
        }
 
    }
 

	
 
    pub fn lookahead(&self, offset: usize) -> Option<u8> {
 
        let offset_pos = self.offset + offset;
 
        if offset_pos < self.input.len() {
 
            Some(self.input[offset_pos])
 
        } else {
 
            None
 
        }
 
    }
 

	
 
    #[inline]
 
    pub fn section_at_pos(&self, start: InputPosition, end: InputPosition) -> &[u8] {
 
        &self.input[start.offset as usize..end.offset as usize]
 
    }
 

	
 
    #[inline]
 
    pub fn section_at_span(&self, span: InputSpan) -> &[u8] {
 
        &self.input[span.begin.offset as usize..span.end.offset as usize]
 
    }
 

	
 
    // Consumes the next character. Will check well-formedness of newlines: \r
 
    // must be followed by a \n, because this is used for error reporting. Will
 
    // not check for ascii-ness of the file, better left to a tokenizer.
 
    pub fn consume(&mut self) {
 
        match self.next() {
 
            Some(b'\r') => {
 
                if Some(b'\n') == self.lookahead(1) {
 
                    // Well formed file
 
                    self.offset += 1;
 
                } else {
 
                    // Not a well-formed file, pretend like we can continue
 
                    self.offset += 1;
 
                    self.set_error("Encountered carriage-feed without a following newline");
 
                }
 
            },
 
            Some(b'\n') => {
 
                self.line += 1;
 
                self.offset += 1;
 
            },
 
            Some(_) => {
 
                self.offset += 1;
 
            }
 
            None => {}
 
        }
 

	
 
        // Maybe we actually want to check this in release mode. Then again:
 
        // a 4 gigabyte source file... Really?
 
        debug_assert!(self.offset < u32::max_value() as usize);
 
    }
 

	
 
    fn set_error(&mut self, msg: &str) {
 
        if self.had_error.is_none() {
 
            self.had_error = Some(ParseError::new_error_str_at_pos(self, self.pos(), msg));
 
        }
 
    }
 

	
 
    fn get_lookup(&self) -> RwLockReadGuard<Vec<u32>> {
 
        // Once constructed the lookup always contains one element. We use this
 
        // to see if it is constructed already.
 
        {
 
            let lookup = self.offset_lookup.read().unwrap();
 
            if !lookup.is_empty() {
 
                return lookup;
 
            }
 
        }
 

	
 
        // Lookup was not constructed yet
 
        let mut lookup = self.offset_lookup.write().unwrap();
 
        if !lookup.is_empty() {
 
            // Somebody created it before we had the chance
 
            drop(lookup);
 
            let lookup = self.offset_lookup.read().unwrap();
 
            return lookup;
 
        }
 

	
 
        // Build the line number (!) to offset lookup, so offset by 1. We 
 
        // assume the entire source file is scanned (most common case) for
 
        // preallocation.
 
        lookup.reserve(self.line as usize + 2);
 
        lookup.push(0); // line 0: never used
 
        lookup.push(0); // first line: first character
 

	
 
        for char_idx in 0..self.input.len() {
 
            if self.input[char_idx] == b'\n' {
 
                lookup.push(char_idx as u32 + 1);
 
            }
 
        }
 

	
 
        lookup.push(self.input.len() as u32 + 1); // for lookup_line_end, intentionally adding one character
 

	
 
        // Return created lookup
 
        drop(lookup);
 
        let lookup = self.offset_lookup.read().unwrap();
 
        return lookup;
 
    }
 

	
 
    /// Retrieves offset at which line starts (right after newline)
 
    fn lookup_line_start_offset(&self, line_number: u32) -> u32 {
 
        let lookup = self.get_lookup();
 
        lookup[line_number as usize]
 
    }
 

	
 
    /// Retrieves offset at which line ends (at the newline character or the
 
    /// preceding carriage feed for \r\n-encoded newlines)
 
    fn lookup_line_end_offset(&self, line_number: u32) -> u32 {
 
        let lookup = self.get_lookup();
 
        let offset = lookup[(line_number + 1) as usize] - 1;
 
        let offset_usize = offset as usize;
 

	
 
        // Compensate for newlines and a potential carriage feed. Note that the
 
        // end position is exclusive. So we only need to compensate for a
 
        // "\r\n"
 
        if offset_usize > 0 && offset_usize < self.input.len() && self.input[offset_usize] == b'\n' && self.input[offset_usize - 1] == b'\r' {
 
            offset - 1
 
        } else {
 
            offset
 
        }
 
    }
 
}
 

	
 
#[derive(Debug)]
 
pub enum StatementKind {
 
    Info,
 
    Error
 
}
 

	
 
#[derive(Debug)]
 
pub enum ContextKind {
 
    SingleLine,
 
    MultiLine,
 
}
 

	
 
#[derive(Debug)]
 
pub struct ErrorStatement {
 
    pub(crate) statement_kind: StatementKind,
 
    pub(crate) context_kind: ContextKind,
 
    pub(crate) start_line: u32,
 
    pub(crate) start_column: u32,
 
    pub(crate) end_line: u32,
 
    pub(crate) end_column: u32,
 
    pub(crate) filename: String,
 
    pub(crate) context: String,
 
    pub(crate) message: String,
src/protocol/mod.rs
Show inline comments
 
mod arena;
 
pub(crate) mod eval;
 
pub(crate) mod input_source;
 
mod parser;
 
#[cfg(test)] mod tests;
 

	
 
pub(crate) mod ast;
 
pub(crate) mod ast_printer;
 

	
 
use std::sync::Mutex;
 

	
 
use crate::collections::{StringPool, StringRef};
 
use crate::protocol::ast::*;
 
use crate::protocol::eval::*;
 
use crate::protocol::input_source::*;
 
use crate::protocol::parser::*;
 
use crate::protocol::type_table::*;
 

	
 
pub use parser::type_table::TypeId;
 

	
 
/// A protocol description module
 
pub struct Module {
 
    pub(crate) source: InputSource,
 
    pub(crate) root_id: RootId,
 
    pub(crate) name: Option<StringRef<'static>>,
 
}
 
/// Description of a protocol object, used to configure new connectors.
 
#[repr(C)]
 
pub struct ProtocolDescription {
 
    pub(crate) modules: Vec<Module>,
 
    pub(crate) heap: Heap,
 
    pub(crate) types: TypeTable,
 
    pub(crate) pool: Mutex<StringPool>,
 
}
 
#[derive(Debug, Clone)]
 
pub(crate) struct ComponentState {
 
    pub(crate) prompt: Prompt,
 
}
 

	
 
#[derive(Debug)]
 
pub enum ComponentCreationError {
 
    ModuleDoesntExist,
 
    DefinitionDoesntExist,
 
    DefinitionNotComponent,
 
    InvalidNumArguments,
 
    InvalidArgumentType(usize),
 
    UnownedPort,
 
    InSync,
 
}
 

	
 
impl ProtocolDescription {
 
    pub fn parse(buffer: &[u8]) -> Result<Self, String> {
 
        let source = InputSource::new(String::new(), Vec::from(buffer));
 
        let mut parser = Parser::new();
 
        parser.feed(source).expect("failed to feed source");
 
        
 
        if let Err(err) = parser.parse() {
 
            println!("ERROR:\n{}", err);
 
            return Err(format!("{}", err))
 
        }
 

	
 
        debug_assert_eq!(parser.modules.len(), 1, "only supporting one module here for now");
 
        let modules: Vec<Module> = parser.modules.into_iter()
 
            .map(|module| Module{
 
                source: module.source,
 
                root_id: module.root_id,
 
                name: module.name.map(|(_, name)| name)
 
            })
 
            .collect();
 

	
 
        return Ok(ProtocolDescription {
 
            modules,
 
            heap: parser.heap,
 
            types: parser.type_table,
 
            pool: Mutex::new(parser.string_pool),
 
        });
 
    }
 

	
 
    pub(crate) fn new_component(
 
        &self, module_name: &[u8], identifier: &[u8], arguments: ValueGroup
 
    ) -> Result<Prompt, ComponentCreationError> {
 
        // Find the module in which the definition can be found
 
        let module_root = self.lookup_module_root(module_name);
 
        if module_root.is_none() {
 
            return Err(ComponentCreationError::ModuleDoesntExist);
 
        }
 
        let module_root = module_root.unwrap();
 

	
 
        let root = &self.heap[module_root];
 
        let definition_id = root.get_definition_ident(&self.heap, identifier);
 
        if definition_id.is_none() {
 
            return Err(ComponentCreationError::DefinitionDoesntExist);
 
        }
 
        let definition_id = definition_id.unwrap();
 

	
 
        let ast_definition = &self.heap[definition_id];
 
        if !ast_definition.is_component() {
 
            return Err(ComponentCreationError::DefinitionNotComponent);
 
        }
 

	
 
        // Make sure that the types of the provided value group matches that of
 
        // the expected types.
 
        let ast_definition = ast_definition.as_component();
 
        if !ast_definition.poly_vars.is_empty() {
 
            return Err(ComponentCreationError::DefinitionNotComponent);
 
        }
 

	
 
        // - check number of arguments by retrieving the one instantiated
 
        //   monomorph
 
        let concrete_type = ConcreteType{ parts: vec![ConcreteTypePart::Component(definition_id, 0)] };
 
        let mono_index = self.types.get_procedure_monomorph_type_id(&definition_id, &concrete_type.parts).unwrap();
 
        let mono_type = self.types.get_procedure_monomorph(mono_index);
 
        if mono_type.arg_types.len() != arguments.values.len() {
 
            return Err(ComponentCreationError::InvalidNumArguments);
 
        }
 

	
 
        // - for each argument try to make sure the types match
 
        for arg_idx in 0..arguments.values.len() {
 
            let expected_type = &mono_type.arg_types[arg_idx];
 
            let provided_value = &arguments.values[arg_idx];
 
            if !self.verify_same_type(expected_type, 0, &arguments, provided_value) {
 
                return Err(ComponentCreationError::InvalidArgumentType(arg_idx));
 
            }
 
        }
 

	
 
        // By now we're sure that all of the arguments are correct. So create
 
        // the connector.
 
        return Ok(Prompt::new(&self.types, &self.heap, definition_id, mono_index, arguments));
 
    }
 

	
 
    fn lookup_module_root(&self, module_name: &[u8]) -> Option<RootId> {
 
        for module in self.modules.iter() {
 
            match &module.name {
 
                Some(name) => if name.as_bytes() == module_name {
 
                    return Some(module.root_id);
 
                },
 
                None => if module_name.is_empty() {
 
                    return Some(module.root_id);
 
                }
 
            }
 
        }
 

	
 
        return None;
 
    }
 

	
 
    fn verify_same_type(&self, expected: &ConcreteType, expected_idx: usize, arguments: &ValueGroup, argument: &Value) -> bool {
 
        use ConcreteTypePart as CTP;
 

	
 
        match &expected.parts[expected_idx] {
 
            CTP::Void | CTP::Message | CTP::Slice | CTP::Function(_, _) | CTP::Component(_, _) => unreachable!(),
 
            CTP::Void | CTP::Message | CTP::Slice | CTP::Pointer | CTP::Function(_, _) | CTP::Component(_, _) => unreachable!(),
 
            CTP::Bool => if let Value::Bool(_) = argument { true } else { false },
 
            CTP::UInt8 => if let Value::UInt8(_) = argument { true } else { false },
 
            CTP::UInt16 => if let Value::UInt16(_) = argument { true } else { false },
 
            CTP::UInt32 => if let Value::UInt32(_) = argument { true } else { false },
 
            CTP::UInt64 => if let Value::UInt64(_) = argument { true } else { false },
 
            CTP::SInt8 => if let Value::SInt8(_) = argument { true } else { false },
 
            CTP::SInt16 => if let Value::SInt16(_) = argument { true } else { false },
 
            CTP::SInt32 => if let Value::SInt32(_) = argument { true } else { false },
 
            CTP::SInt64 => if let Value::SInt64(_) = argument { true } else { false },
 
            CTP::Character => if let Value::Char(_) = argument { true } else { false },
 
            CTP::String => {
 
                // Match outer string type and embedded character types
 
                if let Value::String(heap_pos) = argument {
 
                    for element in &arguments.regions[*heap_pos as usize] {
 
                        if let Value::Char(_) = element {} else {
 
                            return false;
 
                        }
 
                    }
 
                } else {
 
                    return false;
 
                }
 

	
 
                return true;
 
            },
 
            CTP::Array => {
 
                if let Value::Array(heap_pos) = argument {
 
                    let heap_pos = *heap_pos;
 
                    for element in &arguments.regions[heap_pos as usize] {
 
                        if !self.verify_same_type(expected, expected_idx + 1, arguments, element) {
 
                            return false;
 
                        }
 
                    }
 
                    return true;
 
                } else {
 
                    return false;
 
                }
 
            },
 
            CTP::Input => if let Value::Input(_) = argument { true } else { false },
 
            CTP::Output => if let Value::Output(_) = argument { true } else { false },
 
            CTP::Tuple(_) => todo!("implement full type checking on user-supplied arguments"),
 
            CTP::Instance(definition_id, _num_embedded) => {
 
                let definition = self.types.get_base_definition(definition_id).unwrap();
 
                match &definition.definition {
 
                    DefinedTypeVariant::Enum(definition) => {
 
                        if let Value::Enum(variant_value) = argument {
 
                            let is_valid = definition.variants.iter()
 
                                .any(|v| v.value == *variant_value);
 
                            return is_valid;
 
                        }
 
                    },
 
                    _ => todo!("implement full type checking on user-supplied arguments"),
 
                }
 

	
 
                return false;
 
            },
 
        }
 
    }
 
}
 

	
 
pub trait RunContext {
 
    fn performed_put(&mut self, port: PortId) -> bool;
 
    fn performed_get(&mut self, port: PortId) -> Option<ValueGroup>; // None if still waiting on message
 
    fn fires(&mut self, port: PortId) -> Option<Value>; // None if not yet branched
 
    fn performed_fork(&mut self) -> Option<bool>; // None if not yet forked
 
    fn created_channel(&mut self) -> Option<(Value, Value)>; // None if not yet prepared
 
}
 

	
 
pub struct ProtocolDescriptionBuilder {
 
    parser: Parser,
 
}
 

	
 
impl ProtocolDescriptionBuilder {
 
    pub fn new() -> Self {
 
        return Self{
 
            parser: Parser::new(),
 
        }
 
    }
 

	
 
    pub fn add(&mut self, filename: String, buffer: Vec<u8>) -> Result<(), ParseError> {
 
        let input = InputSource::new(filename, buffer);
 
        self.parser.feed(input)?;
 

	
 
        return Ok(())
 
    }
 

	
 
    pub fn compile(mut self) -> Result<ProtocolDescription, ParseError> {
 
        self.parser.parse()?;
 

	
 
        let modules: Vec<Module> = self.parser.modules.into_iter()
 
            .map(|module| Module{
 
                source: module.source,
 
                root_id: module.root_id,
 
                name: module.name.map(|(_, name)| name)
 
            })
 
            .collect();
 

	
 
        return Ok(ProtocolDescription {
 
            modules,
 
            heap: self.parser.heap,
 
            types: self.parser.type_table,
 
            pool: Mutex::new(self.parser.string_pool),
 
        });
 
    }
 
}
src/protocol/parser/mod.rs
Show inline comments
 
pub(crate) mod symbol_table;
 
pub(crate) mod type_table;
 
pub(crate) mod tokens;
 
pub(crate) mod token_parsing;
 
pub(crate) mod pass_tokenizer;
 
pub(crate) mod pass_symbols;
 
pub(crate) mod pass_imports;
 
pub(crate) mod pass_definitions;
 
pub(crate) mod pass_definitions_types;
 
pub(crate) mod pass_validation_linking;
 
pub(crate) mod pass_rewriting;
 
pub(crate) mod pass_typing;
 
pub(crate) mod pass_stack_size;
 
mod visitor;
 

	
 
use tokens::*;
 
use crate::collections::*;
 
use visitor::Visitor;
 
use pass_tokenizer::PassTokenizer;
 
use pass_symbols::PassSymbols;
 
use pass_imports::PassImport;
 
use pass_definitions::PassDefinitions;
 
use pass_validation_linking::PassValidationLinking;
 
use pass_typing::{PassTyping, ResolveQueue};
 
use pass_rewriting::PassRewriting;
 
use pass_stack_size::PassStackSize;
 
use symbol_table::*;
 
use type_table::TypeTable;
 
use type_table::*;
 

	
 
use crate::protocol::ast::*;
 
use crate::protocol::input_source::*;
 

	
 
use crate::protocol::ast_printer::ASTWriter;
 
use crate::protocol::parser::type_table::PolymorphicVariable;
 

	
 
#[derive(Debug, PartialEq, Eq, PartialOrd, Ord)]
 
pub enum ModuleCompilationPhase {
 
    Tokenized,              // source is tokenized
 
    SymbolsScanned,         // all definitions are linked to their type class
 
    ImportsResolved,        // all imports are added to the symbol table
 
    DefinitionsParsed,      // produced the AST for the entire module
 
    TypesAddedToTable,      // added all definitions to the type table
 
    ValidatedAndLinked,     // AST is traversed and has linked the required AST nodes
 
    Typed,                  // Type inference and checking has been performed
 
    Rewritten,              // Special AST nodes are rewritten into regular AST nodes
 
    // When we continue with the compiler:
 
    // StackSize
 
}
 

	
 
pub struct Module {
 
    // Buffers
 
    pub source: InputSource,
 
    pub tokens: TokenBuffer,
 
    // Identifiers
 
    pub root_id: RootId,
 
    pub name: Option<(PragmaId, StringRef<'static>)>,
 
    pub version: Option<(PragmaId, i64)>,
 
    pub phase: ModuleCompilationPhase,
 
}
 

	
 
// TODO: This is kind of wrong. Because when we're producing bytecode we would
 
//       like the bytecode itself to not have the notion of the size of a pointer
 
//       type. But until I figure out what we do want I'll just set everything
 
//       to a 64-bit architecture.
 
pub struct TargetArch {
 
    pub array_size_alignment: (usize, usize),
 
    pub slice_size_alignment: (usize, usize),
 
    pub string_size_alignment: (usize, usize),
 
    pub port_size_alignment: (usize, usize),
 
    pub pointer_size_alignment: (usize, usize),
 
    pub void_type_id: TypeId,
 
    pub message_type_id: TypeId,
 
    pub bool_type_id: TypeId,
 
    pub uint8_type_id: TypeId,
 
    pub uint16_type_id: TypeId,
 
    pub uint32_type_id: TypeId,
 
    pub uint64_type_id: TypeId,
 
    pub sint8_type_id: TypeId,
 
    pub sint16_type_id: TypeId,
 
    pub sint32_type_id: TypeId,
 
    pub sint64_type_id: TypeId,
 
    pub char_type_id: TypeId,
 
    pub string_type_id: TypeId,
 
    pub array_type_id: TypeId,
 
    pub slice_type_id: TypeId,
 
    pub input_type_id: TypeId,
 
    pub output_type_id: TypeId,
 
    pub pointer_type_id: TypeId,
 
}
 

	
 
impl TargetArch {
 
    fn new() -> Self {
 
        return Self{
 
            void_type_id: TypeId::new_invalid(),
 
            bool_type_id: TypeId::new_invalid(),
 
            message_type_id: TypeId::new_invalid(),
 
            uint8_type_id: TypeId::new_invalid(),
 
            uint16_type_id: TypeId::new_invalid(),
 
            uint32_type_id: TypeId::new_invalid(),
 
            uint64_type_id: TypeId::new_invalid(),
 
            sint8_type_id: TypeId::new_invalid(),
 
            sint16_type_id: TypeId::new_invalid(),
 
            sint32_type_id: TypeId::new_invalid(),
 
            sint64_type_id: TypeId::new_invalid(),
 
            char_type_id: TypeId::new_invalid(),
 
            string_type_id: TypeId::new_invalid(),
 
            array_type_id: TypeId::new_invalid(),
 
            slice_type_id: TypeId::new_invalid(),
 
            input_type_id: TypeId::new_invalid(),
 
            output_type_id: TypeId::new_invalid(),
 
            pointer_type_id: TypeId::new_invalid(),
 
        }
 
    }
 
}
 

	
 
pub struct PassCtx<'a> {
 
    heap: &'a mut Heap,
 
    symbols: &'a mut SymbolTable,
 
    pool: &'a mut StringPool,
 
    arch: &'a TargetArch,
 
}
 

	
 
pub struct Parser {
 
    // Storage of all information created/gathered during compilation.
 
    pub(crate) heap: Heap,
 
    pub(crate) string_pool: StringPool, // Do not deallocate, holds all strings
 
    pub(crate) modules: Vec<Module>,
 
    pub(crate) symbol_table: SymbolTable,
 
    pub(crate) type_table: TypeTable,
 
    // Compiler passes, used as little state machine that keep their memory
 
    // around.
 
    pass_tokenizer: PassTokenizer,
 
    pass_symbols: PassSymbols,
 
    pass_import: PassImport,
 
    pass_definitions: PassDefinitions,
 
    pass_validation: PassValidationLinking,
 
    pass_typing: PassTyping,
 
    pass_rewriting: PassRewriting,
 
    pass_stack_size: PassStackSize,
 
    // Compiler options
 
    pub write_ast_to: Option<String>,
 
    pub(crate) arch: TargetArch,
 
}
 

	
 
impl Parser {
 
    pub fn new() -> Self {
 
        let mut parser = Parser{
 
            heap: Heap::new(),
 
            string_pool: StringPool::new(),
 
            modules: Vec::new(),
 
            symbol_table: SymbolTable::new(),
 
            type_table: TypeTable::new(),
 
            pass_tokenizer: PassTokenizer::new(),
 
            pass_symbols: PassSymbols::new(),
 
            pass_import: PassImport::new(),
 
            pass_definitions: PassDefinitions::new(),
 
            pass_validation: PassValidationLinking::new(),
 
            pass_typing: PassTyping::new(),
 
            pass_rewriting: PassRewriting::new(),
 
            pass_stack_size: PassStackSize::new(),
 
            write_ast_to: None,
 
            arch: TargetArch {
 
                array_size_alignment: (3*8, 8), // pointer, length, capacity
 
                slice_size_alignment: (2*8, 8), // pointer, length
 
                string_size_alignment: (3*8, 8), // pointer, length, capacity
 
                port_size_alignment: (3*4, 4), // two u32s: connector + port ID
 
                pointer_size_alignment: (8, 8),
 
            }
 
            arch: TargetArch::new(),
 
        };
 

	
 
        parser.symbol_table.insert_scope(None, SymbolScope::Global);
 

	
 
        // Insert builtin types
 
        // TODO: At some point use correct values for size/alignment
 
        parser.arch.void_type_id    = insert_builtin_type(&mut parser.type_table, vec![ConcreteTypePart::Void], false, 0, 1);
 
        parser.arch.message_type_id = insert_builtin_type(&mut parser.type_table, vec![ConcreteTypePart::Message], false, 24, 8);
 
        parser.arch.bool_type_id    = insert_builtin_type(&mut parser.type_table, vec![ConcreteTypePart::Bool], false, 1, 1);
 
        parser.arch.uint8_type_id   = insert_builtin_type(&mut parser.type_table, vec![ConcreteTypePart::UInt8], false, 1, 1);
 
        parser.arch.uint16_type_id  = insert_builtin_type(&mut parser.type_table, vec![ConcreteTypePart::UInt16], false, 2, 2);
 
        parser.arch.uint32_type_id  = insert_builtin_type(&mut parser.type_table, vec![ConcreteTypePart::UInt32], false, 4, 4);
 
        parser.arch.uint64_type_id  = insert_builtin_type(&mut parser.type_table, vec![ConcreteTypePart::UInt64], false, 8, 8);
 
        parser.arch.sint8_type_id   = insert_builtin_type(&mut parser.type_table, vec![ConcreteTypePart::SInt8], false, 1, 1);
 
        parser.arch.sint16_type_id  = insert_builtin_type(&mut parser.type_table, vec![ConcreteTypePart::SInt16], false, 2, 2);
 
        parser.arch.sint32_type_id  = insert_builtin_type(&mut parser.type_table, vec![ConcreteTypePart::SInt32], false, 4, 4);
 
        parser.arch.sint64_type_id  = insert_builtin_type(&mut parser.type_table, vec![ConcreteTypePart::SInt64], false, 8, 8);
 
        parser.arch.char_type_id    = insert_builtin_type(&mut parser.type_table, vec![ConcreteTypePart::Character], false, 4, 4);
 
        parser.arch.string_type_id  = insert_builtin_type(&mut parser.type_table, vec![ConcreteTypePart::String], false, 24, 8);
 
        parser.arch.array_type_id   = insert_builtin_type(&mut parser.type_table, vec![ConcreteTypePart::Array, ConcreteTypePart::Void], true, 24, 8);
 
        parser.arch.slice_type_id   = insert_builtin_type(&mut parser.type_table, vec![ConcreteTypePart::Slice, ConcreteTypePart::Void], true, 16, 4);
 
        parser.arch.input_type_id   = insert_builtin_type(&mut parser.type_table, vec![ConcreteTypePart::Input, ConcreteTypePart::Void], true, 8, 8);
 
        parser.arch.output_type_id  = insert_builtin_type(&mut parser.type_table, vec![ConcreteTypePart::Output, ConcreteTypePart::Void], true, 8, 8);
 
        parser.arch.pointer_type_id = insert_builtin_type(&mut parser.type_table, vec![ConcreteTypePart::Pointer, ConcreteTypePart::Void], true, 8, 8);
 

	
 
        // Insert builtin functions
 
        fn quick_type(variants: &[ParserTypeVariant]) -> ParserType {
 
            let mut t = ParserType{ elements: Vec::with_capacity(variants.len()), full_span: InputSpan::new() };
 
            for variant in variants {
 
                t.elements.push(ParserTypeElement{ element_span: InputSpan::new(), variant: variant.clone() });
 
            }
 
            t
 
        }
 

	
 
        use ParserTypeVariant as PTV;
 
        insert_builtin_function(&mut parser, "get", &["T"], |id| (
 
            vec![
 
                ("input", quick_type(&[PTV::Input, PTV::PolymorphicArgument(id.upcast(), 0)]))
 
            ],
 
            quick_type(&[PTV::PolymorphicArgument(id.upcast(), 0)])
 
        ));
 
        insert_builtin_function(&mut parser, "put", &["T"], |id| (
 
            vec![
 
                ("output", quick_type(&[PTV::Output, PTV::PolymorphicArgument(id.upcast(), 0)])),
 
                ("value", quick_type(&[PTV::PolymorphicArgument(id.upcast(), 0)])),
 
            ],
 
            quick_type(&[PTV::Void])
 
        ));
 
        insert_builtin_function(&mut parser, "fires", &["T"], |id| (
 
            vec![
 
                ("port", quick_type(&[PTV::InputOrOutput, PTV::PolymorphicArgument(id.upcast(), 0)]))
 
            ],
 
            quick_type(&[PTV::Bool])
 
        ));
 
        insert_builtin_function(&mut parser, "create", &["T"], |id| (
 
            vec![
 
                ("length", quick_type(&[PTV::IntegerLike]))
 
            ],
 
            quick_type(&[PTV::ArrayLike, PTV::PolymorphicArgument(id.upcast(), 0)])
 
        ));
 
        insert_builtin_function(&mut parser, "length", &["T"], |id| (
 
            vec![
 
                ("array", quick_type(&[PTV::ArrayLike, PTV::PolymorphicArgument(id.upcast(), 0)]))
 
            ],
 
            quick_type(&[PTV::UInt32]) // TODO: @PtrInt
 
        ));
 
        insert_builtin_function(&mut parser, "assert", &[], |_id| (
 
            vec![
 
                ("condition", quick_type(&[PTV::Bool])),
 
            ],
 
            quick_type(&[PTV::Void])
 
        ));
 
        insert_builtin_function(&mut parser, "print", &[], |_id| (
 
            vec![
 
                ("message", quick_type(&[PTV::String])),
 
            ],
 
            quick_type(&[PTV::Void])
 
        ));
 

	
 
        parser
 
    }
 

	
 
    pub fn feed(&mut self, mut source: InputSource) -> Result<(), ParseError> {
 
        let mut token_buffer = TokenBuffer::new();
 
        self.pass_tokenizer.tokenize(&mut source, &mut token_buffer)?;
 

	
 
        let module = Module{
 
            source,
 
            tokens: token_buffer,
 
            root_id: RootId::new_invalid(),
 
            name: None,
 
            version: None,
 
            phase: ModuleCompilationPhase::Tokenized,
 
        };
 
        self.modules.push(module);
 

	
 
        Ok(())
 
    }
 

	
 
    pub fn parse(&mut self) -> Result<(), ParseError> {
 
        let mut pass_ctx = PassCtx{
 
            heap: &mut self.heap,
 
            symbols: &mut self.symbol_table,
 
            pool: &mut self.string_pool,
 
            arch: &self.arch,
 
        };
 

	
 
        // Advance all modules to the phase where all symbols are scanned
 
        for module_idx in 0..self.modules.len() {
 
            self.pass_symbols.parse(&mut self.modules, module_idx, &mut pass_ctx)?;
 
        }
 

	
 
        // With all symbols scanned, perform further compilation until we can
 
        // add all base types to the type table.
 
        for module_idx in 0..self.modules.len() {
 
            self.pass_import.parse(&mut self.modules, module_idx, &mut pass_ctx)?;
 
            self.pass_definitions.parse(&mut self.modules, module_idx, &mut pass_ctx)?;
 
        }
 

	
 
        // Add every known type to the type table
 
        self.type_table.build_base_types(&mut self.modules, &mut pass_ctx)?;
 

	
 
        // Continue compilation with the remaining phases now that the types
 
        // are all in the type table
 
        for module_idx in 0..self.modules.len() {
 
            let mut ctx = visitor::Ctx{
 
                heap: &mut self.heap,
 
                modules: &mut self.modules,
 
                module_idx,
 
                symbols: &mut self.symbol_table,
 
                types: &mut self.type_table,
 
                arch: &self.arch,
 
            };
 
            self.pass_validation.visit_module(&mut ctx)?;
 
        }
 

	
 
        // Perform typechecking on all modules
 
        let mut queue = ResolveQueue::new();
 
        for module_idx in 0..self.modules.len() {
 
            let mut ctx = visitor::Ctx{
 
                heap: &mut self.heap,
 
                modules: &mut self.modules,
 
                module_idx,
 
                symbols: &mut self.symbol_table,
 
                types: &mut self.type_table,
 
                arch: &self.arch,
 
            };
 
            PassTyping::queue_module_definitions(&mut ctx, &mut queue);
 
        };
 
        while !queue.is_empty() {
 
            let top = queue.pop().unwrap();
 
            let mut ctx = visitor::Ctx{
 
                heap: &mut self.heap,
 
                modules: &mut self.modules,
 
                module_idx: top.root_id.index as usize,
 
                symbols: &mut self.symbol_table,
 
                types: &mut self.type_table,
 
                arch: &self.arch,
 
            };
 
            self.pass_typing.handle_module_definition(&mut ctx, &mut queue, top)?;
 
        }
 

	
 
        // Rewrite nodes in tree, then prepare for execution of code
 
        for module_idx in 0..self.modules.len() {
 
            self.modules[module_idx].phase = ModuleCompilationPhase::Typed;
 
            let mut ctx = visitor::Ctx{
 
                heap: &mut self.heap,
 
                modules: &mut self.modules,
 
                module_idx,
 
                symbols: &mut self.symbol_table,
 
                types: &mut self.type_table,
 
                arch: &self.arch,
 
            };
 
            self.pass_rewriting.visit_module(&mut ctx);
 
            self.pass_stack_size.visit_module(&mut ctx);
 
        }
 

	
 
        // Write out desired information
 
        if let Some(filename) = &self.write_ast_to {
 
            let mut writer = ASTWriter::new();
 
            let mut file = std::fs::File::create(std::path::Path::new(filename)).unwrap();
 
            writer.write_ast(&mut file, &self.heap);
 
        }
 

	
 
        Ok(())
 
    }
 
}
 

	
 
fn insert_builtin_type(type_table: &mut TypeTable, parts: Vec<ConcreteTypePart>, has_poly_var: bool, size: usize, alignment: usize) -> TypeId {
 
    const POLY_VARS: [PolymorphicVariable; 1] = [PolymorphicVariable{
 
        identifier: Identifier::new_empty(InputSpan::new()),
 
        is_in_use: false,
 
    }];
 

	
 
    let concrete_type = ConcreteType{ parts };
 
    let poly_var = if has_poly_var {
 
        POLY_VARS.as_slice()
 
    } else {
 
        &[]
 
    };
 

	
 
    return type_table.add_builtin_type(concrete_type, poly_var, size, alignment);
 
}
 

	
 
// Note: args and return type need to be a function because we need to know the function ID.
 
fn insert_builtin_function<T: Fn(FunctionDefinitionId) -> (Vec<(&'static str, ParserType)>, ParserType)> (
 
    p: &mut Parser, func_name: &str, polymorphic: &[&str], arg_and_return_fn: T) {
 

	
 
    p: &mut Parser, func_name: &str, polymorphic: &[&str], arg_and_return_fn: T
 
) {
 
    let mut poly_vars = Vec::with_capacity(polymorphic.len());
 
    for poly_var in polymorphic {
 
        poly_vars.push(Identifier{ span: InputSpan::new(), value: p.string_pool.intern(poly_var.as_bytes()) });
 
    }
 

	
 
    let func_ident_ref = p.string_pool.intern(func_name.as_bytes());
 
    let func_id = p.heap.alloc_function_definition(|this| FunctionDefinition{
 
        this,
 
        defined_in: RootId::new_invalid(),
 
        builtin: true,
 
        span: InputSpan::new(),
 
        identifier: Identifier{ span: InputSpan::new(), value: func_ident_ref.clone() },
 
        poly_vars,
 
        return_type: ParserType{ elements: Vec::new(), full_span: InputSpan::new() },
 
        parameters: Vec::new(),
 
        scope: ScopeId::new_invalid(),
 
        body: BlockStatementId::new_invalid(),
 
        num_expressions_in_body: -1,
 
    });
 

	
 
    let (arguments, return_type) = arg_and_return_fn(func_id);
 

	
 
    let mut parameters = Vec::with_capacity(arguments.len());
 
    for (arg_name, arg_type) in arguments {
 
        let identifier = Identifier{ span: InputSpan::new(), value: p.string_pool.intern(arg_name.as_bytes()) };
 
        let param_id = p.heap.alloc_variable(|this| Variable{
 
            this,
 
            kind: VariableKind::Parameter,
 
            parser_type: arg_type.clone(),
 
            identifier,
 
            relative_pos_in_parent: 0,
 
            unique_id_in_scope: 0
 
        });
 
        parameters.push(param_id);
 
    }
 

	
 
    let func = &mut p.heap[func_id];
 
    func.parameters = parameters;
 
    func.return_type = return_type;
 

	
 
    p.symbol_table.insert_symbol(SymbolScope::Global, Symbol{
 
        name: func_ident_ref,
 
        variant: SymbolVariant::Definition(SymbolDefinition{
 
            defined_in_module: RootId::new_invalid(),
 
            defined_in_scope: SymbolScope::Global,
 
            definition_span: InputSpan::new(),
 
            identifier_span: InputSpan::new(),
 
            imported_at: None,
 
            class: DefinitionClass::Function,
 
            definition_id: func_id.upcast(),
 
        })
 
    }).unwrap();
 
}
 
\ No newline at end of file
src/protocol/parser/pass_typing.rs
Show inline comments
 
@@ -3594,384 +3594,385 @@ impl PassTyping {
 
            let inference_type = self.determine_inference_type_from_parser_type_elements(&embedded_parser_type.elements, false);
 
            embedded.push(inference_type);
 
        }
 

	
 
        // Handle the type of the union itself
 
        let parts_reserved = 1 + poly_args.len() + total_num_poly_parts;
 
        let mut parts = Vec::with_capacity(parts_reserved);
 
        parts.push(ITP::Instance(definition_id, poly_args.len() as u32));
 
        let mut union_type_done = true;
 
        for (poly_var_idx, poly_var) in poly_args.iter().enumerate() {
 
            if !poly_var.is_done { union_type_done = false; }
 

	
 
            parts.push(ITP::Marker(poly_var_idx as u32));
 
            parts.extend(poly_var.parts.iter().cloned());
 
        }
 

	
 
        debug_assert_eq!(parts_reserved, parts.len());
 
        let union_type = InferenceType::new(!poly_args.is_empty(), union_type_done, parts);
 

	
 
        self.extra_data[extra_data_idx as usize] = ExtraData{
 
            expr_id: lit_id.upcast(),
 
            definition_id: literal.definition,
 
            poly_vars: poly_args,
 
            embedded,
 
            returned: union_type
 
        };
 
    }
 

	
 
    /// Inserts the extra polymorphic data struct. Assumes that the select
 
    /// expression's referenced (definition_id, field_idx) has been resolved.
 
    fn insert_initial_select_polymorph_data(
 
        &mut self, ctx: &Ctx, select_id: SelectExpressionId, struct_def_id: DefinitionId
 
    ) {
 
        use InferenceTypePart as ITP;
 

	
 
        // Retrieve relevant data
 
        let expr = &ctx.heap[select_id];
 
        let expr_type = &self.expr_types[expr.unique_id_in_definition as usize];
 
        let field_idx = expr_type.field_or_monomorph_idx as usize;
 
        let extra_data_idx = expr_type.extra_data_idx; // TODO: @Temp
 
        debug_assert!(extra_data_idx != -1, "initial select polymorph data, but no preallocated ExtraData");
 

	
 
        let definition = ctx.heap[struct_def_id].as_struct();
 

	
 
        // Generate initial polyvar types and struct type
 
        // TODO: @Performance: we can immediately set the polyvars of the subject's struct type
 
        let num_poly_vars = definition.poly_vars.len();
 
        let mut poly_vars = Vec::with_capacity(num_poly_vars);
 
        let struct_parts_reserved = 1 + 2 * num_poly_vars;
 
        let mut struct_parts = Vec::with_capacity(struct_parts_reserved);
 
        struct_parts.push(ITP::Instance(struct_def_id, num_poly_vars as u32));
 

	
 
        for poly_idx in 0..num_poly_vars {
 
            poly_vars.push(InferenceType::new(true, false, vec![
 
                ITP::Marker(poly_idx as u32), ITP::Unknown,
 
            ]));
 
            struct_parts.push(ITP::Marker(poly_idx as u32));
 
            struct_parts.push(ITP::Unknown);
 
        }
 
        debug_assert_eq!(struct_parts.len(), struct_parts_reserved);
 

	
 
        // Generate initial field type
 
        let field_type = self.determine_inference_type_from_parser_type_elements(&definition.fields[field_idx].parser_type.elements, false);
 
        self.extra_data[extra_data_idx as usize] = ExtraData{
 
            expr_id: select_id.upcast(),
 
            definition_id: struct_def_id,
 
            poly_vars,
 
            embedded: vec![InferenceType::new(num_poly_vars != 0, num_poly_vars == 0, struct_parts)],
 
            returned: field_type
 
        };
 
    }
 

	
 
    /// Determines the initial InferenceType from the provided ParserType. This
 
    /// may be called with two kinds of intentions:
 
    /// 1. To resolve a ParserType within the body of a function, or on
 
    ///     polymorphic arguments to calls/instantiations within that body. This
 
    ///     means that the polymorphic variables are known and can be replaced
 
    ///     with the monomorph we're instantiating.
 
    /// 2. To resolve a ParserType on a called function's definition or on
 
    ///     an instantiated datatype's members. This means that the polymorphic
 
    ///     arguments inside those ParserTypes refer to the polymorphic
 
    ///     variables in the called/instantiated type's definition.
 
    /// In the second case we place InferenceTypePart::Marker instances such
 
    /// that we can perform type inference on the polymorphic variables.
 
    fn determine_inference_type_from_parser_type_elements(
 
        &mut self, elements: &[ParserTypeElement],
 
        use_definitions_known_poly_args: bool
 
    ) -> InferenceType {
 
        use ParserTypeVariant as PTV;
 
        use InferenceTypePart as ITP;
 

	
 
        let mut infer_type = Vec::with_capacity(elements.len());
 
        let mut has_inferred = false;
 
        let mut has_markers = false;
 

	
 
        for element in elements {
 
            match &element.variant {
 
                // Compiler-only types
 
                PTV::Void => { infer_type.push(ITP::Void); },
 
                PTV::InputOrOutput => { infer_type.push(ITP::PortLike); has_inferred = true },
 
                PTV::ArrayLike => { infer_type.push(ITP::ArrayLike); has_inferred = true },
 
                PTV::IntegerLike => { infer_type.push(ITP::IntegerLike); has_inferred = true },
 
                // Builtins
 
                PTV::Message => {
 
                    // TODO: @types Remove the Message -> Byte hack at some point...
 
                    infer_type.push(ITP::Message);
 
                    infer_type.push(ITP::UInt8);
 
                },
 
                PTV::Bool => { infer_type.push(ITP::Bool); },
 
                PTV::UInt8 => { infer_type.push(ITP::UInt8); },
 
                PTV::UInt16 => { infer_type.push(ITP::UInt16); },
 
                PTV::UInt32 => { infer_type.push(ITP::UInt32); },
 
                PTV::UInt64 => { infer_type.push(ITP::UInt64); },
 
                PTV::SInt8 => { infer_type.push(ITP::SInt8); },
 
                PTV::SInt16 => { infer_type.push(ITP::SInt16); },
 
                PTV::SInt32 => { infer_type.push(ITP::SInt32); },
 
                PTV::SInt64 => { infer_type.push(ITP::SInt64); },
 
                PTV::Character => { infer_type.push(ITP::Character); },
 
                PTV::String => {
 
                    infer_type.push(ITP::String);
 
                    infer_type.push(ITP::Character);
 
                },
 
                // Special markers
 
                PTV::IntegerLiteral => { unreachable!("integer literal type on variable type"); },
 
                PTV::Inferred => {
 
                    infer_type.push(ITP::Unknown);
 
                    has_inferred = true;
 
                },
 
                // With nested types
 
                PTV::Array => { infer_type.push(ITP::Array); },
 
                PTV::Input => { infer_type.push(ITP::Input); },
 
                PTV::Output => { infer_type.push(ITP::Output); },
 
                PTV::Tuple(num_embedded) => { infer_type.push(ITP::Tuple(*num_embedded)); },
 
                PTV::PolymorphicArgument(belongs_to_definition, poly_arg_idx) => {
 
                    let poly_arg_idx = *poly_arg_idx;
 
                    if use_definitions_known_poly_args {
 
                        // Refers to polymorphic argument on procedure we're currently processing.
 
                        // This argument is already known.
 
                        debug_assert_eq!(*belongs_to_definition, self.definition_type.definition_id());
 
                        debug_assert!((poly_arg_idx as usize) < self.poly_vars.len());
 

	
 
                        Self::determine_inference_type_from_concrete_type(
 
                            &mut infer_type, &self.poly_vars[poly_arg_idx as usize].parts
 
                        );
 
                    } else {
 
                        // Polymorphic argument has to be inferred
 
                        has_markers = true;
 
                        has_inferred = true;
 
                        infer_type.push(ITP::Marker(poly_arg_idx));
 
                        infer_type.push(ITP::Unknown)
 
                    }
 
                },
 
                PTV::Definition(definition_id, num_embedded) => {
 
                    infer_type.push(ITP::Instance(*definition_id, *num_embedded));
 
                }
 
            }
 
        }
 

	
 
        InferenceType::new(has_markers, !has_inferred, infer_type)
 
    }
 

	
 
    /// Determines the inference type from an already concrete type. Applies the
 
    /// various type "hacks" inside the type inferencer.
 
    fn determine_inference_type_from_concrete_type(parser_type: &mut Vec<InferenceTypePart>, concrete_type: &[ConcreteTypePart]) {
 
        use InferenceTypePart as ITP;
 
        use ConcreteTypePart as CTP;
 

	
 
        for concrete_part in concrete_type {
 
            match concrete_part {
 
                CTP::Void => parser_type.push(ITP::Void),
 
                CTP::Message => {
 
                    parser_type.push(ITP::Message);
 
                    parser_type.push(ITP::UInt8)
 
                },
 
                CTP::Bool => parser_type.push(ITP::Bool),
 
                CTP::UInt8 => parser_type.push(ITP::UInt8),
 
                CTP::UInt16 => parser_type.push(ITP::UInt16),
 
                CTP::UInt32 => parser_type.push(ITP::UInt32),
 
                CTP::UInt64 => parser_type.push(ITP::UInt64),
 
                CTP::SInt8 => parser_type.push(ITP::SInt8),
 
                CTP::SInt16 => parser_type.push(ITP::SInt16),
 
                CTP::SInt32 => parser_type.push(ITP::SInt32),
 
                CTP::SInt64 => parser_type.push(ITP::SInt64),
 
                CTP::Character => parser_type.push(ITP::Character),
 
                CTP::String => {
 
                    parser_type.push(ITP::String);
 
                    parser_type.push(ITP::Character)
 
                },
 
                CTP::Array => parser_type.push(ITP::Array),
 
                CTP::Slice => parser_type.push(ITP::Slice),
 
                CTP::Input => parser_type.push(ITP::Input),
 
                CTP::Output => parser_type.push(ITP::Output),
 
                CTP::Pointer => unreachable!("pointer type during concrete to inference type conversion"),
 
                CTP::Tuple(num) => parser_type.push(ITP::Tuple(*num)),
 
                CTP::Instance(id, num) => parser_type.push(ITP::Instance(*id, *num)),
 
                CTP::Function(_, _) => unreachable!("function type during concrete to inference type conversion"),
 
                CTP::Component(_, _) => unreachable!("component type during concrete to inference type conversion"),
 
            }
 
        }
 
    }
 

	
 
    /// Construct an error when an expression's type does not match. This
 
    /// happens if we infer the expression type from its arguments (e.g. the
 
    /// expression type of an addition operator is the type of the arguments)
 
    /// But the expression type was already set due to our parent (e.g. an
 
    /// "if statement" or a "logical not" always expecting a boolean)
 
    fn construct_expr_type_error(
 
        &self, ctx: &Ctx, expr_id: ExpressionId, arg_id: ExpressionId
 
    ) -> ParseError {
 
        // TODO: Expand and provide more meaningful information for humans
 
        let expr = &ctx.heap[expr_id];
 
        let arg_expr = &ctx.heap[arg_id];
 
        let expr_idx = expr.get_unique_id_in_definition();
 
        let arg_expr_idx = arg_expr.get_unique_id_in_definition();
 
        let expr_type = &self.expr_types[expr_idx as usize].expr_type;
 
        let arg_type = &self.expr_types[arg_expr_idx as usize].expr_type;
 

	
 
        return ParseError::new_error_at_span(
 
            &ctx.module().source, expr.operation_span(), format!(
 
                "incompatible types: this expression expected a '{}'",
 
                expr_type.display_name(&ctx.heap)
 
            )
 
        ).with_info_at_span(
 
            &ctx.module().source, arg_expr.full_span(), format!(
 
                "but this expression yields a '{}'",
 
                arg_type.display_name(&ctx.heap)
 
            )
 
        )
 
    }
 

	
 
    fn construct_arg_type_error(
 
        &self, ctx: &Ctx, expr_id: ExpressionId,
 
        arg1_id: ExpressionId, arg2_id: ExpressionId
 
    ) -> ParseError {
 
        let expr = &ctx.heap[expr_id];
 
        let arg1 = &ctx.heap[arg1_id];
 
        let arg2 = &ctx.heap[arg2_id];
 

	
 
        let arg1_idx = arg1.get_unique_id_in_definition();
 
        let arg1_type = &self.expr_types[arg1_idx as usize].expr_type;
 
        let arg2_idx = arg2.get_unique_id_in_definition();
 
        let arg2_type = &self.expr_types[arg2_idx as usize].expr_type;
 

	
 
        return ParseError::new_error_str_at_span(
 
            &ctx.module().source, expr.operation_span(),
 
            "incompatible types: cannot apply this expression"
 
        ).with_info_at_span(
 
            &ctx.module().source, arg1.full_span(), format!(
 
                "Because this expression has type '{}'",
 
                arg1_type.display_name(&ctx.heap)
 
            )
 
        ).with_info_at_span(
 
            &ctx.module().source, arg2.full_span(), format!(
 
                "But this expression has type '{}'",
 
                arg2_type.display_name(&ctx.heap)
 
            )
 
        )
 
    }
 

	
 
    fn construct_template_type_error(
 
        &self, ctx: &Ctx, expr_id: ExpressionId, template: &[InferenceTypePart]
 
    ) -> ParseError {
 
        let expr = &ctx.heap[expr_id];
 
        let expr_idx = expr.get_unique_id_in_definition();
 
        let expr_type = &self.expr_types[expr_idx as usize].expr_type;
 

	
 
        return ParseError::new_error_at_span(
 
            &ctx.module().source, expr.full_span(), format!(
 
                "incompatible types: got a '{}' but expected a '{}'",
 
                expr_type.display_name(&ctx.heap), 
 
                InferenceType::partial_display_name(&ctx.heap, template)
 
            )
 
        )
 
    }
 

	
 
    /// Constructs a human interpretable error in the case that type inference
 
    /// on a polymorphic variable to a function call or literal construction 
 
    /// failed. This may only be caused by a pair of inference types (which may 
 
    /// come from arguments or the return type) having two different inferred 
 
    /// values for that polymorphic variable.
 
    ///
 
    /// So we find this pair and construct the error using it.
 
    ///
 
    /// We assume that the expression is a function call or a struct literal,
 
    /// and that an actual error has occurred.
 
    fn construct_poly_arg_error(
 
        ctx: &Ctx, poly_data: &ExtraData, expr_id: ExpressionId
 
    ) -> ParseError {
 
        // Helper function to check for polymorph mismatch between two inference
 
        // types.
 
        fn has_poly_mismatch<'a>(type_a: &'a InferenceType, type_b: &'a InferenceType) -> Option<(u32, &'a [InferenceTypePart], &'a [InferenceTypePart])> {
 
            if !type_a.has_marker || !type_b.has_marker {
 
                return None
 
            }
 

	
 
            for (marker_a, section_a) in type_a.marker_iter() {
 
                for (marker_b, section_b) in type_b.marker_iter() {
 
                    if marker_a != marker_b {
 
                        // Not the same polymorphic variable
 
                        continue;
 
                    }
 

	
 
                    if !InferenceType::check_subtrees(section_a, 0, section_b, 0) {
 
                        // Not compatible
 
                        return Some((marker_a, section_a, section_b))
 
                    }
 
                }
 
            }
 

	
 
            None
 
        }
 

	
 
        // Helper function to check for polymorph mismatch between an inference
 
        // type and the polymorphic variables in the poly_data struct.
 
        fn has_explicit_poly_mismatch<'a>(
 
            poly_vars: &'a [InferenceType], arg: &'a InferenceType
 
        ) -> Option<(u32, &'a [InferenceTypePart], &'a [InferenceTypePart])> {
 
            for (marker, section) in arg.marker_iter() {
 
                debug_assert!((marker as usize) < poly_vars.len());
 
                let poly_section = &poly_vars[marker as usize].parts;
 
                if !InferenceType::check_subtrees(poly_section, 0, section, 0) {
 
                    return Some((marker, poly_section, section))
 
                }
 
            }
 

	
 
            None
 
        }
 

	
 
        // Helpers function to retrieve polyvar name and definition name
 
        fn get_poly_var_and_definition_name<'a>(ctx: &'a Ctx, poly_var_idx: u32, definition_id: DefinitionId) -> (&'a str, &'a str) {
 
            let definition = &ctx.heap[definition_id];
 
            let poly_var = definition.poly_vars()[poly_var_idx as usize].value.as_str();
 
            let func_name = definition.identifier().value.as_str();
 

	
 
            (poly_var, func_name)
 
        }
 

	
 
        // Helper function to construct initial error
 
        fn construct_main_error(ctx: &Ctx, poly_data: &ExtraData, poly_var_idx: u32, expr: &Expression) -> ParseError {
 
            match expr {
 
                Expression::Call(expr) => {
 
                    let (poly_var, func_name) = get_poly_var_and_definition_name(ctx, poly_var_idx, poly_data.definition_id);
 
                    return ParseError::new_error_at_span(
 
                        &ctx.module().source, expr.func_span, format!(
 
                            "Conflicting type for polymorphic variable '{}' of '{}'",
 
                            poly_var, func_name
 
                        )
 
                    )
 
                },
 
                Expression::Literal(expr) => {
 
                    let (poly_var, type_name) = get_poly_var_and_definition_name(ctx, poly_var_idx, poly_data.definition_id);
 
                    return ParseError::new_error_at_span(
 
                        &ctx.module().source, expr.span, format!(
 
                            "Conflicting type for polymorphic variable '{}' of instantiation of '{}'",
 
                            poly_var, type_name
 
                        )
 
                    );
 
                },
 
                Expression::Select(expr) => {
 
                    let (poly_var, struct_name) = get_poly_var_and_definition_name(ctx, poly_var_idx, poly_data.definition_id);
 
                    let field_name = match &expr.kind {
 
                        SelectKind::StructField(v) => v,
 
                        SelectKind::TupleMember(_) => unreachable!(), // because we're constructing a polymorph error, and tuple access does not deal with polymorphs
 
                    };
 
                    return ParseError::new_error_at_span(
 
                        &ctx.module().source, expr.full_span, format!(
 
                            "Conflicting type for polymorphic variable '{}' while accessing field '{}' of '{}'",
 
                            poly_var, field_name.value.as_str(), struct_name
 
                        )
 
                    )
 
                }
 
                _ => unreachable!("called construct_poly_arg_error without an expected expression, got: {:?}", expr)
 
            }
 
        }
 

	
 
        // Actual checking
 
        let expr = &ctx.heap[expr_id];
 
        let (expr_args, expr_return_name) = match expr {
 
            Expression::Call(expr) => 
 
                (
 
                    expr.arguments.clone(),
 
                    "return type"
 
                ),
 
            Expression::Literal(expr) => {
 
                let expressions = match &expr.value {
src/protocol/parser/type_table.rs
Show inline comments
 
/**
 
 * type_table.rs
 
 *
 
 * The type table is a lookup from AST definition (which contains just what the
 
 * programmer typed) to a type with additional information computed (e.g. the
 
 * byte size and offsets of struct members). The type table should be considered
 
 * the authoritative source of information on types by the compiler (not the
 
 * AST itself!).
 
 *
 
 * The type table operates in two modes: one is where we just look up the type,
 
 * check its fields for correctness and mark whether it is polymorphic or not.
 
 * The second one is where we compute byte sizes, alignment and offsets.
 
 *
 
 * The basic algorithm for type resolving and computing byte sizes is to
 
 * recursively try to lay out each member type of a particular type. This is
 
 * done in a stack-like fashion, where each embedded type pushes a breadcrumb
 
 * unto the stack. We may discover a cycle in embedded types (we call this a
 
 * "type loop"). After which the type table attempts to break the type loop by
 
 * making specific types heap-allocated. Upon doing so we know their size
 
 * because their stack-size is now based on pointers. Hence breaking the type
 
 * loop required for computing the byte size of types.
 
 *
 
 * The reason for these type shenanigans is because PDL is a value-based
 
 * language, but we would still like to be able to express recursively defined
 
 * types like trees or linked lists. Hence we need to insert pointers somewhere
 
 * to break these cycles.
 
 *
 
 * We will insert these pointers into the variants of unions. However note that
 
 * we can only compute the stack size of a union until we've looked at *all*
 
 * variants. Hence we perform an initial pass where we detect type loops, a
 
 * second pass where we compute the stack sizes of everything, and a third pass
 
 * where we actually compute the size of the heap allocations for unions.
 
 *
 
 * As a final bit of global documentation: non-polymorphic types will always
 
 * have one "monomorph" entry. This contains the non-polymorphic type's memory
 
 * layout.
 
 */
 

	
 
use std::fmt::{Formatter, Result as FmtResult};
 
use std::collections::HashMap;
 
use std::hash::{Hash, Hasher};
 

	
 
use crate::protocol::ast::*;
 
use crate::protocol::parser::symbol_table::SymbolScope;
 
use crate::protocol::input_source::ParseError;
 
use crate::protocol::parser::*;
 

	
 
//------------------------------------------------------------------------------
 
// Defined Types
 
//------------------------------------------------------------------------------
 

	
 
#[derive(Copy, Clone, PartialEq, Eq)]
 
pub enum TypeClass {
 
    Enum,
 
    Union,
 
    Struct,
 
    Function,
 
    Component
 
}
 

	
 
impl TypeClass {
 
    pub(crate) fn display_name(&self) -> &'static str {
 
        match self {
 
            TypeClass::Enum => "enum",
 
            TypeClass::Union => "union",
 
            TypeClass::Struct => "struct",
 
            TypeClass::Function => "function",
 
            TypeClass::Component => "component",
 
        }
 
    }
 

	
 
    pub(crate) fn is_data_type(&self) -> bool {
 
        match self {
 
            TypeClass::Enum | TypeClass::Union | TypeClass::Struct => true,
 
            TypeClass::Function | TypeClass::Component => false,
 
        }
 
    }
 
}
 

	
 
impl std::fmt::Display for TypeClass {
 
    fn fmt(&self, f: &mut Formatter<'_>) -> FmtResult {
 
        write!(f, "{}", self.display_name())
 
    }
 
}
 

	
 
/// Struct wrapping around a potentially polymorphic type. If the type does not
 
/// have any polymorphic arguments then it will not have any monomorphs and
 
/// `is_polymorph` will be set to `false`. A type with polymorphic arguments
 
/// only has `is_polymorph` set to `true` if the polymorphic arguments actually
 
/// appear in the types associated types (function return argument, struct
 
/// field, enum variant, etc.). Otherwise the polymorphic argument is just a
 
/// marker and does not influence the bytesize of the type.
 
pub struct DefinedType {
 
    pub(crate) ast_root: RootId,
 
    pub(crate) ast_definition: DefinitionId,
 
    pub(crate) definition: DefinedTypeVariant,
 
    pub(crate) poly_vars: Vec<PolymorphicVariable>,
 
    pub(crate) is_polymorph: bool,
 
}
 

	
 
pub enum DefinedTypeVariant {
 
    Enum(EnumType),
 
    Union(UnionType),
 
    Struct(StructType),
 
    Function(FunctionType),
 
    Component(ComponentType)
 
}
 

	
 
impl DefinedTypeVariant {
 
    pub(crate) fn type_class(&self) -> TypeClass {
 
        match self {
 
            DefinedTypeVariant::Enum(_) => TypeClass::Enum,
 
            DefinedTypeVariant::Union(_) => TypeClass::Union,
 
            DefinedTypeVariant::Struct(_) => TypeClass::Struct,
 
            DefinedTypeVariant::Function(_) => TypeClass::Function,
 
            DefinedTypeVariant::Component(_) => TypeClass::Component
 
        }
 
    }
 

	
 
    pub(crate) fn as_struct(&self) -> &StructType {
 
        match self {
 
            DefinedTypeVariant::Struct(v) => v,
 
            _ => unreachable!("Cannot convert {} to struct variant", self.type_class())
 
        }
 
    }
 

	
 
    pub(crate) fn as_enum(&self) -> &EnumType {
 
        match self {
 
            DefinedTypeVariant::Enum(v) => v,
 
            _ => unreachable!("Cannot convert {} to enum variant", self.type_class())
 
        }
 
    }
 

	
 
    pub(crate) fn as_union(&self) -> &UnionType {
 
        match self {
 
            DefinedTypeVariant::Union(v) => v,
 
            _ => unreachable!("Cannot convert {} to union variant", self.type_class())
 
        }
 
    }
 
}
 

	
 
pub struct PolymorphicVariable {
 
    identifier: Identifier,
 
    is_in_use: bool, // a polymorphic argument may be defined, but not used by the type definition
 
    pub(crate) identifier: Identifier,
 
    pub(crate) is_in_use: bool, // a polymorphic argument may be defined, but not used by the type definition
 
}
 

	
 
/// `EnumType` is the classical C/C++ enum type. It has various variants with
 
/// an assigned integer value. The integer values may be user-defined,
 
/// compiler-defined, or a mix of the two. If a user assigns the same enum
 
/// value multiple times, we assume the user is an expert and we consider both
 
/// variants to be equal to one another.
 
pub struct EnumType {
 
    pub variants: Vec<EnumVariant>,
 
    pub minimum_tag_value: i64,
 
    pub maximum_tag_value: i64,
 
    pub tag_type: ConcreteType,
 
    pub size: usize,
 
    pub alignment: usize,
 
}
 

	
 
// TODO: Also support maximum u64 value
 
pub struct EnumVariant {
 
    pub identifier: Identifier,
 
    pub value: i64,
 
}
 

	
 
/// `UnionType` is the algebraic datatype (or sum type, or discriminated union).
 
/// A value is an element of the union, identified by its tag, and may contain
 
/// a single subtype.
 
/// For potentially infinite types (i.e. a tree, or a linked list) only unions
 
/// can break the infinite cycle. So when we lay out these unions in memory we
 
/// will reserve enough space on the stack for all union variants that do not
 
/// cause "type loops" (i.e. a union `A` with a variant containing a struct
 
/// `B`). And we will reserve enough space on the heap (and store a pointer in
 
/// the union) for all variants which do cause type loops (i.e. a union `A`
 
/// with a variant to a struct `B` that contains the union `A` again).
 
pub struct UnionType {
 
    pub variants: Vec<UnionVariant>,
 
    pub tag_type: ConcreteType,
 
    pub tag_size: usize,
 
}
 

	
 
pub struct UnionVariant {
 
    pub identifier: Identifier,
 
    pub embedded: Vec<ParserType>, // zero-length does not have embedded values
 
    pub tag_value: i64,
 
}
 

	
 
/// `StructType` is a generic C-like struct type (or record type, or product
 
/// type) type.
 
pub struct StructType {
 
    pub fields: Vec<StructField>,
 
}
 

	
 
pub struct StructField {
 
    pub identifier: Identifier,
 
    pub parser_type: ParserType,
 
}
 

	
 
/// `FunctionType` is what you expect it to be: a particular function's
 
/// signature.
 
pub struct FunctionType {
 
    pub return_type: ParserType,
 
    pub arguments: Vec<FunctionArgument>,
 
}
 

	
 
pub struct ComponentType {
 
    pub variant: ComponentVariant,
 
    pub arguments: Vec<FunctionArgument>,
 
}
 

	
 
pub struct FunctionArgument {
 
    identifier: Identifier,
 
    parser_type: ParserType,
 
}
 

	
 
/// Represents the data associated with a single expression after type inference
 
/// for a monomorph (or just the normal expression types, if dealing with a
 
/// non-polymorphic function/component).
 
pub struct MonomorphExpression {
 
    // The output type of the expression. Note that for a function it is not the
 
    // function's signature but its return type
 
    pub(crate) expr_type: ConcreteType,
 
    // Has multiple meanings: the field index for select expressions, the
 
    // monomorph index for polymorphic function calls or literals. Negative
 
    // values are never used, but used to catch programming errors.
 
    pub(crate) field_or_monomorph_idx: i32,
 
    pub(crate) type_id: TypeId,
 
}
 

	
 
//------------------------------------------------------------------------------
 
// Type monomorph storage
 
//------------------------------------------------------------------------------
 

	
 
pub(crate) enum MonoTypeVariant {
 
    Builtin, // no extra data, added manually in compiler initialization code
 
    Enum, // no extra data
 
    Struct(StructMonomorph),
 
    Union(UnionMonomorph),
 
    Procedure(ProcedureMonomorph), // functions, components
 
    Tuple(TupleMonomorph),
 
}
 

	
 
impl MonoTypeVariant {
 
    fn as_struct_mut(&mut self) -> &mut StructMonomorph {
 
        match self {
 
            MonoTypeVariant::Struct(v) => v,
 
            _ => unreachable!(),
 
        }
 
    }
 

	
 
    pub(crate) fn as_union(&self) -> &UnionMonomorph {
 
        match self {
 
            MonoTypeVariant::Union(v) => v,
 
            _ => unreachable!(),
 
        }
 
    }
 

	
 
    fn as_union_mut(&mut self) -> &mut UnionMonomorph {
 
        match self {
 
            MonoTypeVariant::Union(v) => v,
 
            _ => unreachable!(),
 
        }
 
    }
 

	
 
    fn as_tuple_mut(&mut self) -> &mut TupleMonomorph {
 
        match self {
 
            MonoTypeVariant::Tuple(v) => v,
 
            _ => unreachable!(),
 
        }
 
    }
 

	
 
    fn as_procedure(&self) -> &ProcedureMonomorph {
 
        match self {
 
            MonoTypeVariant::Procedure(v) => v,
 
            _ => unreachable!(),
 
        }
 
    }
 

	
 
    fn as_procedure_mut(&mut self) -> &mut ProcedureMonomorph {
 
        match self {
 
            MonoTypeVariant::Procedure(v) => v,
 
            _ => unreachable!(),
 
        }
 
    }
 
}
 

	
 
/// Struct monomorph
 
pub struct StructMonomorph {
 
    pub fields: Vec<StructMonomorphField>,
 
}
 

	
 
pub struct StructMonomorphField {
 
    pub type_id: TypeId,
 
    concrete_type: ConcreteType,
 
    pub size: usize,
 
    pub alignment: usize,
 
    pub offset: usize,
 
}
 

	
 
/// Union monomorph
 
pub struct UnionMonomorph {
 
    pub variants: Vec<UnionMonomorphVariant>,
 
    pub tag_size: usize, // copied from `UnionType` upon monomorph construction.
 
    // note that the stack size is in the `TypeMonomorph` struct. This size and
 
    // alignment will include the size of the union tag.
 
    //
 
    // heap_size contains the allocated size of the union in the case it
 
    // is used to break a type loop. If it is 0, then it doesn't require
 
    // allocation and lives entirely on the stack.
 
    pub heap_size: usize,
 
    pub heap_alignment: usize,
 
}
 

	
 
pub struct UnionMonomorphVariant {
 
    pub lives_on_heap: bool,
 
    pub embedded: Vec<UnionMonomorphEmbedded>,
 
}
 

	
 
pub struct UnionMonomorphEmbedded {
 
    pub type_id: TypeId,
 
    concrete_type: ConcreteType,
 
    // Note that the meaning of the offset (and alignment) depend on whether or
 
    // not the variant lives on the stack/heap. If it lives on the stack then
 
    // they refer to the offset from the start of the union value (so the first
 
    // embedded type lives at a non-zero offset, because the union tag sits in
 
    // the front). If it lives on the heap then it refers to the offset from the
 
    // allocated memory region (so the first embedded type lives at a 0 offset).
 
    pub size: usize,
 
    pub alignment: usize,
 
    pub offset: usize,
 
}
 

	
 
/// Procedure (functions and components of all possible types) monomorph. Also
 
/// stores the expression type data from the typechecking/inferencing pass.
 
pub struct ProcedureMonomorph {
 
@@ -594,384 +594,385 @@ enum MemoryLayoutResult {
 
    TypeExists(usize, usize), // (size, alignment)
 
    PushBreadcrumb(MemoryBreadcrumb),
 
}
 

	
 
// TODO: @Optimize, initial memory-unoptimized implementation
 
struct TypeLoopEntry {
 
    type_id: TypeId,
 
    is_union: bool,
 
}
 

	
 
struct TypeLoop {
 
    members: Vec<TypeLoopEntry>,
 
}
 

	
 
type DefinitionMap = HashMap<DefinitionId, DefinedType>;
 
type MonoTypeMap = HashMap<MonoSearchKey, TypeId>;
 
type MonoTypeArray = Vec<MonoType>;
 

	
 
pub struct TypeTable {
 
    // Lookup from AST DefinitionId to a defined type. Also lookups for
 
    // concrete type to monomorphs
 
    pub(crate) definition_lookup: DefinitionMap,
 
    mono_type_lookup: MonoTypeMap,
 
    pub(crate) mono_types: MonoTypeArray,
 
    mono_search_key: MonoSearchKey,
 
    // Breadcrumbs left behind while trying to find type loops. Also used to
 
    // determine sizes of types when all type loops are detected.
 
    type_loop_breadcrumbs: Vec<TypeLoopBreadcrumb>,
 
    type_loops: Vec<TypeLoop>,
 
    // Stores all encountered types during type loop detection. Used afterwards
 
    // to iterate over all types in order to compute size/alignment.
 
    encountered_types: Vec<TypeLoopEntry>,
 
    // Breadcrumbs and temporary storage during memory layout computation.
 
    memory_layout_breadcrumbs: Vec<MemoryBreadcrumb>,
 
    size_alignment_stack: Vec<(usize, usize)>,
 
}
 

	
 
impl TypeTable {
 
    /// Construct a new type table without any resolved types.
 
    pub(crate) fn new() -> Self {
 
        Self{ 
 
            definition_lookup: HashMap::with_capacity(128),
 
            mono_type_lookup: HashMap::with_capacity(128),
 
            mono_types: Vec::with_capacity(128),
 
            mono_search_key: MonoSearchKey::with_capacity(32),
 
            type_loop_breadcrumbs: Vec::with_capacity(32),
 
            type_loops: Vec::with_capacity(8),
 
            encountered_types: Vec::with_capacity(32),
 
            memory_layout_breadcrumbs: Vec::with_capacity(32),
 
            size_alignment_stack: Vec::with_capacity(64),
 
        }
 
    }
 

	
 
    /// Iterates over all defined types (polymorphic and non-polymorphic) and
 
    /// add their types in two passes. In the first pass we will just add the
 
    /// base types (we will not consider monomorphs, and we will not compute
 
    /// byte sizes). In the second pass we will compute byte sizes of
 
    /// non-polymorphic types, and potentially the monomorphs that are embedded
 
    /// in those types.
 
    pub(crate) fn build_base_types(&mut self, modules: &mut [Module], ctx: &mut PassCtx) -> Result<(), ParseError> {
 
        // Make sure we're allowed to cast root_id to index into ctx.modules
 
        debug_assert!(modules.iter().all(|m| m.phase >= ModuleCompilationPhase::DefinitionsParsed));
 
        debug_assert!(self.definition_lookup.is_empty());
 

	
 
        dbg_code!({
 
            for (index, module) in modules.iter().enumerate() {
 
                debug_assert_eq!(index, module.root_id.index as usize);
 
            }
 
        });
 

	
 
        // Use context to guess hashmap size of the base types
 
        let reserve_size = ctx.heap.definitions.len();
 
        self.definition_lookup.reserve(reserve_size);
 

	
 
        // Resolve all base types
 
        for definition_idx in 0..ctx.heap.definitions.len() {
 
            let definition_id = ctx.heap.definitions.get_id(definition_idx);
 
            let definition = &ctx.heap[definition_id];
 

	
 
            match definition {
 
                Definition::Enum(_) => self.build_base_enum_definition(modules, ctx, definition_id)?,
 
                Definition::Union(_) => self.build_base_union_definition(modules, ctx, definition_id)?,
 
                Definition::Struct(_) => self.build_base_struct_definition(modules, ctx, definition_id)?,
 
                Definition::Function(_) => self.build_base_function_definition(modules, ctx, definition_id)?,
 
                Definition::Component(_) => self.build_base_component_definition(modules, ctx, definition_id)?,
 
            }
 
        }
 

	
 
        debug_assert_eq!(self.definition_lookup.len(), reserve_size, "mismatch in reserved size of type table");
 
        for module in modules.iter_mut() {
 
            module.phase = ModuleCompilationPhase::TypesAddedToTable;
 
        }
 

	
 
        // Go through all types again, lay out all types that are not
 
        // polymorphic. This might cause us to lay out monomorphized polymorphs
 
        // if these were member types of non-polymorphic types.
 
        for definition_idx in 0..ctx.heap.definitions.len() {
 
            let definition_id = ctx.heap.definitions.get_id(definition_idx);
 
            let poly_type = self.definition_lookup.get(&definition_id).unwrap();
 

	
 
            if !poly_type.definition.type_class().is_data_type() || !poly_type.poly_vars.is_empty() {
 
                continue;
 
            }
 

	
 
            // If here then the type is a data type without polymorphic
 
            // variables, but we might have instantiated it already, so:
 
            let concrete_parts = [ConcreteTypePart::Instance(definition_id, 0)];
 
            self.mono_search_key.set(&concrete_parts, &[]);
 
            let type_id = self.mono_type_lookup.get(&self.mono_search_key);
 
            if type_id.is_none() {
 
                self.detect_and_resolve_type_loops_for(
 
                    modules, ctx.heap,
 
                    ConcreteType{
 
                        parts: vec![ConcreteTypePart::Instance(definition_id, 0)]
 
                    },
 
                )?;
 
                self.lay_out_memory_for_encountered_types(ctx.arch);
 
            }
 
        }
 

	
 
        Ok(())
 
    }
 

	
 
    /// Retrieves base definition from type table. We must be able to retrieve
 
    /// it as we resolve all base types upon type table construction (for now).
 
    /// However, in the future we might do on-demand type resolving, so return
 
    /// an option anyway
 
    #[inline]
 
    pub(crate) fn get_base_definition(&self, definition_id: &DefinitionId) -> Option<&DefinedType> {
 
        self.definition_lookup.get(&definition_id)
 
    }
 

	
 
    /// Returns the index into the monomorph type array if the procedure type
 
    /// already has a (reserved) monomorph.
 
    #[inline]
 
    pub(crate) fn get_procedure_monomorph_type_id(&self, definition_id: &DefinitionId, type_parts: &[ConcreteTypePart]) -> Option<TypeId> {
 
        // Cannot use internal search key due to mutability issues. But this
 
        // method should end up being deprecated at some point anyway.
 
        debug_assert_eq!(get_concrete_type_definition(type_parts).unwrap(), *definition_id);
 
        let base_type = self.definition_lookup.get(definition_id).unwrap();
 
        let mut search_key = MonoSearchKey::with_capacity(type_parts.len());
 
        search_key.set(type_parts, &base_type.poly_vars);
 

	
 
        return self.mono_type_lookup.get(&search_key).copied();
 
    }
 

	
 
    #[inline]
 
    pub(crate) fn get_monomorph(&self, type_id: TypeId) -> &MonoType {
 
        return &self.mono_types[type_id.0 as usize];
 
    }
 

	
 
    /// Returns a mutable reference to a procedure's monomorph expression data.
 
    /// Used by typechecker to fill in previously reserved type information
 
    #[inline]
 
    pub(crate) fn get_procedure_monomorph_mut(&mut self, type_id: TypeId) -> &mut ProcedureMonomorph {
 
        let mono_type = &mut self.mono_types[type_id.0 as usize];
 
        return mono_type.variant.as_procedure_mut();
 
    }
 

	
 
    #[inline]
 
    pub(crate) fn get_procedure_monomorph(&self, type_id: TypeId) -> &ProcedureMonomorph {
 
        let mono_type = &self.mono_types[type_id.0 as usize];
 
        return mono_type.variant.as_procedure();
 
    }
 

	
 
    /// Reserves space for a monomorph of a polymorphic procedure. The index
 
    /// will point into a (reserved) slot of the array of expression types. The
 
    /// monomorph may NOT exist yet (because the reservation implies that we're
 
    /// going to be performing typechecking on it, and we don't want to
 
    /// check the same monomorph twice)
 
    pub(crate) fn reserve_procedure_monomorph_type_id(&mut self, definition_id: &DefinitionId, concrete_type: ConcreteType) -> TypeId {
 
        debug_assert_eq!(get_concrete_type_definition(&concrete_type.parts).unwrap(), *definition_id);
 
        let type_id = TypeId(self.mono_types.len() as i64);
 
        let base_type = self.definition_lookup.get_mut(definition_id).unwrap();
 
        self.mono_search_key.set(&concrete_type.parts, &base_type.poly_vars);
 

	
 
        debug_assert!(!self.mono_type_lookup.contains_key(&self.mono_search_key));
 
        self.mono_type_lookup.insert(self.mono_search_key.clone(), type_id);
 
        self.mono_types.push(MonoType::new_empty(type_id, concrete_type, MonoTypeVariant::Procedure(ProcedureMonomorph{
 
            arg_types: Vec::new(),
 
            expr_data: Vec::new(),
 
        })));
 

	
 
        return type_id;
 
    }
 

	
 
    /// Adds a builtin type to the type table. As this is only called by the
 
    /// compiler during setup we assume it cannot fail.
 
    // TODO: Finish this train of thought, requires a little bit of design work
 
    pub(crate) fn add_builtin_type(&mut self, concrete_type: ConcreteType, poly_vars: &[PolymorphicVariable], size: usize, alignment: usize) -> TypeId {
 
        self.mono_search_key.set(&concrete_type.parts, poly_vars);
 
        debug_assert!(!self.mono_type_lookup.contains_key(&self.mono_search_key));
 
        debug_assert_ne!(alignment, 0);
 
        let type_id = TypeId(self.mono_types.len() as i64);
 
        self.mono_type_lookup.insert(self.mono_search_key.clone(), type_id);
 
        self.mono_types.push(MonoType{
 
            type_id,
 
            concrete_type,
 
            size,
 
            alignment,
 
            variant: MonoTypeVariant::Builtin,
 
        });
 

	
 
        return type_id;
 
    }
 

	
 
    /// Adds a monomorphed type to the type table. If it already exists then the
 
    /// previous entry will be used.
 
    pub(crate) fn add_monomorphed_type(
 
        &mut self, modules: &[Module], heap: &Heap, arch: &TargetArch,
 
        definition_id: DefinitionId, concrete_type: ConcreteType
 
    ) -> Result<TypeId, ParseError> {
 
        debug_assert_eq!(definition_id, get_concrete_type_definition(&concrete_type.parts).unwrap());
 

	
 
        // Check if the concrete type was already added
 
        let definition = self.definition_lookup.get(&definition_id).unwrap();
 
        let poly_var_in_use = &definition.poly_vars;
 
        self.mono_search_key.set(&concrete_type.parts, poly_var_in_use.as_slice());
 
        if let Some(type_id) = self.mono_type_lookup.get(&self.mono_search_key) {
 
            return Ok(*type_id);
 
        }
 

	
 
        // Concrete type needs to be added
 
        self.detect_and_resolve_type_loops_for(modules, heap, concrete_type)?;
 
        let type_id = self.encountered_types[0].type_id;
 
        self.lay_out_memory_for_encountered_types(arch);
 

	
 
        return Ok(type_id);
 
    }
 

	
 
    //--------------------------------------------------------------------------
 
    // Building base types
 
    //--------------------------------------------------------------------------
 

	
 
    /// Builds the base type for an enum. Will not compute byte sizes
 
    fn build_base_enum_definition(&mut self, modules: &[Module], ctx: &mut PassCtx, definition_id: DefinitionId) -> Result<(), ParseError> {
 
        debug_assert!(!self.definition_lookup.contains_key(&definition_id), "base enum already built");
 
        let definition = ctx.heap[definition_id].as_enum();
 
        let root_id = definition.defined_in;
 

	
 
        // Determine enum variants
 
        let mut enum_value = -1;
 
        let mut variants = Vec::with_capacity(definition.variants.len());
 

	
 
        for variant in &definition.variants {
 
            if enum_value == i64::MAX {
 
                let source = &modules[definition.defined_in.index as usize].source;
 
                return Err(ParseError::new_error_str_at_span(
 
                    source, variant.identifier.span,
 
                    "this enum variant has an integer value that is too large"
 
                ));
 
            }
 

	
 
            enum_value += 1;
 
            if let EnumVariantValue::Integer(explicit_value) = variant.value {
 
                enum_value = explicit_value;
 
            }
 

	
 
            variants.push(EnumVariant{
 
                identifier: variant.identifier.clone(),
 
                value: enum_value,
 
            });
 
        }
 

	
 
        // Determine tag size
 
        let mut min_enum_value = 0;
 
        let mut max_enum_value = 0;
 
        if !variants.is_empty() {
 
            min_enum_value = variants[0].value;
 
            max_enum_value = variants[0].value;
 
            for variant in variants.iter().skip(1) {
 
                min_enum_value = min_enum_value.min(variant.value);
 
                max_enum_value = max_enum_value.max(variant.value);
 
            }
 
        }
 

	
 
        let (tag_type, size_and_alignment) = Self::variant_tag_type_from_values(min_enum_value, max_enum_value);
 

	
 
        // Enum names and polymorphic args do not conflict
 
        Self::check_identifier_collision(
 
            modules, root_id, &variants, |variant| &variant.identifier, "enum variant"
 
        )?;
 

	
 
        // Polymorphic arguments cannot appear as embedded types, because
 
        // they can only consist of integer variants.
 
        Self::check_poly_args_collision(modules, ctx, root_id, &definition.poly_vars)?;
 
        let poly_vars = Self::create_polymorphic_variables(&definition.poly_vars);
 

	
 
        self.definition_lookup.insert(definition_id, DefinedType {
 
            ast_root: root_id,
 
            ast_definition: definition_id,
 
            definition: DefinedTypeVariant::Enum(EnumType{
 
                variants,
 
                minimum_tag_value: min_enum_value,
 
                maximum_tag_value: max_enum_value,
 
                tag_type,
 
                size: size_and_alignment,
 
                alignment: size_and_alignment
 
            }),
 
            poly_vars,
 
            is_polymorph: false,
 
        });
 

	
 
        return Ok(());
 
    }
 

	
 
    /// Builds the base type for a union. Will compute byte sizes.
 
    fn build_base_union_definition(&mut self, modules: &[Module], ctx: &mut PassCtx, definition_id: DefinitionId) -> Result<(), ParseError> {
 
        debug_assert!(!self.definition_lookup.contains_key(&definition_id), "base union already built");
 
        let definition = ctx.heap[definition_id].as_union();
 
        let root_id = definition.defined_in;
 

	
 
        // Check all variants and their embedded types
 
        let mut variants = Vec::with_capacity(definition.variants.len());
 
        let mut tag_counter = 0;
 
        for variant in &definition.variants {
 
            for embedded in &variant.value {
 
                Self::check_member_parser_type(
 
                    modules, ctx, root_id, embedded, false
 
                )?;
 
            }
 

	
 
            variants.push(UnionVariant{
 
                identifier: variant.identifier.clone(),
 
                embedded: variant.value.clone(),
 
                tag_value: tag_counter,
 
            });
 
            tag_counter += 1;
 
        }
 

	
 
        let mut max_tag_value = 0;
 
        if tag_counter != 0 {
 
            max_tag_value = tag_counter - 1
 
        }
 

	
 
        let (tag_type, tag_size) = Self::variant_tag_type_from_values(0, max_tag_value);
 

	
 
        // Make sure there are no conflicts in identifiers
 
        Self::check_identifier_collision(
 
            modules, root_id, &variants, |variant| &variant.identifier, "union variant"
 
        )?;
 
        Self::check_poly_args_collision(modules, ctx, root_id, &definition.poly_vars)?;
 

	
 
        // Construct internal representation of union
 
        let mut poly_vars = Self::create_polymorphic_variables(&definition.poly_vars);
 
        for variant in &definition.variants {
 
            for embedded in &variant.value {
 
                Self::mark_used_polymorphic_variables(&mut poly_vars, embedded);
 
            }
 
        }
 

	
 
        let is_polymorph = poly_vars.iter().any(|arg| arg.is_in_use);
 

	
 
        self.definition_lookup.insert(definition_id, DefinedType{
 
            ast_root: root_id,
 
            ast_definition: definition_id,
 
            definition: DefinedTypeVariant::Union(UnionType{ variants, tag_type, tag_size }),
 
            poly_vars,
 
            is_polymorph
 
        });
 

	
 
        return Ok(());
 
    }
 

	
 
    /// Builds base struct type. Will not compute byte sizes.
 
    fn build_base_struct_definition(&mut self, modules: &[Module], ctx: &mut PassCtx, definition_id: DefinitionId) -> Result<(), ParseError> {
 
        debug_assert!(!self.definition_lookup.contains_key(&definition_id), "base struct already built");
 
        let definition = ctx.heap[definition_id].as_struct();
 
        let root_id = definition.defined_in;
 

	
 
        // Check all struct fields and construct internal representation
 
        let mut fields = Vec::with_capacity(definition.fields.len());
 

	
 
        for field in &definition.fields {
 
            Self::check_member_parser_type(
 
                modules, ctx, root_id, &field.parser_type, false
 
            )?;
 

	
 
            fields.push(StructField{
 
                identifier: field.field.clone(),
 
                parser_type: field.parser_type.clone(),
 
            });
 
        }
 

	
 
        // Make sure there are no conflicting variables
 
@@ -1605,679 +1606,672 @@ impl TypeTable {
 
                Self::set_search_key_to_tuple(&mut self.mono_search_key, &self.definition_lookup, &concrete_type.parts);
 
                self.mono_type_lookup.insert(self.mono_search_key.clone(), type_id);
 
                self.mono_types.push(MonoType::new_empty(type_id, concrete_type, MonoTypeVariant::Tuple(TupleMonomorph{ members })));
 

	
 
                type_id
 
            },
 
            CTP::Instance(_check_definition_id, _) => {
 
                debug_assert_eq!(definition_id, *_check_definition_id); // because this is how `definition_id` was determined
 

	
 
                Self::set_search_key_to_type(&mut self.mono_search_key, &self.definition_lookup, &concrete_type.parts);
 
                let base_type = self.definition_lookup.get(&definition_id).unwrap();
 
                let type_id = match &base_type.definition {
 
                    DTV::Enum(definition) => {
 
                        // The enum is a bit exceptional in that when we insert
 
                        // it we we will immediately set its size/alignment:
 
                        // there is nothing to compute here.
 
                        debug_assert!(definition.size != 0 && definition.alignment != 0);
 
                        let type_id = TypeId(self.mono_types.len() as i64);
 
                        self.mono_type_lookup.insert(self.mono_search_key.clone(), type_id);
 
                        self.mono_types.push(MonoType::new_empty(type_id, concrete_type, MonoTypeVariant::Enum));
 

	
 
                        let mono_type = &mut self.mono_types[type_id.0 as usize];
 
                        mono_type.size = definition.size;
 
                        mono_type.alignment = definition.alignment;
 

	
 
                        type_id
 
                    },
 
                    DTV::Union(definition) => {
 
                        // Create all the variants with their concrete types
 
                        let mut mono_variants = Vec::with_capacity(definition.variants.len());
 
                        for poly_variant in &definition.variants {
 
                            let mut mono_embedded = Vec::with_capacity(poly_variant.embedded.len());
 
                            for poly_embedded in &poly_variant.embedded {
 
                                let mono_concrete = Self::construct_concrete_type(poly_embedded, &concrete_type);
 
                                mono_embedded.push(UnionMonomorphEmbedded{
 
                                    type_id: TypeId::new_invalid(),
 
                                    concrete_type: mono_concrete,
 
                                    size: 0,
 
                                    alignment: 0,
 
                                    offset: 0
 
                                });
 
                            }
 

	
 
                            mono_variants.push(UnionMonomorphVariant{
 
                                lives_on_heap: false,
 
                                embedded: mono_embedded,
 
                            })
 
                        }
 

	
 
                        let type_id = TypeId(self.mono_types.len() as i64);
 
                        let tag_size = definition.tag_size;
 
                        Self::set_search_key_to_type(&mut self.mono_search_key, &self.definition_lookup, &concrete_type.parts);
 
                        self.mono_type_lookup.insert(self.mono_search_key.clone(), type_id);
 
                        self.mono_types.push(MonoType::new_empty(type_id, concrete_type, MonoTypeVariant::Union(UnionMonomorph{
 
                            variants: mono_variants,
 
                            tag_size,
 
                            heap_size: 0,
 
                            heap_alignment: 0,
 
                        })));
 

	
 
                        is_union = true;
 
                        type_id
 
                    },
 
                    DTV::Struct(definition) => {
 
                        // Create fields
 
                        let mut mono_fields = Vec::with_capacity(definition.fields.len());
 
                        for poly_field in &definition.fields {
 
                            let mono_concrete = Self::construct_concrete_type(&poly_field.parser_type, &concrete_type);
 
                            mono_fields.push(StructMonomorphField{
 
                                type_id: TypeId::new_invalid(),
 
                                concrete_type: mono_concrete,
 
                                size: 0,
 
                                alignment: 0,
 
                                offset: 0
 
                            })
 
                        }
 

	
 
                        let type_id = TypeId(self.mono_types.len() as i64);
 
                        Self::set_search_key_to_type(&mut self.mono_search_key, &self.definition_lookup, &concrete_type.parts);
 
                        self.mono_type_lookup.insert(self.mono_search_key.clone(), type_id);
 
                        self.mono_types.push(MonoType::new_empty(type_id, concrete_type, MonoTypeVariant::Struct(StructMonomorph{
 
                            fields: mono_fields,
 
                        })));
 

	
 
                        type_id
 
                    },
 
                    DTV::Function(_) | DTV::Component(_) => {
 
                        unreachable!("pushing type resolving breadcrumb for procedure type")
 
                    },
 
                };
 

	
 
                type_id
 
            },
 
            _ => unreachable!(),
 
        };
 

	
 
        self.encountered_types.push(TypeLoopEntry{ type_id, is_union });
 
        self.type_loop_breadcrumbs.push(TypeLoopBreadcrumb{
 
            type_id,
 
            next_member: 0,
 
            next_embedded: 0,
 
        });
 
    }
 

	
 
    /// Constructs a concrete type out of a parser type for a struct field or
 
    /// union embedded type. It will do this by looking up the polymorphic
 
    /// variables in the supplied concrete type. The assumption is that the
 
    /// polymorphic variable's indices correspond to the subtrees in the
 
    /// concrete type.
 
    fn construct_concrete_type(member_type: &ParserType, container_type: &ConcreteType) -> ConcreteType {
 
        use ParserTypeVariant as PTV;
 
        use ConcreteTypePart as CTP;
 

	
 
        // TODO: Combine with code in pass_typing.rs
 
        fn parser_to_concrete_part(part: &ParserTypeVariant) -> Option<ConcreteTypePart> {
 
            match part {
 
                PTV::Void      => Some(CTP::Void),
 
                PTV::Message   => Some(CTP::Message),
 
                PTV::Bool      => Some(CTP::Bool),
 
                PTV::UInt8     => Some(CTP::UInt8),
 
                PTV::UInt16    => Some(CTP::UInt16),
 
                PTV::UInt32    => Some(CTP::UInt32),
 
                PTV::UInt64    => Some(CTP::UInt64),
 
                PTV::SInt8     => Some(CTP::SInt8),
 
                PTV::SInt16    => Some(CTP::SInt16),
 
                PTV::SInt32    => Some(CTP::SInt32),
 
                PTV::SInt64    => Some(CTP::SInt64),
 
                PTV::Character => Some(CTP::Character),
 
                PTV::String    => Some(CTP::String),
 
                PTV::Array     => Some(CTP::Array),
 
                PTV::Input     => Some(CTP::Input),
 
                PTV::Output    => Some(CTP::Output),
 
                PTV::Tuple(num) => Some(CTP::Tuple(*num)),
 
                PTV::Definition(definition_id, num) => Some(CTP::Instance(*definition_id, *num)),
 
                _              => None
 
            }
 
        }
 

	
 
        let mut parts = Vec::with_capacity(member_type.elements.len()); // usually a correct estimation, might not be
 
        for member_part in &member_type.elements {
 
            // Check if we have a regular builtin type
 
            if let Some(part) = parser_to_concrete_part(&member_part.variant) {
 
                parts.push(part);
 
                continue;
 
            }
 

	
 
            // Not builtin, but if all code is working correctly, we only care
 
            // about the polymorphic argument at this point.
 
            if let PTV::PolymorphicArgument(_container_definition_id, poly_arg_idx) = member_part.variant {
 
                debug_assert_eq!(_container_definition_id, get_concrete_type_definition(&container_type.parts).unwrap());
 

	
 
                let mut container_iter = container_type.embedded_iter(0);
 
                for _ in 0..poly_arg_idx {
 
                    container_iter.next();
 
                }
 

	
 
                let poly_section = container_iter.next().unwrap();
 
                parts.extend(poly_section);
 

	
 
                continue;
 
            }
 

	
 
            unreachable!("unexpected type part {:?} from {:?}", member_part, member_type);
 
        }
 

	
 
        return ConcreteType{ parts };
 
    }
 

	
 
    //--------------------------------------------------------------------------
 
    // Determining memory layout for types
 
    //--------------------------------------------------------------------------
 

	
 
    /// Should be called after type loops are detected (and resolved
 
    /// successfully). As a result of this call we expect the
 
    /// `encountered_types` array to be filled. We'll calculate size/alignment/
 
    /// offset values for those types in this routine.
 
    fn lay_out_memory_for_encountered_types(&mut self, arch: &TargetArch) {
 
        // Programmers note: this works like a little stack machine. We have
 
        // memory layout breadcrumbs which, like the type loop breadcrumbs, keep
 
        // track of the currently considered member type. This breadcrumb also
 
        // stores an index into the `size_alignment_stack`, which will be used
 
        // to store intermediate size/alignment pairs until all members are
 
        // resolved. Note that this `size_alignment_stack` is NOT an
 
        // optimization, we're working around borrowing rules here.
 

	
 
        // Just finished type loop detection, so we're left with the encountered
 
        // types only
 
        debug_assert!(self.type_loops.is_empty());
 
        debug_assert!(!self.encountered_types.is_empty());
 
        debug_assert!(self.memory_layout_breadcrumbs.is_empty());
 
        debug_assert!(self.size_alignment_stack.is_empty());
 

	
 
        let (ptr_size, ptr_align) = self.mono_types[arch.pointer_type_id.0 as usize].get_size_alignment().unwrap();
 

	
 
        // Push the first entry (the type we originally started with when we
 
        // were detecting type loops)
 
        let first_entry = &self.encountered_types[0];
 
        self.memory_layout_breadcrumbs.push(MemoryBreadcrumb{
 
            type_id: first_entry.type_id,
 
            next_member: 0,
 
            next_embedded: 0,
 
            first_size_alignment_idx: 0,
 
        });
 

	
 
        // Enter the main resolving loop
 
        'breadcrumb_loop: while !self.memory_layout_breadcrumbs.is_empty() {
 
            let cur_breadcrumb_idx = self.memory_layout_breadcrumbs.len() - 1;
 
            let mut breadcrumb = self.memory_layout_breadcrumbs[cur_breadcrumb_idx].clone();
 

	
 
            let mono_type = &self.mono_types[breadcrumb.type_id.0 as usize];
 
            match &mono_type.variant {
 
                MonoTypeVariant::Builtin | MonoTypeVariant::Enum => {
 
                    // Size should already be computed
 
                    dbg_code!({
 
                        let mono_type = &self.mono_types[breadcrumb.type_id.0 as usize];
 
                        debug_assert!(mono_type.size != 0 && mono_type.alignment != 0);
 
                    });
 
                },
 
                MonoTypeVariant::Union(mono_type) => {
 
                    // Retrieve size/alignment of each embedded type. We do not
 
                    // compute the offsets or total type sizes yet.
 
                    let num_variants = mono_type.variants.len() as u32;
 
                    while breadcrumb.next_member < num_variants {
 
                        let mono_variant = &mono_type.variants[breadcrumb.next_member as usize];
 

	
 
                        if mono_variant.lives_on_heap {
 
                            // To prevent type loops we made this a heap-
 
                            // allocated variant. This implies we cannot
 
                            // compute sizes of members at this point.
 
                        } else {
 
                            let num_embedded = mono_variant.embedded.len() as u32;
 
                            while breadcrumb.next_embedded < num_embedded {
 
                                let mono_embedded = &mono_variant.embedded[breadcrumb.next_embedded as usize];
 
                                let layout_result = Self::get_memory_layout_or_breadcrumb(
 
                                    &self.definition_lookup, &self.mono_type_lookup, &self.mono_types,
 
                                    &mut self.mono_search_key, arch, &mono_embedded.concrete_type.parts,
 
                                    self.size_alignment_stack.len()
 
                                );
 
                                match layout_result {
 
                                    MemoryLayoutResult::TypeExists(size, alignment) => {
 
                                        self.size_alignment_stack.push((size, alignment));
 
                                    },
 
                                    MemoryLayoutResult::PushBreadcrumb(new_breadcrumb) => {
 
                                        self.memory_layout_breadcrumbs[cur_breadcrumb_idx] = breadcrumb;
 
                                        self.memory_layout_breadcrumbs.push(new_breadcrumb);
 
                                        continue 'breadcrumb_loop;
 
                                    }
 
                                }
 

	
 
                                breadcrumb.next_embedded += 1;
 
                            }
 
                        }
 

	
 
                        breadcrumb.next_member += 1;
 
                        breadcrumb.next_embedded = 0;
 
                    }
 

	
 
                    // If here then we can at least compute the stack size of
 
                    // the type, we'll have to come back at the very end to
 
                    // fill in the heap size/alignment/offset of each heap-
 
                    // allocated variant.
 
                    let mut max_size = mono_type.tag_size;
 
                    let mut max_alignment = mono_type.tag_size;
 

	
 
                    let mono_type = &mut self.mono_types[breadcrumb.type_id.0 as usize];
 
                    let union_type = mono_type.variant.as_union_mut();
 
                    let mut size_alignment_idx = breadcrumb.first_size_alignment_idx as usize;
 

	
 
                    for variant in &mut union_type.variants {
 
                        // We're doing stack computations, so always start with
 
                        // the tag size/alignment.
 
                        let mut variant_offset = union_type.tag_size;
 
                        let mut variant_alignment = union_type.tag_size;
 

	
 
                        if variant.lives_on_heap {
 
                            // Variant lives on heap, so just a pointer
 
                            let (ptr_size, ptr_align) = arch.pointer_size_alignment;
 
                            align_offset_to(&mut variant_offset, ptr_align);
 

	
 
                            variant_offset += ptr_size;
 
                            variant_alignment = variant_alignment.max(ptr_align);
 
                        } else {
 
                            // Variant lives on stack, so walk all embedded
 
                            // types.
 
                            for embedded in &mut variant.embedded {
 
                                let (size, alignment) = self.size_alignment_stack[size_alignment_idx];
 
                                embedded.size = size;
 
                                embedded.alignment = alignment;
 
                                size_alignment_idx += 1;
 

	
 
                                align_offset_to(&mut variant_offset, alignment);
 
                                embedded.offset = variant_offset;
 

	
 
                                variant_offset += size;
 
                                variant_alignment = variant_alignment.max(alignment);
 
                            }
 
                        };
 

	
 
                        max_size = max_size.max(variant_offset);
 
                        max_alignment = max_alignment.max(variant_alignment);
 
                    }
 

	
 
                    mono_type.size = max_size;
 
                    mono_type.alignment = max_alignment;
 
                    self.size_alignment_stack.truncate(breadcrumb.first_size_alignment_idx as usize);
 
                },
 
                MonoTypeVariant::Struct(mono_type) => {
 
                    // Retrieve size and alignment of each struct member. We'll
 
                    // compute the offsets once all of those are known
 
                    let num_fields = mono_type.fields.len() as u32;
 
                    while breadcrumb.next_member < num_fields {
 
                        let mono_field = &mono_type.fields[breadcrumb.next_member as usize];
 

	
 
                        let layout_result = Self::get_memory_layout_or_breadcrumb(
 
                            &self.definition_lookup, &self.mono_type_lookup, &self.mono_types,
 
                            &mut self.mono_search_key, arch, &mono_field.concrete_type.parts,
 
                            self.size_alignment_stack.len()
 
                        );
 
                        match layout_result {
 
                            MemoryLayoutResult::TypeExists(size, alignment) => {
 
                                self.size_alignment_stack.push((size, alignment))
 
                            },
 
                            MemoryLayoutResult::PushBreadcrumb(new_breadcrumb) => {
 
                                self.memory_layout_breadcrumbs[cur_breadcrumb_idx] = breadcrumb;
 
                                self.memory_layout_breadcrumbs.push(new_breadcrumb);
 
                                continue 'breadcrumb_loop;
 
                            },
 
                        }
 

	
 
                        breadcrumb.next_member += 1;
 
                    }
 

	
 
                    // Compute offsets and size of total type
 
                    let mut cur_offset = 0;
 
                    let mut max_alignment = 1;
 

	
 
                    let mono_type = &mut self.mono_types[breadcrumb.type_id.0 as usize];
 
                    let struct_type = mono_type.variant.as_struct_mut();
 
                    let mut size_alignment_idx = breadcrumb.first_size_alignment_idx as usize;
 

	
 
                    for field in &mut struct_type.fields {
 
                        let (size, alignment) = self.size_alignment_stack[size_alignment_idx];
 
                        field.size = size;
 
                        field.alignment = alignment;
 
                        size_alignment_idx += 1;
 

	
 
                        align_offset_to(&mut cur_offset, alignment);
 
                        field.offset = cur_offset;
 

	
 
                        cur_offset += size;
 
                        max_alignment = max_alignment.max(alignment);
 
                    }
 

	
 
                    mono_type.size = cur_offset;
 
                    mono_type.alignment = max_alignment;
 
                    self.size_alignment_stack.truncate(breadcrumb.first_size_alignment_idx as usize);
 
                },
 
                MonoTypeVariant::Procedure(_) => {
 
                    unreachable!();
 
                },
 
                MonoTypeVariant::Tuple(mono_type) => {
 
                    let num_members = mono_type.members.len() as u32;
 
                    while breadcrumb.next_member < num_members {
 
                        let mono_member = &mono_type.members[breadcrumb.next_member as usize];
 
                        let layout_result = Self::get_memory_layout_or_breadcrumb(
 
                            &self.definition_lookup, &self.mono_type_lookup, &self.mono_types,
 
                            &mut self.mono_search_key, arch, &mono_member.concrete_type.parts,
 
                            self.size_alignment_stack.len()
 
                        );
 
                        match layout_result {
 
                            MemoryLayoutResult::TypeExists(size, alignment) => {
 
                                self.size_alignment_stack.push((size, alignment));
 
                            },
 
                            MemoryLayoutResult::PushBreadcrumb(new_breadcrumb) => {
 
                                self.memory_layout_breadcrumbs[cur_breadcrumb_idx] = breadcrumb;
 
                                self.memory_layout_breadcrumbs.push(new_breadcrumb);
 
                                continue 'breadcrumb_loop;
 
                            },
 
                        }
 

	
 
                        breadcrumb.next_member += 1;
 
                    }
 

	
 
                    // If here then we can compute the memory layout of the tuple.
 
                    let mut cur_offset = 0;
 
                    let mut max_alignment = 1;
 

	
 
                    let mono_type = &mut self.mono_types[breadcrumb.type_id.0 as usize];
 
                    let mono_tuple = mono_type.variant.as_tuple_mut();
 
                    let mut size_alignment_index = breadcrumb.first_size_alignment_idx as usize;
 
                    for member_index in 0..num_members {
 
                        let (member_size, member_alignment) = self.size_alignment_stack[size_alignment_index];
 
                        align_offset_to(&mut cur_offset, member_alignment);
 
                        size_alignment_index += 1;
 

	
 
                        let member = &mut mono_tuple.members[member_index as usize];
 
                        member.size = member_size;
 
                        member.alignment = member_alignment;
 
                        member.offset = cur_offset;
 

	
 
                        cur_offset += member_size;
 
                        max_alignment = max_alignment.max(member_alignment);
 
                    }
 

	
 
                    mono_type.size = cur_offset;
 
                    mono_type.alignment = max_alignment;
 
                    self.size_alignment_stack.truncate(breadcrumb.first_size_alignment_idx as usize);
 
                },
 
            }
 

	
 
            // If here, then we completely layed out the current type. So move
 
            // to the next breadcrumb
 
            self.memory_layout_breadcrumbs.pop();
 
        }
 

	
 
        debug_assert!(self.size_alignment_stack.is_empty());
 

	
 
        // If here then all types have been layed out. What remains is to
 
        // compute the sizes/alignment/offsets of the heap variants of the
 
        // unions we have encountered.
 
        for entry in &self.encountered_types {
 
            if !entry.is_union {
 
                continue;
 
            }
 

	
 
            // First pass, use buffer to store size/alignment to prevent
 
            // borrowing issues.
 
            let mono_type = self.mono_types[entry.type_id.0 as usize].variant.as_union();
 
            for variant in &mono_type.variants {
 
                if !variant.lives_on_heap {
 
                    continue;
 
                }
 

	
 
                debug_assert!(!variant.embedded.is_empty());
 

	
 
                for embedded in &variant.embedded {
 
                    let layout_result = Self::get_memory_layout_or_breadcrumb(
 
                        &self.definition_lookup, &self.mono_type_lookup, &self.mono_types,
 
                        &mut self.mono_search_key, arch, &embedded.concrete_type.parts,
 
                        self.size_alignment_stack.len()
 
                    );
 
                    match layout_result {
 
                        MemoryLayoutResult::TypeExists(size, alignment) => {
 
                            self.size_alignment_stack.push((size, alignment));
 
                        },
 
                        _ => unreachable!(), // type was not truly infinite, so type must have been found
 
                    }
 
                }
 
            }
 

	
 
            // Second pass, apply the size/alignment values in our buffer
 
            let mono_type = self.mono_types[entry.type_id.0 as usize].variant.as_union_mut();
 

	
 
            let mut max_size = 0;
 
            let mut max_alignment = 1;
 
            let mut size_alignment_idx = 0;
 

	
 
            for variant in &mut mono_type.variants {
 
                if !variant.lives_on_heap {
 
                    continue;
 
                }
 

	
 
                let mut variant_offset = 0;
 
                let mut variant_alignment = 1;
 

	
 
                for embedded in &mut variant.embedded {
 
                    let (size, alignment) = self.size_alignment_stack[size_alignment_idx];
 
                    embedded.size = size;
 
                    embedded.alignment = alignment;
 
                    size_alignment_idx += 1;
 

	
 
                    align_offset_to(&mut variant_offset, alignment);
 
                    embedded.alignment = variant_offset;
 

	
 
                    variant_offset += size;
 
                    variant_alignment = variant_alignment.max(alignment);
 
                }
 

	
 
                max_size = max_size.max(variant_offset);
 
                max_alignment = max_alignment.max(variant_alignment);
 
            }
 

	
 
            if max_size != 0 {
 
                // At least one entry lives on the heap
 
                mono_type.heap_size = max_size;
 
                mono_type.heap_alignment = max_alignment;
 
            }
 
        }
 

	
 
        // And now, we're actually, properly, done
 
        self.encountered_types.clear();
 
    }
 

	
 
    /// Attempts to compute size/alignment for the provided type. Note that this
 
    /// is called *after* type loops have been succesfully resolved. Hence we
 
    /// may assume that all monomorph entries exist, but we may not assume that
 
    /// those entries already have their size/alignment computed.
 
    // Passed parameters are messy. But need to strike balance between borrowing
 
    // and allocations in hot loops. So it is what it is.
 
    fn get_memory_layout_or_breadcrumb(
 
        definition_map: &DefinitionMap, mono_type_map: &MonoTypeMap, mono_types: &MonoTypeArray,
 
        search_key: &mut MonoSearchKey, arch: &TargetArch, parts: &[ConcreteTypePart],
 
        size_alignment_stack_len: usize,
 
    ) -> MemoryLayoutResult {
 
        use ConcreteTypePart as CTP;
 

	
 
        debug_assert!(!parts.is_empty());
 
        let (builtin_size, builtin_alignment) = match parts[0] {
 
            CTP::Void   => (0, 1),
 
            CTP::Message => arch.array_size_alignment,
 
            CTP::Bool   => (1, 1),
 
            CTP::UInt8  => (1, 1),
 
            CTP::UInt16 => (2, 2),
 
            CTP::UInt32 => (4, 4),
 
            CTP::UInt64 => (8, 8),
 
            CTP::SInt8  => (1, 1),
 
            CTP::SInt16 => (2, 2),
 
            CTP::SInt32 => (4, 4),
 
            CTP::SInt64 => (8, 8),
 
            CTP::Character => (4, 4),
 
            CTP::String => arch.string_size_alignment,
 
            CTP::Array => arch.array_size_alignment,
 
            CTP::Slice => arch.array_size_alignment,
 
            CTP::Input => arch.port_size_alignment,
 
            CTP::Output => arch.port_size_alignment,
 
        let type_id = match parts[0] {
 
            CTP::Void      => arch.void_type_id,
 
            CTP::Message   => arch.message_type_id,
 
            CTP::Bool      => arch.bool_type_id,
 
            CTP::UInt8     => arch.uint8_type_id,
 
            CTP::UInt16    => arch.uint16_type_id,
 
            CTP::UInt32    => arch.uint32_type_id,
 
            CTP::UInt64    => arch.uint64_type_id,
 
            CTP::SInt8     => arch.sint8_type_id,
 
            CTP::SInt16    => arch.sint16_type_id,
 
            CTP::SInt32    => arch.sint32_type_id,
 
            CTP::SInt64    => arch.sint64_type_id,
 
            CTP::Character => arch.char_type_id,
 
            CTP::String    => arch.string_type_id,
 
            CTP::Array     => arch.array_type_id,
 
            CTP::Slice     => arch.slice_type_id,
 
            CTP::Input     => arch.input_type_id,
 
            CTP::Output    => arch.output_type_id,
 
            CTP::Pointer   => arch.pointer_type_id,
 
            CTP::Tuple(_) => {
 
                Self::set_search_key_to_tuple(search_key, definition_map, parts);
 
                let type_id = mono_type_map.get(&search_key).copied().unwrap();
 
                let mono_type = &mono_types[type_id.0 as usize];
 
                if let Some((size, alignment)) = mono_type.get_size_alignment() {
 
                    return MemoryLayoutResult::TypeExists(size, alignment);
 
                } else {
 
                    return MemoryLayoutResult::PushBreadcrumb(MemoryBreadcrumb{
 
                        type_id,
 
                        next_member: 0,
 
                        next_embedded: 0,
 
                        first_size_alignment_idx: size_alignment_stack_len as u32,
 
                    })
 
                }
 

	
 
                type_id
 
            },
 
            CTP::Instance(definition_id, _) => {
 
                // Retrieve entry and the specific monomorph index by applying
 
                // the full concrete type.
 
                let definition_type = definition_map.get(&definition_id).unwrap();
 
                search_key.set(parts, &definition_type.poly_vars);
 
                let type_id = mono_type_map.get(&search_key).copied().unwrap();
 
                let mono_type = &mono_types[type_id.0 as usize];
 

	
 
                if let Some((size, alignment)) = mono_type.get_size_alignment() {
 
                    return MemoryLayoutResult::TypeExists(size, alignment);
 
                } else {
 
                    return MemoryLayoutResult::PushBreadcrumb(MemoryBreadcrumb{
 
                        type_id,
 
                        next_member: 0,
 
                        next_embedded: 0,
 
                        first_size_alignment_idx: size_alignment_stack_len as u32,
 
                    });
 
                }
 
                type_id
 
            },
 
            CTP::Function(_, _) | CTP::Component(_, _) => {
 
                todo!("storage for 'function pointers'");
 
            }
 
        };
 

	
 
        return MemoryLayoutResult::TypeExists(builtin_size, builtin_alignment);
 
        let mono_type = &mono_types[type_id.0 as usize];
 
        if let Some((size, alignment)) = mono_type.get_size_alignment() {
 
            return MemoryLayoutResult::TypeExists(size, alignment);
 
        } else {
 
            return MemoryLayoutResult::PushBreadcrumb(MemoryBreadcrumb{
 
                type_id,
 
                next_member: 0,
 
                next_embedded: 0,
 
                first_size_alignment_idx: size_alignment_stack_len as u32,
 
            });
 
        }
 
    }
 

	
 
    /// Returns tag concrete type (always a builtin integer type), the size of
 
    /// that type in bytes (and implicitly, its alignment)
 
    fn variant_tag_type_from_values(min_val: i64, max_val: i64) -> (ConcreteType, usize) {
 
        debug_assert!(min_val <= max_val);
 

	
 
        let (part, size) = if min_val >= 0 {
 
            // Can be an unsigned integer
 
            if max_val <= (u8::MAX as i64) {
 
                (ConcreteTypePart::UInt8, 1)
 
            } else if max_val <= (u16::MAX as i64) {
 
                (ConcreteTypePart::UInt16, 2)
 
            } else if max_val <= (u32::MAX as i64) {
 
                (ConcreteTypePart::UInt32, 4)
 
            } else {
 
                (ConcreteTypePart::UInt64, 8)
 
            }
 
        } else {
 
            // Must be a signed integer
 
            if min_val >= (i8::MIN as i64) && max_val <= (i8::MAX as i64) {
 
                (ConcreteTypePart::SInt8, 1)
 
            } else if min_val >= (i16::MIN as i64) && max_val <= (i16::MAX as i64) {
 
                (ConcreteTypePart::SInt16, 2)
 
            } else if min_val >= (i32::MIN as i64) && max_val <= (i32::MAX as i64) {
 
                (ConcreteTypePart::SInt32, 4)
 
            } else {
 
                (ConcreteTypePart::SInt64, 8)
 
            }
 
        };
 

	
 
        return (ConcreteType{ parts: vec![part] }, size);
 
    }
 

	
 
    //--------------------------------------------------------------------------
 
    // Small utilities
 
    //--------------------------------------------------------------------------
 

	
 
    fn create_polymorphic_variables(variables: &[Identifier]) -> Vec<PolymorphicVariable> {
 
        let mut result = Vec::with_capacity(variables.len());
 
        for variable in variables.iter() {
 
            result.push(PolymorphicVariable{ identifier: variable.clone(), is_in_use: false });
 
        }
 

	
 
        result
 
    }
 

	
 
    fn mark_used_polymorphic_variables(poly_vars: &mut Vec<PolymorphicVariable>, parser_type: &ParserType) {
 
        for element in &parser_type.elements {
 
            if let ParserTypeVariant::PolymorphicArgument(_, idx) = &element.variant {
 
                poly_vars[*idx as usize].is_in_use = true;
 
            }
 
        }
 
    }
 

	
 
    /// Sets the search key. If `false` is returned then the provided type is a
 
    /// builtin type. If `true` is returned then we're dealing with a user-
 
    /// defined type.
 
    fn set_search_key_to_type(search_key: &mut MonoSearchKey, definition_map: &DefinitionMap, type_parts: &[ConcreteTypePart]) -> bool {
 
        match type_parts[0] {
 
            ConcreteTypePart::Tuple(_) => {
 
                Self::set_search_key_to_tuple(search_key, definition_map, type_parts);
 
                return true;
 
            },
 
            ConcreteTypePart::Instance(definition_id, _) => {
 
                let definition_type = definition_map.get(&definition_id).unwrap();
 
                search_key.set(type_parts, &definition_type.poly_vars);
 
                return true;
 
            },
 
            ConcreteTypePart::Function(_, _) | ConcreteTypePart::Component(_, _) => {
 
                todo!("implement function pointers")
 
            },
 
            _ => return false,
 
        }
 
    }
 

	
 
    fn set_search_key_to_tuple(search_key: &mut MonoSearchKey, definition_map: &DefinitionMap, type_parts: &[ConcreteTypePart]) {
 
        dbg_code!({
 
            let is_tuple = if let ConcreteTypePart::Tuple(_) = type_parts[0] { true } else { false };
 
            assert!(is_tuple);
 
        });
 
        search_key.set_top_type(type_parts[0]);
 
        for subtree in ConcreteTypeIter::new(type_parts, 0) {
 
            if let Some(definition_id) = get_concrete_type_definition(subtree) {
 
                // A definition, so retrieve poly var usage info
 
                let definition_type = definition_map.get(&definition_id).unwrap();
 
                search_key.push_subtree(subtree, &definition_type.poly_vars);
 
            } else {
 
                // Not a definition, so all type information is important
 
                search_key.push_subtype(subtree, true);
 
            }
 
        }
 
    }
 
}
 

	
 
#[inline]
 
fn align_offset_to(offset: &mut usize, alignment: usize) {
 
    debug_assert!(alignment > 0);
 
    let alignment_min_1 = alignment - 1;
 
    *offset += alignment_min_1;
 
    *offset &= !(alignment_min_1);
 
}
 

	
 
#[inline]
 
fn get_concrete_type_definition(concrete_parts: &[ConcreteTypePart]) -> Option<DefinitionId> {
 
    match concrete_parts[0] {
 
        ConcreteTypePart::Instance(definition_id, _) |
 
        ConcreteTypePart::Function(definition_id, _) |
 
        ConcreteTypePart::Component(definition_id, _) => {
 
            return Some(definition_id);
 
        },
 
        _ => {
 
            return None;
 
        },
 
    }
 
}
 
\ No newline at end of file
0 comments (0 inline, 0 general)