Changeset - e2849e9bfb16
[Not reviewed]
0 9 0
mh - 4 years ago 2021-05-05 12:00:13
contact@maxhenger.nl
moving to desktop
6 files changed:
0 comments (0 inline, 0 general)
src/collections/scoped_buffer.rs
Show inline comments
 
/// scoped_buffer.rs
 
///
 
/// Solves the common pattern where we are performing some kind of recursive
 
/// pattern while using a temporary buffer. At the start, or during the
 
/// procedure, we push stuff into the buffer. At the end we take out what we
 
/// have put in.
 
///
 
/// It is unsafe because we're using pointers to circumvent borrowing rules in
 
/// the name of code cleanliness. The correctness of use is checked in debug
 
/// mode.
 

	
 
use std::iter::FromIterator;
 

	
 
pub(crate) struct ScopedBuffer<T: Sized> {
 
    pub inner: Vec<T>,
 
}
 

	
 
/// A section of the buffer. Keeps track of where we started the section. When
 
/// done with the section one must call `into_vec` or `forget` to remove the
 
/// section from the underlying buffer. This will also be done upon dropping the
 
/// ScopedSection in case errors are being handled.
 
pub(crate) struct ScopedSection<T: Sized> {
 
    inner: *mut Vec<T>,
 
    start_size: u32,
 
    #[cfg(debug_assertions)] cur_size: u32,
 
}
 

	
 
impl<T: Sized> ScopedBuffer<T> {
 
    pub(crate) fn new_reserved(capacity: usize) -> Self {
 
        Self { inner: Vec::with_capacity(capacity) }
 
    }
 

	
 
    pub(crate) fn start_section(&mut self) -> ScopedSection<T> {
 
        let start_size = self.inner.len() as u32;
 
        ScopedSection {
 
            inner: &mut self.inner,
 
            start_size,
 
            cur_size: start_size
 
        }
 
    }
 
}
 

	
 
impl<T: Clone> ScopedBuffer<T> {
 
    pub(crate) fn start_section_initialized(&mut self, initialize_with: &[T]) -> ScopedSection<T> {
 
        let start_size = self.inner.len() as u32;
 
        let data_size = initialize_with.len() as u32;
 
        self.inner.extend_from_slice(initialize_with);
 
        ScopedSection{
 
            inner: &mut self.inner,
 
            start_size,
 
            cur_size: start_size + data_size,
 
        }
 
    }
 
}
 

	
 
#[cfg(debug_assertions)]
 
impl<T: Sized> Drop for ScopedBuffer<T> {
 
    fn drop(&mut self) {
 
        // Make sure that everyone cleaned up the buffer neatly
 
        debug_assert!(self.inner.is_empty(), "dropped non-empty scoped buffer");
 
    }
 
}
 

	
 
impl<T: Sized> ScopedSection<T> {
 
    #[inline]
 
    pub(crate) fn push(&mut self, value: T) {
 
        let vec = unsafe{&mut *self.inner};
 
        debug_assert_eq!(vec.len(), self.cur_size as usize, "trying to push onto section, but size is larger than expected");
 
        vec.push(value);
 
        if cfg!(debug_assertions) { self.cur_size += 1; }
 
    }
 

	
 
    pub(crate) fn len(&self) -> usize {
 
        let vec = unsafe{&mut *self.inner};
 
        debug_assert_eq!(vec.len(), self.cur_size as usize, "trying to get section length, but size is larger than expected");
 
        return vec.len() - self.start_size as usize;
 
    }
 

	
 
    #[inline]
 
    pub(crate) fn forget(mut self) {
 
        let vec = unsafe{&mut *self.inner};
 
        if cfg!(debug_assertions) {
 
            debug_assert_eq!(
 
                vec.len(), self.cur_size as usize,
 
                "trying to forget section, but size is larger than expected"
 
            );
 
            self.cur_size = self.start_size;
 
        }
 
        vec.truncate(self.start_size as usize);
 
    }
 

	
 
    #[inline]
 
    pub(crate) fn into_vec(mut self) -> Vec<T> {
 
        let vec = unsafe{&mut *self.inner};
 
        if cfg!(debug_assertions) {
 
            debug_assert_eq!(
 
                vec.len(), self.cur_size as usize,
 
                "trying to turn section into vec, but size is larger than expected"
 
            );
 
            self.cur_size = self.start_size;
 
        }
 
        let section = Vec::from_iter(vec.drain(self.start_size as usize..));
 
        section
 
    }
 
}
 

	
 
impl<T: Sized> std::ops::Index<usize> for ScopedSection<T> {
 
    type Output = T;
 

	
 
    fn index(&self, idx: usize) -> &Self::Output {
 
        let vec = unsafe{&*self.inner};
 
        return &vec[self.start_size as usize + idx]
 
    }
 
}
 

	
 
#[cfg(debug_assertions)]
 
impl<T: Sized> Drop for ScopedSection<T> {
 
    fn drop(&mut self) {
 
        let mut vec = unsafe{&mut *self.inner};
 
        let vec = unsafe{&mut *self.inner};
 
        debug_assert_eq!(vec.len(), self.cur_size as usize);
 
        vec.truncate(self.start_size as usize);
 
    }
 
}
 
\ No newline at end of file
src/protocol/ast_printer.rs
Show inline comments
 
#![allow(dead_code)]
 

	
 
use std::fmt::{Debug, Display, Write};
 
use std::fmt::{Debug, Display};
 
use std::io::Write as IOWrite;
 

	
 
use super::ast::*;
 
use super::token_parsing::*;
 

	
 
const INDENT: usize = 2;
 

	
 
const PREFIX_EMPTY: &'static str = "    ";
 
const PREFIX_ROOT_ID: &'static str = "Root";
 
const PREFIX_PRAGMA_ID: &'static str = "Prag";
 
const PREFIX_IMPORT_ID: &'static str = "Imp ";
 
const PREFIX_TYPE_ANNOT_ID: &'static str = "TyAn";
 
const PREFIX_VARIABLE_ID: &'static str = "Var ";
 
const PREFIX_PARAMETER_ID: &'static str = "Par ";
 
const PREFIX_LOCAL_ID: &'static str = "Loc ";
 
const PREFIX_DEFINITION_ID: &'static str = "Def ";
 
const PREFIX_STRUCT_ID: &'static str = "DefS";
 
const PREFIX_ENUM_ID: &'static str = "DefE";
 
const PREFIX_UNION_ID: &'static str = "DefU";
 
const PREFIX_COMPONENT_ID: &'static str = "DefC";
 
const PREFIX_FUNCTION_ID: &'static str = "DefF";
 
const PREFIX_STMT_ID: &'static str = "Stmt";
 
const PREFIX_BLOCK_STMT_ID: &'static str = "SBl ";
 
const PREFIX_LOCAL_STMT_ID: &'static str = "SLoc";
 
const PREFIX_MEM_STMT_ID: &'static str = "SMem";
 
const PREFIX_CHANNEL_STMT_ID: &'static str = "SCha";
 
const PREFIX_SKIP_STMT_ID: &'static str = "SSki";
 
const PREFIX_LABELED_STMT_ID: &'static str = "SLab";
 
const PREFIX_IF_STMT_ID: &'static str = "SIf ";
 
const PREFIX_ENDIF_STMT_ID: &'static str = "SEIf";
 
const PREFIX_WHILE_STMT_ID: &'static str = "SWhi";
 
const PREFIX_ENDWHILE_STMT_ID: &'static str = "SEWh";
 
const PREFIX_BREAK_STMT_ID: &'static str = "SBre";
 
const PREFIX_CONTINUE_STMT_ID: &'static str = "SCon";
 
const PREFIX_SYNC_STMT_ID: &'static str = "SSyn";
 
const PREFIX_ENDSYNC_STMT_ID: &'static str = "SESy";
 
const PREFIX_RETURN_STMT_ID: &'static str = "SRet";
 
const PREFIX_ASSERT_STMT_ID: &'static str = "SAsr";
 
const PREFIX_GOTO_STMT_ID: &'static str = "SGot";
 
const PREFIX_NEW_STMT_ID: &'static str = "SNew";
 
const PREFIX_PUT_STMT_ID: &'static str = "SPut";
 
const PREFIX_EXPR_STMT_ID: &'static str = "SExp";
 
const PREFIX_ASSIGNMENT_EXPR_ID: &'static str = "EAsi";
 
const PREFIX_BINDING_EXPR_ID: &'static str = "EBnd";
 
const PREFIX_CONDITIONAL_EXPR_ID: &'static str = "ECnd";
 
const PREFIX_BINARY_EXPR_ID: &'static str = "EBin";
 
const PREFIX_UNARY_EXPR_ID: &'static str = "EUna";
 
const PREFIX_INDEXING_EXPR_ID: &'static str = "EIdx";
 
const PREFIX_SLICING_EXPR_ID: &'static str = "ESli";
 
const PREFIX_SELECT_EXPR_ID: &'static str = "ESel";
 
const PREFIX_LITERAL_EXPR_ID: &'static str = "ELit";
 
const PREFIX_CALL_EXPR_ID: &'static str = "ECll";
 
const PREFIX_VARIABLE_EXPR_ID: &'static str = "EVar";
 

	
 
struct KV<'a> {
 
    buffer: &'a mut String,
 
    prefix: Option<(&'static str, i32)>,
 
    indent: usize,
 
    temp_key: &'a mut String,
 
    temp_val: &'a mut String,
 
}
 

	
 
impl<'a> KV<'a> {
 
    fn new(buffer: &'a mut String, temp_key: &'a mut String, temp_val: &'a mut String, indent: usize) -> Self {
 
        temp_key.clear();
 
        temp_val.clear();
 
        KV{
 
            buffer,
 
            prefix: None,
 
            indent,
 
            temp_key,
 
            temp_val
 
        }
 
    }
 

	
 
    fn with_id(mut self, prefix: &'static str, id: i32) -> Self {
 
        self.prefix = Some((prefix, id));
 
        self
 
    }
 

	
 
    fn with_s_key(self, key: &str) -> Self {
 
        self.temp_key.push_str(key);
 
        self
 
    }
 

	
 
    fn with_d_key<D: Display>(self, key: &D) -> Self {
 
        self.temp_key.push_str(&key.to_string());
 
        self
 
    }
 

	
 
    fn with_s_val(self, val: &str) -> Self {
 
        self.temp_val.push_str(val);
 
        self
 
    }
 

	
 
    fn with_disp_val<D: Display>(self, val: &D) -> Self {
 
        self.temp_val.push_str(&format!("{}", val));
 
        self
 
    }
 

	
 
    fn with_debug_val<D: Debug>(self, val: &D) -> Self {
 
        self.temp_val.push_str(&format!("{:?}", val));
 
        self
 
    }
 

	
 
    fn with_identifier_val(self, val: &Identifier) -> Self {
 
        self.temp_val.push_str(val.value.as_str());
 
        self
 
    }
 

	
 
    fn with_opt_disp_val<D: Display>(self, val: Option<&D>) -> Self {
 
        match val {
 
            Some(v) => { self.temp_val.push_str(&format!("Some({})", v)); },
 
            None => { self.temp_val.push_str("None"); }
 
        }
 
        self
 
    }
 

	
 
    fn with_opt_identifier_val(self, val: Option<&Identifier>) -> Self {
 
        match val {
 
            Some(v) => {
 
                self.temp_val.push_str("Some(");
 
                self.temp_val.push_str(v.value.as_str());
 
                self.temp_val.push(')');
 
            },
 
            None => {
 
                self.temp_val.push_str("None");
 
            }
 
        }
 
        self
 
    }
 

	
 
    fn with_custom_val<F: Fn(&mut String)>(mut self, val_fn: F) -> Self {
 
        val_fn(&mut self.temp_val);
 
        self
 
    }
 
}
 

	
 
impl<'a> Drop for KV<'a> {
 
    fn drop(&mut self) {
 
        // Prefix and indent
 
        if let Some((prefix, id)) = &self.prefix {
 
            self.buffer.push_str(&format!("{}[{:04}]", prefix, id));
 
        } else {
 
            self.buffer.push_str("           ");
 
        }
 

	
 
        for _ in 0..self.indent * INDENT {
 
            self.buffer.push(' ');
 
        }
 

	
 
        // Leading dash
 
        self.buffer.push_str("- ");
 

	
 
        // Key and value
 
        self.buffer.push_str(self.temp_key);
 
        if self.temp_val.is_empty() {
 
            self.buffer.push(':');
 
        } else {
 
            self.buffer.push_str(": ");
 
            self.buffer.push_str(&self.temp_val);
 
        }
 
        self.buffer.push('\n');
 
    }
 
}
 

	
 
pub(crate) struct ASTWriter {
 
    cur_definition: Option<DefinitionId>,
 
    buffer: String,
 
    temp1: String,
 
    temp2: String,
 
}
 

	
 
impl ASTWriter {
 
    pub(crate) fn new() -> Self {
 
        Self{
 
            cur_definition: None,
 
            buffer: String::with_capacity(4096),
 
            temp1: String::with_capacity(256),
 
            temp2: String::with_capacity(256),
 
        }
 
    }
 
    pub(crate) fn write_ast<W: IOWrite>(&mut self, w: &mut W, heap: &Heap) {
 
        for root_id in heap.protocol_descriptions.iter().map(|v| v.this) {
 
            self.write_module(heap, root_id);
 
            w.write_all(self.buffer.as_bytes()).expect("flush buffer");
 
            self.buffer.clear();
 
        }
 
    }
 

	
 
    //--------------------------------------------------------------------------
 
    // Top-level module writing
 
    //--------------------------------------------------------------------------
 

	
 
    fn write_module(&mut self, heap: &Heap, root_id: RootId) {
 
        self.kv(0).with_id(PREFIX_ROOT_ID, root_id.index)
 
            .with_s_key("Module");
 

	
 
        let root = &heap[root_id];
 
        self.kv(1).with_s_key("Pragmas");
 
        for pragma_id in &root.pragmas {
 
            self.write_pragma(heap, *pragma_id, 2);
 
        }
 

	
 
        self.kv(1).with_s_key("Imports");
 
        for import_id in &root.imports {
 
            self.write_import(heap, *import_id, 2);
 
        }
 

	
 
        self.kv(1).with_s_key("Definitions");
 
        for def_id in &root.definitions {
 
            self.write_definition(heap, *def_id, 2);
 
        }
 
    }
 

	
 
    fn write_pragma(&mut self, heap: &Heap, pragma_id: PragmaId, indent: usize) {
 
        match &heap[pragma_id] {
 
            Pragma::Version(pragma) => {
 
                self.kv(indent).with_id(PREFIX_PRAGMA_ID, pragma.this.index)
 
                    .with_s_key("PragmaVersion")
 
                    .with_disp_val(&pragma.version);
 
            },
 
            Pragma::Module(pragma) => {
 
                self.kv(indent).with_id(PREFIX_PRAGMA_ID, pragma.this.index)
 
                    .with_s_key("PragmaModule")
 
                    .with_identifier_val(&pragma.value);
 
            }
 
        }
 
    }
 

	
 
    fn write_import(&mut self, heap: &Heap, import_id: ImportId, indent: usize) {
 
        let import = &heap[import_id];
 
        let indent2 = indent + 1;
 

	
 
        match import {
 
            Import::Module(import) => {
 
                self.kv(indent).with_id(PREFIX_IMPORT_ID, import.this.index)
 
                    .with_s_key("ImportModule");
 

	
 
                self.kv(indent2).with_s_key("Name").with_identifier_val(&import.module);
 
                self.kv(indent2).with_s_key("Alias").with_identifier_val(&import.alias);
 
                self.kv(indent2).with_s_key("Target").with_disp_val(&import.module_id.index);
 
            },
 
            Import::Symbols(import) => {
 
                self.kv(indent).with_id(PREFIX_IMPORT_ID, import.this.index)
 
                    .with_s_key("ImportSymbol");
 

	
 
                self.kv(indent2).with_s_key("Name").with_identifier_val(&import.module);
 
                self.kv(indent2).with_s_key("Target").with_disp_val(&import.module_id.index);
 

	
 
                self.kv(indent2).with_s_key("Symbols");
 

	
 
                let indent3 = indent2 + 1;
 
                let indent4 = indent3 + 1;
 
                for symbol in &import.symbols {
 
                    self.kv(indent3).with_s_key("AliasedSymbol");
 
                    self.kv(indent4).with_s_key("Name").with_identifier_val(&symbol.name);
 
                    self.kv(indent4).with_s_key("Alias").with_opt_identifier_val(symbol.alias.as_ref());
 
                    self.kv(indent4).with_s_key("Definition").with_disp_val(&symbol.definition_id.index);
 
                }
 
            }
 
        }
 
    }
 

	
 
    //--------------------------------------------------------------------------
 
    // Top-level definition writing
 
    //--------------------------------------------------------------------------
 

	
 
    fn write_definition(&mut self, heap: &Heap, def_id: DefinitionId, indent: usize) {
 
        self.cur_definition = Some(def_id);
 
        let indent2 = indent + 1;
 
        let indent3 = indent2 + 1;
 
        let indent4 = indent3 + 1;
 

	
 
        match &heap[def_id] {
 
            Definition::Struct(def) => {
 
                self.kv(indent).with_id(PREFIX_STRUCT_ID, def.this.0.index)
 
                    .with_s_key("DefinitionStruct");
 

	
 
                self.kv(indent2).with_s_key("Name").with_identifier_val(&def.identifier);
 
                for poly_var_id in &def.poly_vars {
 
                    self.kv(indent3).with_s_key("PolyVar").with_identifier_val(&poly_var_id);
 
                }
 

	
 
                self.kv(indent2).with_s_key("Fields");
 
                for field in &def.fields {
 
                    self.kv(indent3).with_s_key("Field");
 
                    self.kv(indent4).with_s_key("Name")
 
                        .with_identifier_val(&field.field);
 
                    self.kv(indent4).with_s_key("Type")
 
                        .with_custom_val(|s| write_parser_type(s, heap, &field.parser_type));
 
                }
 
            },
 
            Definition::Enum(def) => {
 
                self.kv(indent).with_id(PREFIX_ENUM_ID, def.this.0.index)
 
                    .with_s_key("DefinitionEnum");
 

	
 
                self.kv(indent2).with_s_key("Name").with_identifier_val(&def.identifier);
 
                for poly_var_id in &def.poly_vars {
 
                    self.kv(indent3).with_s_key("PolyVar").with_identifier_val(&poly_var_id);
 
                }
 

	
 
                self.kv(indent2).with_s_key("Variants");
 
                for variant in &def.variants {
 
                    self.kv(indent3).with_s_key("Variant");
 
                    self.kv(indent4).with_s_key("Name")
 
                        .with_identifier_val(&variant.identifier);
 
                    let variant_value = self.kv(indent4).with_s_key("Value");
 
                    match &variant.value {
 
                        EnumVariantValue::None => variant_value.with_s_val("None"),
 
                        EnumVariantValue::Integer(value) => variant_value.with_disp_val(value),
 
                    };
 
                }
 
            },
 
            Definition::Union(def) => {
 
                self.kv(indent).with_id(PREFIX_UNION_ID, def.this.0.index)
 
                    .with_s_key("DefinitionUnion");
 

	
 
                self.kv(indent2).with_s_key("Name").with_identifier_val(&def.identifier);
 
                for poly_var_id in &def.poly_vars {
 
                    self.kv(indent3).with_s_key("PolyVar").with_identifier_val(&poly_var_id);
 
                }
 

	
 
                self.kv(indent2).with_s_key("Variants");
 
                for variant in &def.variants {
 
                    self.kv(indent3).with_s_key("Variant");
 
                    self.kv(indent4).with_s_key("Name")
 
                        .with_identifier_val(&variant.identifier);
 
                        
 
                    match &variant.value {
 
                        UnionVariantValue::None => {
 
                            self.kv(indent4).with_s_key("Value").with_s_val("None");
 
                        }
 
                        UnionVariantValue::Embedded(embedded) => {
 
                            self.kv(indent4).with_s_key("Values");
 
                            for embedded in embedded {
 
                                self.kv(indent4+1).with_s_key("Value")
 
                                    .with_custom_val(|v| write_parser_type(v, heap, embedded));
 
                            }
 
                        }
 
                    }
 
                }
 
            }
 
            Definition::Function(def) => {
 
                self.kv(indent).with_id(PREFIX_FUNCTION_ID, def.this.0.index)
 
                    .with_s_key("DefinitionFunction");
 

	
 
                self.kv(indent2).with_s_key("Name").with_identifier_val(&def.identifier);
 
                for poly_var_id in &def.poly_vars {
 
                    self.kv(indent3).with_s_key("PolyVar").with_identifier_val(&poly_var_id);
 
                }
 

	
 
                self.kv(indent2).with_s_key("ReturnParserTypes");
 
                for return_type in &def.return_types {
 
                    self.kv(indent3).with_s_key("ReturnParserType")
 
                        .with_custom_val(|s| write_parser_type(s, heap, return_type));
 
                }
 

	
 
                self.kv(indent2).with_s_key("Parameters");
 
                for param_id in &def.parameters {
 
                    self.write_parameter(heap, *param_id, indent3);
 
                }
 

	
 
                self.kv(indent2).with_s_key("Body");
 
                self.write_stmt(heap, def.body.upcast(), indent3);
 
            },
 
            Definition::Component(def) => {
 
                self.kv(indent).with_id(PREFIX_COMPONENT_ID,def.this.0.index)
 
                    .with_s_key("DefinitionComponent");
 

	
 
                self.kv(indent2).with_s_key("Name").with_identifier_val(&def.identifier);
 
                self.kv(indent2).with_s_key("Variant").with_debug_val(&def.variant);
 

	
 
                self.kv(indent2).with_s_key("PolymorphicVariables");
 
                for poly_var_id in &def.poly_vars {
 
                    self.kv(indent3).with_s_key("PolyVar").with_identifier_val(&poly_var_id);
 
                }
 

	
 
                self.kv(indent2).with_s_key("Parameters");
 
                for param_id in &def.parameters {
 
                    self.write_parameter(heap, *param_id, indent3)
 
                }
 

	
 
                self.kv(indent2).with_s_key("Body");
 
                self.write_stmt(heap, def.body.upcast(), indent3);
 
            }
 
        }
 
    }
 

	
 
    fn write_parameter(&mut self, heap: &Heap, param_id: ParameterId, indent: usize) {
 
        let indent2 = indent + 1;
 
        let param = &heap[param_id];
 

	
 
        self.kv(indent).with_id(PREFIX_PARAMETER_ID, param_id.0.index)
 
            .with_s_key("Parameter");
 
        self.kv(indent2).with_s_key("Name").with_identifier_val(&param.identifier);
 
        self.kv(indent2).with_s_key("ParserType").with_custom_val(|w| write_parser_type(w, heap, &param.parser_type));
 
    }
 

	
 
    fn write_stmt(&mut self, heap: &Heap, stmt_id: StatementId, indent: usize) {
 
        let stmt = &heap[stmt_id];
 
        let indent2 = indent + 1;
 
        let indent3 = indent2 + 1;
 

	
 
        match stmt {
 
            Statement::Block(stmt) => {
 
                self.kv(indent).with_id(PREFIX_BLOCK_STMT_ID, stmt.this.0.index)
 
                    .with_s_key("Block");
 

	
 
                for stmt_id in &stmt.statements {
 
                    self.write_stmt(heap, *stmt_id, indent2);
 
                }
 
            },
 
            Statement::Local(stmt) => {
 
                match stmt {
 
                    LocalStatement::Channel(stmt) => {
 
                        self.kv(indent).with_id(PREFIX_CHANNEL_STMT_ID, stmt.this.0.0.index)
 
                            .with_s_key("LocalChannel");
 

	
 
                        self.kv(indent2).with_s_key("From");
 
                        self.write_local(heap, stmt.from, indent3);
 
                        self.kv(indent2).with_s_key("To");
 
                        self.write_local(heap, stmt.to, indent3);
 
                        self.kv(indent2).with_s_key("Next")
 
                            .with_opt_disp_val(stmt.next.as_ref().map(|v| &v.index));
 
                    },
 
                    LocalStatement::Memory(stmt) => {
 
                        self.kv(indent).with_id(PREFIX_MEM_STMT_ID, stmt.this.0.0.index)
 
                            .with_s_key("LocalMemory");
 

	
 
                        self.kv(indent2).with_s_key("Variable");
 
                        self.write_local(heap, stmt.variable, indent3);
 
                        self.kv(indent2).with_s_key("Next")
 
                            .with_opt_disp_val(stmt.next.as_ref().map(|v| &v.index));
 
                    }
 
                }
 
            },
 
            Statement::Labeled(stmt) => {
 
                self.kv(indent).with_id(PREFIX_LABELED_STMT_ID, stmt.this.0.index)
 
                    .with_s_key("Labeled");
 

	
 
                self.kv(indent2).with_s_key("Label").with_identifier_val(&stmt.label);
 
                self.kv(indent2).with_s_key("Statement");
 
                self.write_stmt(heap, stmt.body, indent3);
 
            },
 
            Statement::If(stmt) => {
 
                self.kv(indent).with_id(PREFIX_IF_STMT_ID, stmt.this.0.index)
 
                    .with_s_key("If");
 

	
 
                self.kv(indent2).with_s_key("EndIf")
 
                    .with_opt_disp_val(stmt.end_if.as_ref().map(|v| &v.0.index));
 

	
 
                self.kv(indent2).with_s_key("Condition");
 
                self.write_expr(heap, stmt.test, indent3);
 

	
 
                self.kv(indent2).with_s_key("TrueBody");
 
                self.write_stmt(heap, stmt.true_body.upcast(), indent3);
 

	
 
                if let Some(false_body) = stmt.false_body {
 
                    self.kv(indent2).with_s_key("FalseBody");
 
                    self.write_stmt(heap, false_body.upcast(), indent3);
 
                }
 
            },
 
            Statement::EndIf(stmt) => {
 
                self.kv(indent).with_id(PREFIX_ENDIF_STMT_ID, stmt.this.0.index)
 
                    .with_s_key("EndIf");
 
                self.kv(indent2).with_s_key("StartIf").with_disp_val(&stmt.start_if.0.index);
 
                self.kv(indent2).with_s_key("Next")
 
                    .with_opt_disp_val(stmt.next.as_ref().map(|v| &v.index));
 
            },
 
            Statement::While(stmt) => {
 
                self.kv(indent).with_id(PREFIX_WHILE_STMT_ID, stmt.this.0.index)
 
                    .with_s_key("While");
 

	
 
                self.kv(indent2).with_s_key("EndWhile")
 
                    .with_opt_disp_val(stmt.end_while.as_ref().map(|v| &v.0.index));
 
                self.kv(indent2).with_s_key("InSync")
 
                    .with_opt_disp_val(stmt.in_sync.as_ref().map(|v| &v.0.index));
 
                self.kv(indent2).with_s_key("Condition");
 
                self.write_expr(heap, stmt.test, indent3);
 
                self.kv(indent2).with_s_key("Body");
 
                self.write_stmt(heap, stmt.body.upcast(), indent3);
 
            },
 
            Statement::EndWhile(stmt) => {
 
                self.kv(indent).with_id(PREFIX_ENDWHILE_STMT_ID, stmt.this.0.index)
 
                    .with_s_key("EndWhile");
 
                self.kv(indent2).with_s_key("StartWhile").with_disp_val(&stmt.start_while.0.index);
 
                self.kv(indent2).with_s_key("Next")
 
                    .with_opt_disp_val(stmt.next.as_ref().map(|v| &v.index));
 
            },
 
            Statement::Break(stmt) => {
 
                self.kv(indent).with_id(PREFIX_BREAK_STMT_ID, stmt.this.0.index)
 
                    .with_s_key("Break");
 
                self.kv(indent2).with_s_key("Label")
 
                    .with_opt_identifier_val(stmt.label.as_ref());
 
                self.kv(indent2).with_s_key("Target")
 
                    .with_opt_disp_val(stmt.target.as_ref().map(|v| &v.0.index));
 
            },
 
            Statement::Continue(stmt) => {
 
                self.kv(indent).with_id(PREFIX_CONTINUE_STMT_ID, stmt.this.0.index)
 
                    .with_s_key("Continue");
 
                self.kv(indent2).with_s_key("Label")
 
                    .with_opt_identifier_val(stmt.label.as_ref());
 
                self.kv(indent2).with_s_key("Target")
 
                    .with_opt_disp_val(stmt.target.as_ref().map(|v| &v.0.index));
 
            },
 
            Statement::Synchronous(stmt) => {
 
                self.kv(indent).with_id(PREFIX_SYNC_STMT_ID, stmt.this.0.index)
 
                    .with_s_key("Synchronous");
 
                self.kv(indent2).with_s_key("EndSync")
 
                    .with_opt_disp_val(stmt.end_sync.as_ref().map(|v| &v.0.index));
 
                self.kv(indent2).with_s_key("Body");
 
                self.write_stmt(heap, stmt.body.upcast(), indent3);
 
            },
 
            Statement::EndSynchronous(stmt) => {
 
                self.kv(indent).with_id(PREFIX_ENDSYNC_STMT_ID, stmt.this.0.index)
 
                    .with_s_key("EndSynchronous");
 
                self.kv(indent2).with_s_key("StartSync").with_disp_val(&stmt.start_sync.0.index);
 
                self.kv(indent2).with_s_key("Next")
 
                    .with_opt_disp_val(stmt.next.as_ref().map(|v| &v.index));
 
            },
 
            Statement::Return(stmt) => {
 
                self.kv(indent).with_id(PREFIX_RETURN_STMT_ID, stmt.this.0.index)
 
                    .with_s_key("Return");
 
                self.kv(indent2).with_s_key("Expressions");
 
                for expr_id in &stmt.expressions {
 
                    self.write_expr(heap, *expr_id, indent3);
 
                }
 
            },
 
            Statement::Goto(stmt) => {
 
                self.kv(indent).with_id(PREFIX_GOTO_STMT_ID, stmt.this.0.index)
 
                    .with_s_key("Goto");
 
                self.kv(indent2).with_s_key("Label").with_identifier_val(&stmt.label);
 
                self.kv(indent2).with_s_key("Target")
 
                    .with_opt_disp_val(stmt.target.as_ref().map(|v| &v.0.index));
 
            },
 
            Statement::New(stmt) => {
 
                self.kv(indent).with_id(PREFIX_NEW_STMT_ID, stmt.this.0.index)
 
                    .with_s_key("New");
 
                self.kv(indent2).with_s_key("Expression");
 
                self.write_expr(heap, stmt.expression.upcast(), indent3);
 
                self.kv(indent2).with_s_key("Next")
 
                    .with_opt_disp_val(stmt.next.as_ref().map(|v| &v.index));
 
            },
 
            Statement::Expression(stmt) => {
 
                self.kv(indent).with_id(PREFIX_EXPR_STMT_ID, stmt.this.0.index)
 
                    .with_s_key("ExpressionStatement");
 
                self.write_expr(heap, stmt.expression, indent2);
 
                self.kv(indent2).with_s_key("Next")
 
                    .with_opt_disp_val(stmt.next.as_ref().map(|v| &v.index));
 
            }
 
        }
 
    }
 

	
 
    fn write_expr(&mut self, heap: &Heap, expr_id: ExpressionId, indent: usize) {
 
        let expr = &heap[expr_id];
 
        let indent2 = indent + 1;
 
        let indent3 = indent2 + 1;
 
        let def_id = self.cur_definition.unwrap();
 

	
 
        match expr {
 
            Expression::Assignment(expr) => {
 
                self.kv(indent).with_id(PREFIX_ASSIGNMENT_EXPR_ID, expr.this.0.index)
 
                    .with_s_key("AssignmentExpr");
 
                self.kv(indent2).with_s_key("Operation").with_debug_val(&expr.operation);
 
                self.kv(indent2).with_s_key("Left");
 
                self.write_expr(heap, expr.left, indent3);
 
                self.kv(indent2).with_s_key("Right");
 
                self.write_expr(heap, expr.right, indent3);
 
                self.kv(indent2).with_s_key("Parent")
 
                    .with_custom_val(|v| write_expression_parent(v, &expr.parent));
 
                self.kv(indent2).with_s_key("ConcreteType")
 
                    .with_custom_val(|v| write_concrete_type(v, heap, def_id, &expr.concrete_type));
 
            },
 
            Expression::Binding(expr) => {
 
                self.kv(indent).with_id(PREFIX_BINARY_EXPR_ID, expr.this.0.index)
 
                    .with_s_key("BindingExpr");
 
                self.kv(indent2).with_s_key("LeftExpression");
 
                self.write_expr(heap, expr.left.upcast(), indent3);
 
                self.kv(indent2).with_s_key("RightExpression");
 
                self.write_expr(heap, expr.right, indent3);
 
                self.kv(indent2).with_s_key("Parent")
 
                    .with_custom_val(|v| write_expression_parent(v, &expr.parent));
 
                self.kv(indent2).with_s_key("ConcreteType")
 
                    .with_custom_val(|v| write_concrete_type(v, heap, def_id, &expr.concrete_type));
 
            },
 
            Expression::Conditional(expr) => {
 
                self.kv(indent).with_id(PREFIX_CONDITIONAL_EXPR_ID, expr.this.0.index)
 
                    .with_s_key("ConditionalExpr");
 
                self.kv(indent2).with_s_key("Condition");
 
                self.write_expr(heap, expr.test, indent3);
 
                self.kv(indent2).with_s_key("TrueExpression");
 
                self.write_expr(heap, expr.true_expression, indent3);
 
                self.kv(indent2).with_s_key("FalseExpression");
 
                self.write_expr(heap, expr.false_expression, indent3);
 
                self.kv(indent2).with_s_key("Parent")
 
                    .with_custom_val(|v| write_expression_parent(v, &expr.parent));
 
                self.kv(indent2).with_s_key("ConcreteType")
 
                    .with_custom_val(|v| write_concrete_type(v, heap, def_id, &expr.concrete_type));
 
            },
 
            Expression::Binary(expr) => {
 
                self.kv(indent).with_id(PREFIX_BINARY_EXPR_ID, expr.this.0.index)
 
                    .with_s_key("BinaryExpr");
 
                self.kv(indent2).with_s_key("Operation").with_debug_val(&expr.operation);
 
                self.kv(indent2).with_s_key("Left");
 
                self.write_expr(heap, expr.left, indent3);
 
                self.kv(indent2).with_s_key("Right");
 
                self.write_expr(heap, expr.right, indent3);
 
                self.kv(indent2).with_s_key("Parent")
 
                    .with_custom_val(|v| write_expression_parent(v, &expr.parent));
 
                self.kv(indent2).with_s_key("ConcreteType")
 
                    .with_custom_val(|v| write_concrete_type(v, heap, def_id, &expr.concrete_type));
 
            },
 
            Expression::Unary(expr) => {
 
                self.kv(indent).with_id(PREFIX_UNARY_EXPR_ID, expr.this.0.index)
 
                    .with_s_key("UnaryExpr");
 
                self.kv(indent2).with_s_key("Operation").with_debug_val(&expr.operation);
 
                self.kv(indent2).with_s_key("Argument");
 
                self.write_expr(heap, expr.expression, indent3);
 
                self.kv(indent2).with_s_key("Parent")
 
                    .with_custom_val(|v| write_expression_parent(v, &expr.parent));
 
                self.kv(indent2).with_s_key("ConcreteType")
 
                    .with_custom_val(|v| write_concrete_type(v, heap, def_id, &expr.concrete_type));
 
            },
 
            Expression::Indexing(expr) => {
 
                self.kv(indent).with_id(PREFIX_INDEXING_EXPR_ID, expr.this.0.index)
 
                    .with_s_key("IndexingExpr");
 
                self.kv(indent2).with_s_key("Subject");
 
                self.write_expr(heap, expr.subject, indent3);
 
                self.kv(indent2).with_s_key("Index");
 
                self.write_expr(heap, expr.index, indent3);
 
                self.kv(indent2).with_s_key("Parent")
 
                    .with_custom_val(|v| write_expression_parent(v, &expr.parent));
 
                self.kv(indent2).with_s_key("ConcreteType")
 
                    .with_custom_val(|v| write_concrete_type(v, heap, def_id, &expr.concrete_type));
 
            },
 
            Expression::Slicing(expr) => {
 
                self.kv(indent).with_id(PREFIX_SLICING_EXPR_ID, expr.this.0.index)
 
                    .with_s_key("SlicingExpr");
 
                self.kv(indent2).with_s_key("Subject");
 
                self.write_expr(heap, expr.subject, indent3);
 
                self.kv(indent2).with_s_key("FromIndex");
 
                self.write_expr(heap, expr.from_index, indent3);
 
                self.kv(indent2).with_s_key("ToIndex");
 
                self.write_expr(heap, expr.to_index, indent3);
 
                self.kv(indent2).with_s_key("Parent")
 
                    .with_custom_val(|v| write_expression_parent(v, &expr.parent));
 
                self.kv(indent2).with_s_key("ConcreteType")
 
                    .with_custom_val(|v| write_concrete_type(v, heap, def_id, &expr.concrete_type));
 
            },
 
            Expression::Select(expr) => {
 
                self.kv(indent).with_id(PREFIX_SELECT_EXPR_ID, expr.this.0.index)
 
                    .with_s_key("SelectExpr");
 
                self.kv(indent2).with_s_key("Subject");
 
                self.write_expr(heap, expr.subject, indent3);
 

	
 
                match &expr.field {
 
                    Field::Length => {
 
                        self.kv(indent2).with_s_key("Field").with_s_val("length");
 
                    },
 
                    Field::Symbolic(field) => {
 
                        self.kv(indent2).with_s_key("Field").with_identifier_val(&field.identifier);
 
                        self.kv(indent3).with_s_key("Definition").with_opt_disp_val(field.definition.as_ref().map(|v| &v.index));
 
                        self.kv(indent3).with_s_key("Index").with_disp_val(&field.field_idx);
 
                    }
 
                }
 
                self.kv(indent2).with_s_key("Parent")
 
                    .with_custom_val(|v| write_expression_parent(v, &expr.parent));
 
                self.kv(indent2).with_s_key("ConcreteType")
 
                    .with_custom_val(|v| write_concrete_type(v, heap, def_id, &expr.concrete_type));
 
            },
 
            Expression::Literal(expr) => {
 
                self.kv(indent).with_id(PREFIX_LITERAL_EXPR_ID, expr.this.0.index)
 
                    .with_s_key("LiteralExpr");
 

	
 
                let val = self.kv(indent2).with_s_key("Value");
 
                match &expr.value {
 
                    Literal::Null => { val.with_s_val("null"); },
 
                    Literal::True => { val.with_s_val("true"); },
 
                    Literal::False => { val.with_s_val("false"); },
 
                    Literal::Character(data) => { val.with_disp_val(data); },
 
                    Literal::String(data) => {
 
                        // Stupid hack
 
                        let string = String::from(data.as_str());
 
                        val.with_disp_val(&string);
 
                    },
 
                    Literal::Integer(data) => { val.with_debug_val(data); },
 
                    Literal::Struct(data) => {
 
                        val.with_s_val("Struct");
 
                        let indent4 = indent3 + 1;
 

	
 
                        self.kv(indent3).with_s_key("ParserType")
 
                            .with_custom_val(|t| write_parser_type(t, heap, &data.parser_type));
 
                        self.kv(indent3).with_s_key("Definition").with_disp_val(&data.definition.index);
 

	
 
                        for field in &data.fields {
 
                            self.kv(indent3).with_s_key("Field");
 
                            self.kv(indent4).with_s_key("Name").with_identifier_val(&field.identifier);
 
                            self.kv(indent4).with_s_key("Index").with_disp_val(&field.field_idx);
 
                            self.kv(indent4).with_s_key("ParserType");
 
                            self.write_expr(heap, field.value, indent4 + 1);
 
                        }
 
                    },
 
                    Literal::Enum(data) => {
 
                        val.with_s_val("Enum");
 

	
 
                        self.kv(indent3).with_s_key("ParserType")
 
                            .with_custom_val(|t| write_parser_type(t, heap, &data.parser_type));
 
                        self.kv(indent3).with_s_key("Definition").with_disp_val(&data.definition.index);
 
                        self.kv(indent3).with_s_key("VariantIdx").with_disp_val(&data.variant_idx);
 
                    },
 
                    Literal::Union(data) => {
 
                        val.with_s_val("Union");
 
                        let indent4 = indent3 + 1;
 

	
 
                        self.kv(indent3).with_s_key("ParserType")
 
                            .with_custom_val(|t| write_parser_type(t, heap, &data.parser_type));
 
                        self.kv(indent3).with_s_key("Definition").with_disp_val(&data.definition.index);
 
                        self.kv(indent3).with_s_key("VariantIdx").with_disp_val(&data.variant_idx);
 

	
 
                        for value in &data.values {
 
                            self.kv(indent3).with_s_key("Value");
 
                            self.write_expr(heap, *value, indent4);
 
                        }
 
                    }
 
                    Literal::Array(data) => {
 
                        val.with_s_val("Array");
 
                        let indent4 = indent3 + 1;
 

	
 
                        self.kv(indent3).with_s_key("Elements");
 
                        for expr_id in data {
 
                            self.write_expr(heap, *expr_id, indent4);
 
                        }
 
                    }
 
                }
 

	
 
                self.kv(indent2).with_s_key("Parent")
 
                    .with_custom_val(|v| write_expression_parent(v, &expr.parent));
 
                self.kv(indent2).with_s_key("ConcreteType")
 
                    .with_custom_val(|v| write_concrete_type(v, heap, def_id, &expr.concrete_type));
 
            },
 
            Expression::Call(expr) => {
 
                self.kv(indent).with_id(PREFIX_CALL_EXPR_ID, expr.this.0.index)
 
                    .with_s_key("CallExpr");
 

	
 
                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));
 
                self.kv(indent2).with_s_key("ConcreteType")
 
                    .with_custom_val(|v| write_concrete_type(v, heap, def_id, &expr.concrete_type));
 
            },
 
            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("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));
 
                self.kv(indent2).with_s_key("ConcreteType")
 
                    .with_custom_val(|v| write_concrete_type(v, heap, def_id, &expr.concrete_type));
 
            }
 
        }
 
    }
 

	
 
    fn write_local(&mut self, heap: &Heap, local_id: LocalId, indent: usize) {
 
        let local = &heap[local_id];
 
        let indent2 = indent + 1;
 

	
 
        self.kv(indent).with_id(PREFIX_LOCAL_ID, local_id.0.index)
 
            .with_s_key("Local");
 

	
 
        self.kv(indent2).with_s_key("Name").with_identifier_val(&local.identifier);
 
        self.kv(indent2).with_s_key("ParserType")
 
            .with_custom_val(|w| write_parser_type(w, heap, &local.parser_type));
 
    }
 

	
 
    //--------------------------------------------------------------------------
 
    // 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 push_bytes(target: &mut String, msg: &[u8]) {
 
        target.push_str(&String::from_utf8_lossy(msg));
 
    }
 

	
 
    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::Message => { push_bytes(target, KW_TYPE_MESSAGE); },
 
            PTV::Bool => { push_bytes(target, KW_TYPE_BOOL); },
 
            PTV::UInt8 => { push_bytes(target, KW_TYPE_UINT8); },
 
            PTV::UInt16 => { push_bytes(target, KW_TYPE_UINT16); },
 
            PTV::UInt32 => { push_bytes(target, KW_TYPE_UINT32); },
 
            PTV::UInt64 => { push_bytes(target, KW_TYPE_UINT64); },
 
            PTV::SInt8 => { push_bytes(target, KW_TYPE_SINT8); },
 
            PTV::SInt16 => { push_bytes(target, KW_TYPE_SINT16); },
 
            PTV::SInt32 => { push_bytes(target, KW_TYPE_SINT32); },
 
            PTV::SInt64 => { push_bytes(target, KW_TYPE_SINT64); },
 
            PTV::Character => { push_bytes(target, KW_TYPE_CHAR); },
 
            PTV::String => { push_bytes(target, KW_TYPE_STRING); },
 
            PTV::IntegerLiteral => { target.push_str("int_literal"); },
 
            PTV::Inferred => { push_bytes(target, KW_TYPE_INFERRED); },
 
            PTV::Array => {
 
                element_idx = write_element(target, heap, t, element_idx + 1);
 
                target.push_str("[]");
 
            },
 
            PTV::Input => {
 
                push_bytes(target, KW_TYPE_IN_PORT);
 
                target.push('<');
 
                element_idx = write_element(target, heap, t, element_idx + 1);
 
                target.push('>');
 
            },
 
            PTV::Output => {
 
                push_bytes(target, KW_TYPE_OUT_PORT);
 
                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].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);
 
}
 

	
 
// TODO: @Cleanup, this is littered at three places in the codebase
 
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::Marker(marker) => {
 
                // Marker points to polymorphic variable index
 
                let definition = &heap[def_id];
 
                let poly_var_ident = &definition.poly_vars()[*marker];
 
                target.push_str(poly_var_ident.value.as_str());
 
                idx = write_concrete_part(target, heap, def_id, t, idx + 1);
 
            },
 
            CTP::Void => target.push_str("void"),
 
            CTP::Message => target.push_str("msg"),
 
            CTP::Bool => target.push_str("bool"),
 
            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 => {
 
                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::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('>');
 
            }
 
        }
 

	
 
        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::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/parser/pass_definitions.rs
Show inline comments
 
use crate::protocol::ast::*;
 
use super::symbol_table::*;
 
use super::{Module, ModuleCompilationPhase, PassCtx};
 
use super::tokens::*;
 
use super::token_parsing::*;
 
use crate::protocol::input_source::{InputSource as InputSource, InputPosition as InputPosition, InputSpan, ParseError};
 
use crate::collections::*;
 

	
 
/// Parses all the tokenized definitions into actual AST nodes.
 
pub(crate) struct PassDefinitions {
 
    // State
 
    cur_definition: DefinitionId,
 
    // Temporary buffers of various kinds
 
    buffer: String,
 
    struct_fields: ScopedBuffer<StructFieldDefinition>,
 
    enum_variants: ScopedBuffer<EnumVariantDefinition>,
 
    union_variants: ScopedBuffer<UnionVariantDefinition>,
 
    parameters: ScopedBuffer<ParameterId>,
 
    expressions: ScopedBuffer<ExpressionId>,
 
    statements: ScopedBuffer<StatementId>,
 
    parser_types: Vec<ParserType>,
 
    parser_types: ScopedBuffer<ParserType>,
 
}
 

	
 
impl PassDefinitions {
 
    pub(crate) fn new() -> Self {
 
        Self{
 
            cur_definition: DefinitionId::new_invalid(),
 
            buffer: String::with_capacity(128),
 
            struct_fields: ScopedBuffer::new_reserved(128),
 
            enum_variants: ScopedBuffer::new_reserved(128),
 
            union_variants: ScopedBuffer::new_reserved(128),
 
            parameters: ScopedBuffer::new_reserved(128),
 
            expressions: ScopedBuffer::new_reserved(128),
 
            statements: ScopedBuffer::new_reserved(128),
 
            parser_types: Vec::with_capacity(128),
 
            parser_types: ScopedBuffer::new_reserved(128),
 
        }
 
    }
 

	
 
    pub(crate) fn parse(&mut self, modules: &mut [Module], module_idx: usize, ctx: &mut PassCtx) -> Result<(), ParseError> {
 
        let module = &modules[module_idx];
 
        let module_range = &module.tokens.ranges[0];
 
        debug_assert_eq!(module.phase, ModuleCompilationPhase::ImportsResolved);
 
        debug_assert_eq!(module_range.range_kind, TokenRangeKind::Module);
 

	
 
        // Although we only need to parse the definitions, we want to go through
 
        // code ranges as well such that we can throw errors if we get
 
        // unexpected tokens at the module level of the source.
 
        let mut range_idx = module_range.first_child_idx;
 
        loop {
 
            let range_idx_usize = range_idx as usize;
 
            let cur_range = &module.tokens.ranges[range_idx_usize];
 

	
 
            match cur_range.range_kind {
 
                TokenRangeKind::Module => unreachable!(), // should not be reachable
 
                TokenRangeKind::Pragma | TokenRangeKind::Import => continue, // already fully parsed
 
                TokenRangeKind::Definition | TokenRangeKind::Code => {}
 
            }
 

	
 
            self.visit_range(modules, module_idx, ctx, range_idx_usize)?;
 

	
 
            if cur_range.next_sibling_idx == NO_SIBLING {
 
                break;
 
            } else {
 
                range_idx = cur_range.next_sibling_idx;
 
            }
 
        }
 

	
 
        modules[module_idx].phase = ModuleCompilationPhase::DefinitionsParsed;
 

	
 
        Ok(())
 
    }
 

	
 
    fn visit_range(
 
        &mut self, modules: &[Module], module_idx: usize, ctx: &mut PassCtx, range_idx: usize
 
    ) -> Result<(), ParseError> {
 
        let module = &modules[module_idx];
 
        let cur_range = &module.tokens.ranges[range_idx];
 
        debug_assert!(cur_range.range_kind == TokenRangeKind::Definition || cur_range.range_kind == TokenRangeKind::Code);
 

	
 
        // Detect which definition we're parsing
 
        let mut iter = module.tokens.iter_range(cur_range);
 
        loop {
 
            let next = iter.next();
 
            if next.is_none() {
 
                return Ok(())
 
            }
 

	
 
            // Token was not None, so peek_ident returns None if not an ident
 
            let ident = peek_ident(&module.source, &mut iter);
 
            match ident {
 
                Some(KW_STRUCT) => self.visit_struct_definition(module, &mut iter, ctx)?,
 
                Some(KW_ENUM) => self.visit_enum_definition(module, &mut iter, ctx)?,
 
                Some(KW_UNION) => self.visit_union_definition(module, &mut iter, ctx)?,
 
                Some(KW_FUNCTION) => self.visit_function_definition(module, &mut iter, ctx)?,
 
                Some(KW_PRIMITIVE) | Some(KW_COMPOSITE) => self.visit_component_definition(module, &mut iter, ctx)?,
 
                _ => return Err(ParseError::new_error_str_at_pos(
 
                    &module.source, iter.last_valid_pos(),
 
                    "unexpected symbol, expected a keyword marking the start of a definition"
 
                )),
 
            }
 
        }
 
    }
 

	
 
    fn visit_struct_definition(
 
        &mut self, module: &Module, iter: &mut TokenIter, ctx: &mut PassCtx
 
    ) -> Result<(), ParseError> {
 
        consume_exact_ident(&module.source, iter, KW_STRUCT)?;
 
        let (ident_text, _) = consume_ident(&module.source, iter)?;
 

	
 
        // Retrieve preallocated DefinitionId
 
        let module_scope = SymbolScope::Module(module.root_id);
 
        let definition_id = ctx.symbols.get_symbol_by_name_defined_in_scope(module_scope, ident_text)
 
            .unwrap().variant.as_definition().definition_id;
 
        self.cur_definition = definition_id;
 

	
 
        // Parse struct definition
 
        consume_polymorphic_vars_spilled(&module.source, iter, ctx)?;
 

	
 
        let mut fields_section = self.struct_fields.start_section();
 
        consume_comma_separated(
 
            TokenKind::OpenCurly, TokenKind::CloseCurly, &module.source, iter, ctx,
 
            |source, iter, ctx| {
 
                let poly_vars = ctx.heap[definition_id].poly_vars(); // TODO: @Cleanup, this is really ugly. But rust...
 

	
 
                let start_pos = iter.last_valid_pos();
 
                let parser_type = consume_parser_type(
 
                    source, iter, &ctx.symbols, &ctx.heap, poly_vars, module_scope,
 
                    definition_id, false, 0
 
                )?;
 
                let field = consume_ident_interned(source, iter, ctx)?;
 
                Ok(StructFieldDefinition{
 
                    span: InputSpan::from_positions(start_pos, field.span.end),
 
                    field, parser_type
 
                })
 
            },
 
            &mut fields_section, "a struct field", "a list of struct fields", None
 
        )?;
 

	
 
        // Transfer to preallocated definition
 
        let struct_def = ctx.heap[definition_id].as_struct_mut();
 
        struct_def.fields = fields_section.into_vec();
 

	
 
        Ok(())
 
    }
 

	
 
    fn visit_enum_definition(
 
        &mut self, module: &Module, iter: &mut TokenIter, ctx: &mut PassCtx
 
    ) -> Result<(), ParseError> {
 
        consume_exact_ident(&module.source, iter, KW_ENUM)?;
 
        let (ident_text, _) = consume_ident(&module.source, iter)?;
 

	
 
        // Retrieve preallocated DefinitionId
 
        let module_scope = SymbolScope::Module(module.root_id);
 
        let definition_id = ctx.symbols.get_symbol_by_name_defined_in_scope(module_scope, ident_text)
 
            .unwrap().variant.as_definition().definition_id;
 
        self.cur_definition = definition_id;
 

	
 
        // Parse enum definition
 
        consume_polymorphic_vars_spilled(&module.source, iter, ctx)?;
 

	
 
        let mut enum_section = self.enum_variants.start_section();
 
        consume_comma_separated(
 
            TokenKind::OpenCurly, TokenKind::CloseCurly, &module.source, iter, ctx,
 
            |source, iter, ctx| {
 
                let identifier = consume_ident_interned(source, iter, ctx)?;
 
                let value = if iter.next() == Some(TokenKind::Equal) {
 
                    iter.consume();
 
                    let (variant_number, _) = consume_integer_literal(source, iter, &mut self.buffer)?;
 
                    EnumVariantValue::Integer(variant_number as i64) // TODO: @int
 
                } else {
 
                    EnumVariantValue::None
 
                };
 
                Ok(EnumVariantDefinition{ identifier, value })
 
            },
 
            &mut enum_section, "an enum variant", "a list of enum variants", None
 
        )?;
 

	
 
        // Transfer to definition
 
        let enum_def = ctx.heap[definition_id].as_enum_mut();
 
        enum_def.variants = enum_section.into_vec();
 

	
 
        Ok(())
 
    }
 

	
 
    fn visit_union_definition(
 
        &mut self, module: &Module, iter: &mut TokenIter, ctx: &mut PassCtx
 
    ) -> Result<(), ParseError> {
 
        consume_exact_ident(&module.source, iter, KW_UNION)?;
 
        let (ident_text, _) = consume_ident(&module.source, iter)?;
 

	
 
        // Retrieve preallocated DefinitionId
 
        let module_scope = SymbolScope::Module(module.root_id);
 
        let definition_id = ctx.symbols.get_symbol_by_name_defined_in_scope(module_scope, ident_text)
 
            .unwrap().variant.as_definition().definition_id;
 
        self.cur_definition = definition_id;
 

	
 
        // Parse union definition
 
        consume_polymorphic_vars_spilled(&module.source, iter, ctx)?;
 

	
 
        let mut variants_section = self.union_variants.start_section();
 
        consume_comma_separated(
 
            TokenKind::OpenCurly, TokenKind::CloseCurly, &module.source, iter, ctx,
 
            |source, iter, ctx| {
 
                let identifier = consume_ident_interned(source, iter, ctx)?;
 
                let mut close_pos = identifier.span.end;
 

	
 
                let mut types_section = self.parser_types.start_section();
 

	
 
                let has_embedded = maybe_consume_comma_separated(
 
                    TokenKind::OpenParen, TokenKind::CloseParen, source, iter, ctx,
 
                    |source, iter, ctx| {
 
                        let poly_vars = ctx.heap[definition_id].poly_vars(); // TODO: @Cleanup, this is really ugly. But rust...
 
                        consume_parser_type(
 
                            source, iter, &ctx.symbols, &ctx.heap, poly_vars,
 
                            module_scope, definition_id, false, 0
 
                        )
 
                    },
 
                    &mut self.parser_types, "an embedded type", Some(&mut close_pos)
 
                    &mut types_section, "an embedded type", Some(&mut close_pos)
 
                )?;
 
                let value = if has_embedded {
 
                    UnionVariantValue::Embedded(self.parser_types.clone())
 
                    UnionVariantValue::Embedded(types_section.into_vec())
 
                } else {
 
                    types_section.forget();
 
                    UnionVariantValue::None
 
                };
 
                self.parser_types.clear();
 

	
 
                Ok(UnionVariantDefinition{
 
                    span: InputSpan::from_positions(identifier.span.begin, close_pos),
 
                    identifier,
 
                    value
 
                })
 
            },
 
            &mut variants_section, "a union variant", "a list of union variants", None
 
        )?;
 

	
 
        // Transfer to AST
 
        let union_def = ctx.heap[definition_id].as_union_mut();
 
        union_def.variants = variants_section.into_vec();
 

	
 
        Ok(())
 
    }
 

	
 
    fn visit_function_definition(
 
        &mut self, module: &Module, iter: &mut TokenIter, ctx: &mut PassCtx
 
    ) -> Result<(), ParseError> {
 
        consume_exact_ident(&module.source, iter, KW_FUNCTION)?;
 
        let (ident_text, _) = consume_ident(&module.source, iter)?;
 

	
 
        // Retrieve preallocated DefinitionId
 
        let module_scope = SymbolScope::Module(module.root_id);
 
        let definition_id = ctx.symbols.get_symbol_by_name_defined_in_scope(module_scope, ident_text)
 
            .unwrap().variant.as_definition().definition_id;
 
        self.cur_definition = definition_id;
 

	
 
        consume_polymorphic_vars_spilled(&module.source, iter, ctx)?;
 

	
 
        // Parse function's argument list
 
        let mut parameter_section = self.parameters.start_section();
 
        consume_parameter_list(
 
            &module.source, iter, ctx, &mut parameter_section, module_scope, definition_id
 
        )?;
 
        let parameters = parameter_section.into_vec();
 

	
 
        // Consume return types
 
        consume_token(&module.source, iter, TokenKind::ArrowRight)?;
 
        let mut open_curly_pos = iter.last_valid_pos();
 
        let mut return_types = self.parser_types.start_section();
 
        let mut open_curly_pos = iter.last_valid_pos(); // bogus value
 
        consume_comma_separated_until(
 
            TokenKind::OpenCurly, &module.source, iter, ctx,
 
            |source, iter, ctx| {
 
                let poly_vars = ctx.heap[definition_id].poly_vars(); // TODO: @Cleanup, this is really ugly. But rust...
 
                consume_parser_type(source, iter, &ctx.symbols, &ctx.heap, poly_vars, module_scope, definition_id, false, 0)
 
            },
 
            &mut self.parser_types, "a return type", Some(&mut open_curly_pos)
 
            &mut return_types, "a return type", Some(&mut open_curly_pos)
 
        )?;
 
        let return_types = self.parser_types.clone();
 
        let return_types = return_types.into_vec();
 

	
 
        // TODO: @ReturnValues
 
        match return_types.len() {
 
            0 => return Err(ParseError::new_error_str_at_pos(&module.source, open_curly_pos, "expected a return type")),
 
            1 => {},
 
            _ => return Err(ParseError::new_error_str_at_pos(&module.source, open_curly_pos, "multiple return types are not (yet) allowed")),
 
        }
 

	
 
        // Consume block
 
        let body = self.consume_block_statement_without_leading_curly(module, iter, ctx, open_curly_pos)?;
 

	
 
        // Assign everything in the preallocated AST node
 
        let function = ctx.heap[definition_id].as_function_mut();
 
        function.return_types = return_types;
 
        function.parameters = parameters;
 
        function.body = body;
 

	
 
        Ok(())
 
    }
 

	
 
    fn visit_component_definition(
 
        &mut self, module: &Module, iter: &mut TokenIter, ctx: &mut PassCtx
 
    ) -> Result<(), ParseError> {
 
        let (_variant_text, _) = consume_any_ident(&module.source, iter)?;
 
        debug_assert!(_variant_text == KW_PRIMITIVE || _variant_text == KW_COMPOSITE);
 
        let (ident_text, _) = consume_ident(&module.source, iter)?;
 

	
 
        // Retrieve preallocated definition
 
        let module_scope = SymbolScope::Module(module.root_id);
 
        let definition_id = ctx.symbols.get_symbol_by_name_defined_in_scope(module_scope, ident_text)
 
            .unwrap().variant.as_definition().definition_id;
 
        self.cur_definition = definition_id;
 

	
 
        consume_polymorphic_vars_spilled(&module.source, iter, ctx)?;
 

	
 
        // Parse component's argument list
 
        let mut parameter_section = self.parameters.start_section();
 
        consume_parameter_list(
 
            &module.source, iter, ctx, &mut parameter_section, module_scope, definition_id
 
        )?;
 
        let parameters = parameter_section.into_vec();
 

	
 
        // Consume block
 
        let body = self.consume_block_statement(module, iter, ctx)?;
 

	
 
        // Assign everything in the AST node
 
        let component = ctx.heap[definition_id].as_component_mut();
 
        component.parameters = parameters;
 
        component.body = body;
 

	
 
        Ok(())
 
    }
 

	
 
    /// Consumes a block statement. If the resulting statement is not a block
 
    /// (e.g. for a shorthand "if (expr) single_statement") then it will be
 
    /// wrapped in one
 
    fn consume_block_or_wrapped_statement(
 
        &mut self, module: &Module, iter: &mut TokenIter, ctx: &mut PassCtx
 
    ) -> Result<BlockStatementId, ParseError> {
 
        if Some(TokenKind::OpenCurly) == iter.next() {
 
            // This is a block statement
 
            self.consume_block_statement(module, iter, ctx)
 
        } else {
 
            // Not a block statement, so wrap it in one
 
            let mut statements = self.statements.start_section();
 
            let wrap_begin_pos = iter.last_valid_pos();
 
            self.consume_statement(module, iter, ctx, &mut statements)?;
 
            let wrap_end_pos = iter.last_valid_pos();
 

	
 
            debug_assert_eq!(statements.len(), 1);
 
            let statements = statements.into_vec();
 

	
 
            Ok(ctx.heap.alloc_block_statement(|this| BlockStatement{
 
                this,
 
                is_implicit: true,
 
                span: InputSpan::from_positions(wrap_begin_pos, wrap_end_pos), // TODO: @Span
 
                statements,
 
                parent_scope: None,
 
                relative_pos_in_parent: 0,
 
                locals: Vec::new(),
 
                labels: Vec::new()
 
            }))
 
        }
 
    }
 

	
 
    /// Consumes a statement and returns a boolean indicating whether it was a
 
    /// block or not.
 
    fn consume_statement(
 
        &mut self, module: &Module, iter: &mut TokenIter, ctx: &mut PassCtx, section: &mut ScopedSection<StatementId>
 
    ) -> Result<(), ParseError> {
 
        let next = iter.next().expect("consume_statement has a next token");
 

	
 
        if next == TokenKind::OpenCurly {
 
            let id = self.consume_block_statement(module, iter, ctx)?;
 
            section.push(id.upcast());
 
        } else if next == TokenKind::Ident {
 
            let ident = peek_ident(&module.source, iter).unwrap();
 
            if ident == KW_STMT_IF {
 
                // Consume if statement and place end-if statement directly
 
                // after it.
 
                let id = self.consume_if_statement(module, iter, ctx)?;
 
                section.push(id.upcast());
 

	
 
                let end_if = ctx.heap.alloc_end_if_statement(|this| EndIfStatement{
 
                    this, start_if: id, next: None
 
                });
 
                section.push(id.upcast());
 

	
 
                let if_stmt = &mut ctx.heap[id];
 
                if_stmt.end_if = Some(end_if);
 
            } else if ident == KW_STMT_WHILE {
 
                let id = self.consume_while_statement(module, iter, ctx)?;
 
                section.push(id.upcast());
 

	
 
                let end_while = ctx.heap.alloc_end_while_statement(|this| EndWhileStatement{
 
                    this, start_while: id, next: None
 
                });
 
                section.push(id.upcast());
 

	
 
                let while_stmt = &mut ctx.heap[id];
 
                while_stmt.end_while = Some(end_while);
 
            } else if ident == KW_STMT_BREAK {
 
                let id = self.consume_break_statement(module, iter, ctx)?;
 
                section.push(id.upcast());
 
            } else if ident == KW_STMT_CONTINUE {
 
                let id = self.consume_continue_statement(module, iter, ctx)?;
 
                section.push(id.upcast());
 
            } else if ident == KW_STMT_SYNC {
 
                let id = self.consume_synchronous_statement(module, iter, ctx)?;
 
                section.push(id.upcast());
 

	
 
                let end_sync = ctx.heap.alloc_end_synchronous_statement(|this| EndSynchronousStatement{
 
                    this, start_sync: id, next: None
 
                });
 

	
 
                let sync_stmt = &mut ctx.heap[id];
 
                sync_stmt.end_sync = Some(end_sync);
 
            } else if ident == KW_STMT_RETURN {
 
                let id = self.consume_return_statement(module, iter, ctx)?;
 
                section.push(id.upcast());
 
            } else if ident == KW_STMT_GOTO {
 
                let id = self.consume_goto_statement(module, iter, ctx)?;
 
                section.push(id.upcast());
 
            } else if ident == KW_STMT_NEW {
 
                let id = self.consume_new_statement(module, iter, ctx)?;
 
                section.push(id.upcast());
 
            } else if ident == KW_STMT_CHANNEL {
 
                let id = self.consume_channel_statement(module, iter, ctx)?;
 
                section.push(id.upcast().upcast());
 
            } else if iter.peek() == Some(TokenKind::Colon) {
 
                self.consume_labeled_statement(module, iter, ctx, section)?;
 
            } else {
 
                // Two fallback possibilities: the first one is a memory
 
                // declaration, the other one is to parse it as a regular
 
                // expression. This is a bit ugly
 
                if let Some((memory_stmt_id, assignment_stmt_id)) = self.maybe_consume_memory_statement(module, iter, ctx)? {
 
                    section.push(memory_stmt_id.upcast().upcast());
 
                    section.push(assignment_stmt_id.upcast());
 
                } else {
 
                    let id = self.consume_expression_statement(module, iter, ctx)?;
 
                    section.push(id.upcast());
 
                }
 
            }
 
        };
 

	
 
        return Ok(());
 
    }
 

	
 
    fn consume_block_statement(
 
        &mut self, module: &Module, iter: &mut TokenIter, ctx: &mut PassCtx
 
    ) -> Result<BlockStatementId, ParseError> {
 
        let open_span = consume_token(&module.source, iter, TokenKind::OpenCurly)?;
 
        self.consume_block_statement_without_leading_curly(module, iter, ctx, open_span.begin)
 
    }
 

	
 
    fn consume_block_statement_without_leading_curly(
 
        &mut self, module: &Module, iter: &mut TokenIter, ctx: &mut PassCtx, open_curly_pos: InputPosition
 
    ) -> Result<BlockStatementId, ParseError> {
 
        let mut stmt_section = self.statements.start_section();
 
        let mut next = iter.next();
 
        while next != Some(TokenKind::CloseCurly) {
 
            if next.is_none() {
 
                return Err(ParseError::new_error_str_at_pos(
 
                    &module.source, iter.last_valid_pos(), "expected a statement or '}'"
 
                ));
 
            }
 
            self.consume_statement(module, iter, ctx, &mut stmt_section)?;
 
            next = iter.next();
 
        }
 

	
 
        let statements = stmt_section.into_vec();
 
        let mut block_span = consume_token(&module.source, iter, TokenKind::CloseCurly)?;
 
        block_span.begin = open_curly_pos;
 

	
 
        Ok(ctx.heap.alloc_block_statement(|this| BlockStatement{
 
            this,
 
            is_implicit: false,
 
            span: block_span,
 
            statements,
 
            parent_scope: None,
 
            relative_pos_in_parent: 0,
 
            locals: Vec::new(),
 
            labels: Vec::new(),
 
        }))
 
    }
 

	
 
    fn consume_if_statement(
 
        &mut self, module: &Module, iter: &mut TokenIter, ctx: &mut PassCtx
 
    ) -> Result<IfStatementId, ParseError> {
 
        let if_span = consume_exact_ident(&module.source, iter, KW_STMT_IF)?;
 
        consume_token(&module.source, iter, TokenKind::OpenParen)?;
 
        let test = self.consume_expression(module, iter, ctx)?;
 
        consume_token(&module.source, iter, TokenKind::CloseParen)?;
 
        let true_body = self.consume_block_or_wrapped_statement(module, iter, ctx)?;
 

	
 
        let false_body = if has_ident(&module.source, iter, KW_STMT_ELSE) {
 
            iter.consume();
 
            let false_body = self.consume_block_or_wrapped_statement(module, iter, ctx)?;
 
            Some(false_body)
 
        } else {
 
            None
 
        };
 

	
 
        Ok(ctx.heap.alloc_if_statement(|this| IfStatement{
 
            this,
 
            span: if_span,
 
            test,
 
            true_body,
 
            false_body,
 
            end_if: None,
 
        }))
 
    }
 

	
 
    fn consume_while_statement(
 
        &mut self, module: &Module, iter: &mut TokenIter, ctx: &mut PassCtx
 
    ) -> Result<WhileStatementId, ParseError> {
 
        let while_span = consume_exact_ident(&module.source, iter, KW_STMT_WHILE)?;
 
        consume_token(&module.source, iter, TokenKind::OpenParen)?;
 
        let test = self.consume_expression(module, iter, ctx)?;
 
        consume_token(&module.source, iter, TokenKind::CloseParen)?;
 
        let body = self.consume_block_or_wrapped_statement(module, iter, ctx)?;
 

	
 
        Ok(ctx.heap.alloc_while_statement(|this| WhileStatement{
 
            this,
 
            span: while_span,
 
            test,
 
            body,
 
            end_while: None,
 
            in_sync: None,
 
        }))
 
    }
 

	
 
    fn consume_break_statement(
 
        &mut self, module: &Module, iter: &mut TokenIter, ctx: &mut PassCtx
 
    ) -> Result<BreakStatementId, ParseError> {
 
        let break_span = consume_exact_ident(&module.source, iter, KW_STMT_BREAK)?;
 
        let label = if Some(TokenKind::Ident) == iter.next() {
 
            let label = consume_ident_interned(&module.source, iter, ctx)?;
 
            Some(label)
 
        } else {
 
            None
 
        };
 
        consume_token(&module.source, iter, TokenKind::SemiColon)?;
 
        Ok(ctx.heap.alloc_break_statement(|this| BreakStatement{
 
            this,
 
            span: break_span,
 
            label,
 
            target: None,
 
        }))
 
    }
 

	
 
    fn consume_continue_statement(
 
        &mut self, module: &Module, iter: &mut TokenIter, ctx: &mut PassCtx
 
    ) -> Result<ContinueStatementId, ParseError> {
 
        let continue_span = consume_exact_ident(&module.source, iter, KW_STMT_CONTINUE)?;
 
        let label=  if Some(TokenKind::Ident) == iter.next() {
 
            let label = consume_ident_interned(&module.source, iter, ctx)?;
 
            Some(label)
 
        } else {
 
            None
 
        };
 
        consume_token(&module.source, iter, TokenKind::SemiColon)?;
 
        Ok(ctx.heap.alloc_continue_statement(|this| ContinueStatement{
 
            this,
 
            span: continue_span,
 
            label,
 
            target: None
 
        }))
 
    }
 

	
 
    fn consume_synchronous_statement(
 
        &mut self, module: &Module, iter: &mut TokenIter, ctx: &mut PassCtx
 
    ) -> Result<SynchronousStatementId, ParseError> {
 
        let synchronous_span = consume_exact_ident(&module.source, iter, KW_STMT_SYNC)?;
 
        let body = self.consume_block_or_wrapped_statement(module, iter, ctx)?;
 

	
 
        Ok(ctx.heap.alloc_synchronous_statement(|this| SynchronousStatement{
 
            this,
 
            span: synchronous_span,
 
            body,
 
            end_sync: None,
 
            parent_scope: None,
 
        }))
 
    }
 

	
 
    fn consume_return_statement(
 
        &mut self, module: &Module, iter: &mut TokenIter, ctx: &mut PassCtx
 
    ) -> Result<ReturnStatementId, ParseError> {
 
        let return_span = consume_exact_ident(&module.source, iter, KW_STMT_RETURN)?;
 
        let mut scoped_section = self.expressions.start_section();
 

	
 
        consume_comma_separated_until(
 
            TokenKind::SemiColon, &module.source, iter, ctx,
 
            |_source, iter, ctx| self.consume_expression(module, iter, ctx),
 
            &mut scoped_section, "a return expression", None
 
        )?;
 
        let expressions = scoped_section.into_vec();
 

	
 
        if expressions.is_empty() {
 
            return Err(ParseError::new_error_str_at_span(&module.source, return_span, "expected at least one return value"));
 
        } else if expressions.len() > 1 {
 
            return Err(ParseError::new_error_str_at_span(&module.source, return_span, "multiple return values are not (yet) supported"))
 
        }
 

	
 
        Ok(ctx.heap.alloc_return_statement(|this| ReturnStatement{
 
            this,
 
            span: return_span,
 
            expressions
 
        }))
 
    }
 

	
 
    fn consume_goto_statement(
 
        &mut self, module: &Module, iter: &mut TokenIter, ctx: &mut PassCtx
 
    ) -> Result<GotoStatementId, ParseError> {
 
        let goto_span = consume_exact_ident(&module.source, iter, KW_STMT_GOTO)?;
 
        let label = consume_ident_interned(&module.source, iter, ctx)?;
 
        consume_token(&module.source, iter, TokenKind::SemiColon)?;
 
        Ok(ctx.heap.alloc_goto_statement(|this| GotoStatement{
 
            this,
 
            span: goto_span,
 
            label,
 
            target: None
 
        }))
 
    }
 

	
 
    fn consume_new_statement(
 
        &mut self, module: &Module, iter: &mut TokenIter, ctx: &mut PassCtx
 
    ) -> Result<NewStatementId, ParseError> {
 
        let new_span = consume_exact_ident(&module.source, iter, KW_STMT_NEW)?;
 

	
 
        // TODO: @Cleanup, should just call something like consume_component_expression-ish
 
        let start_pos = iter.last_valid_pos();
 
        let expression_id = self.consume_primary_expression(module, iter, ctx)?;
 
        let expression = &ctx.heap[expression_id];
 
        let mut valid = false;
 

	
 
        let mut call_id = CallExpressionId::new_invalid();
 
        if let Expression::Call(expression) = expression {
 
            // Allow both components and functions, as it makes more sense to
 
            // check their correct use in the validation and linking pass
 
            if expression.method == Method::UserComponent || expression.method == Method::UserFunction {
 
                call_id = expression.this;
 
                valid = true;
 
            }
 
        }
 

	
 
        if !valid {
 
            return Err(ParseError::new_error_str_at_span(
 
                &module.source, InputSpan::from_positions(start_pos, iter.last_valid_pos()), "expected a call expression"
 
            ));
 
        }
 
        consume_token(&module.source, iter, TokenKind::SemiColon)?;
 

	
 
        debug_assert!(!call_id.is_invalid());
 
        Ok(ctx.heap.alloc_new_statement(|this| NewStatement{
 
            this,
 
            span: new_span,
 
            expression: call_id,
 
            next: None
 
        }))
 
    }
 

	
 
    fn consume_channel_statement(
 
        &mut self, module: &Module, iter: &mut TokenIter, ctx: &mut PassCtx
 
    ) -> Result<ChannelStatementId, ParseError> {
 
        // Consume channel specification
 
        let channel_span = consume_exact_ident(&module.source, iter, KW_STMT_CHANNEL)?;
 
        let channel_type = if Some(TokenKind::OpenAngle) == iter.next() {
 
            // Retrieve the type of the channel, we're cheating a bit here by
 
            // consuming the first '<' and setting the initial angle depth to 1
 
            // such that our final '>' will be consumed as well.
 
            iter.consume();
 
            let definition_id = self.cur_definition;
 
            let poly_vars = ctx.heap[definition_id].poly_vars();
 
            consume_parser_type(
 
                &module.source, iter, &ctx.symbols, &ctx.heap,
 
                &poly_vars, SymbolScope::Module(module.root_id), definition_id,
 
                true, 1
 
            )?
 
        } else {
 
            // Assume inferred
 
            ParserType{ elements: vec![ParserTypeElement{
 
                full_span: channel_span, // TODO: @Span fix
 
                variant: ParserTypeVariant::Inferred
 
            }]}
 
        };
 

	
 
        let from_identifier = consume_ident_interned(&module.source, iter, ctx)?;
 
        consume_token(&module.source, iter, TokenKind::ArrowRight)?;
 
        let to_identifier = consume_ident_interned(&module.source, iter, ctx)?;
 
        consume_token(&module.source, iter, TokenKind::SemiColon)?;
 

	
 
        // Construct ports
 
        let from = ctx.heap.alloc_local(|this| Local{
 
            this,
 
            identifier: from_identifier,
 
            parser_type: channel_type.clone(),
 
            relative_pos_in_block: 0,
 
        });
 
        let to = ctx.heap.alloc_local(|this| Local{
 
            this,
 
            identifier: to_identifier,
 
            parser_type: channel_type,
 
            relative_pos_in_block: 0,
 
        });
 

	
 
        // Construct the channel
 
        Ok(ctx.heap.alloc_channel_statement(|this| ChannelStatement{
 
            this,
 
            span: channel_span,
 
            from, to,
 
            relative_pos_in_block: 0,
 
            next: None,
 
        }))
 
    }
 

	
 
    fn consume_labeled_statement(
 
        &mut self, module: &Module, iter: &mut TokenIter, ctx: &mut PassCtx, section: &mut ScopedSection<StatementId>
 
    ) -> Result<(), ParseError> {
 
        let label = consume_ident_interned(&module.source, iter, ctx)?;
 
        consume_token(&module.source, iter, TokenKind::Colon)?;
 

	
 
        // Not pretty: consume_statement may produce more than one statement.
 
        // The values in the section need to be in the correct order if some
 
        // kind of outer block is consumed, so we take another section, push
 
        // the expressions in that one, and then allocate the labeled statement.
 
        let mut inner_section = self.statements.start_section();
 
        self.consume_statement(module, iter, ctx, &mut inner_section)?;
 
        debug_assert!(inner_section.len() >= 1);
 

	
 
        let stmt_id = ctx.heap.alloc_labeled_statement(|this| LabeledStatement {
 
            this,
 
            label,
 
            body: inner_section[0],
 
            relative_pos_in_block: 0,
 
            in_sync: None,
 
        });
 

	
 
        if inner_section.len() == 1 {
 
            // Produce the labeled statement pointing to the first statement.
 
            // This is by far the most common case.
 
            inner_section.forget();
 
            section.push(stmt_id.upcast());
 
        } else {
 
            // Produce the labeled statement using the first statement, and push
 
            // the remaining ones at the end.
 
            let inner_statements = inner_section.into_vec();
 
            section.push(stmt_id.upcast());
 
            for idx in 1..inner_statements.len() {
 
                section.push(inner_statements[idx])
 
            }
 
        }
 

	
 
        Ok(())
 
    }
 

	
 
    fn maybe_consume_memory_statement(
 
        &mut self, module: &Module, iter: &mut TokenIter, ctx: &mut PassCtx
 
    ) -> Result<Option<(MemoryStatementId, ExpressionStatementId)>, ParseError> {
 
        // This is a bit ugly. It would be nicer if we could somehow
 
        // consume the expression with a type hint if we do get a valid
 
        // type, but we don't get an identifier following it
 
        let iter_state = iter.save();
 
        let definition_id = self.cur_definition;
 
        let poly_vars = ctx.heap[definition_id].poly_vars();
 

	
 
        let parser_type = consume_parser_type(
 
            &module.source, iter, &ctx.symbols, &ctx.heap, poly_vars,
 
            SymbolScope::Definition(definition_id), definition_id, true, 0
 
        );
 

	
 
        if let Ok(parser_type) = parser_type {
 
            if Some(TokenKind::Ident) == iter.next() {
 
                // Assume this is a proper memory statement
 
                let identifier = consume_ident_interned(&module.source, iter, ctx)?;
 
                let memory_span = InputSpan::from_positions(parser_type.elements[0].full_span.begin, identifier.span.end);
 
                let assign_span = consume_token(&module.source, iter, TokenKind::Equal)?;
 

	
 
                let initial_expr_begin_pos = iter.last_valid_pos();
 
                let initial_expr_id = self.consume_expression(module, iter, ctx)?;
 
                let initial_expr_end_pos = iter.last_valid_pos();
 
                consume_token(&module.source, iter, TokenKind::SemiColon)?;
 

	
 
                // Allocate the memory statement with the variable
 
                let local_id = ctx.heap.alloc_local(|this| Local{
 
                    this,
 
                    identifier: identifier.clone(),
 
                    parser_type,
 
                    relative_pos_in_block: 0,
 
                });
 
                let memory_stmt_id = ctx.heap.alloc_memory_statement(|this| MemoryStatement{
 
                    this,
 
                    span: memory_span,
 
                    variable: local_id,
 
                    next: None
 
                });
 

	
 
                // Allocate the initial assignment
 
                let variable_expr_id = ctx.heap.alloc_variable_expression(|this| VariableExpression{
 
                    this,
 
                    identifier,
 
                    declaration: None,
 
                    parent: ExpressionParent::None,
 
                    concrete_type: Default::default()
 
                });
 
                let assignment_expr_id = ctx.heap.alloc_assignment_expression(|this| AssignmentExpression{
 
                    this,
 
                    span: assign_span,
 
                    left: variable_expr_id.upcast(),
 
                    operation: AssignmentOperator::Set,
 
                    right: initial_expr_id,
 
                    parent: ExpressionParent::None,
 
                    concrete_type: Default::default(),
 
                });
 
                let assignment_stmt_id = ctx.heap.alloc_expression_statement(|this| ExpressionStatement{
 
                    this,
 
                    span: InputSpan::from_positions(initial_expr_begin_pos, initial_expr_end_pos),
 
                    expression: assignment_expr_id.upcast(),
 
                    next: None,
 
                });
 

	
 
                return Ok(Some((memory_stmt_id, assignment_stmt_id)))
 
            }
 
        }
 

	
 
        // If here then one of the preconditions for a memory statement was not
 
        // met. So recover the iterator and return
 
        iter.load(iter_state);
 
        Ok(None)
 
    }
 

	
 
    fn consume_expression_statement(
 
        &mut self, module: &Module, iter: &mut TokenIter, ctx: &mut PassCtx
 
    ) -> Result<ExpressionStatementId, ParseError> {
 
        let start_pos = iter.last_valid_pos();
 
        let expression = self.consume_expression(module, iter, ctx)?;
 
        let end_pos = iter.last_valid_pos();
 
        consume_token(&module.source, iter, TokenKind::SemiColon)?;
 

	
 
        Ok(ctx.heap.alloc_expression_statement(|this| ExpressionStatement{
 
            this,
 
            span: InputSpan::from_positions(start_pos, end_pos),
 
            expression,
 
            next: None,
 
        }))
 
    }
 

	
 
    //--------------------------------------------------------------------------
 
    // Expression Parsing
 
    //--------------------------------------------------------------------------
 

	
 
    fn consume_expression(
 
        &mut self, module: &Module, iter: &mut TokenIter, ctx: &mut PassCtx
 
    ) -> Result<ExpressionId, ParseError> {
 
        self.consume_assignment_expression(module, iter, ctx)
 
    }
 

	
 
    fn consume_assignment_expression(
 
        &mut self, module: &Module, iter: &mut TokenIter, ctx: &mut PassCtx
 
    ) -> Result<ExpressionId, ParseError> {
 
        // Utility to convert token into assignment operator
 
        fn parse_assignment_operator(token: Option<TokenKind>) -> Option<AssignmentOperator> {
 
            use TokenKind as TK;
 
            use AssignmentOperator as AO;
 

	
 
            if token.is_none() {
 
                return None
 
            }
 

	
 
            match token.unwrap() {
 
                TK::Equal               => Some(AO::Set),
 
                TK::StarEquals          => Some(AO::Multiplied),
 
                TK::SlashEquals         => Some(AO::Divided),
 
                TK::PercentEquals       => Some(AO::Remained),
 
                TK::PlusEquals          => Some(AO::Added),
 
                TK::MinusEquals         => Some(AO::Subtracted),
 
                TK::ShiftLeftEquals     => Some(AO::ShiftedLeft),
 
                TK::ShiftRightEquals    => Some(AO::ShiftedRight),
 
                TK::AndEquals           => Some(AO::BitwiseAnded),
 
                TK::CaretEquals         => Some(AO::BitwiseXored),
 
                TK::OrEquals            => Some(AO::BitwiseOred),
 
                _                       => None
 
            }
 
        }
 

	
 
        let expr = self.consume_conditional_expression(module, iter, ctx)?;
 
        if let Some(operation) = parse_assignment_operator(iter.next()) {
 
            let span = iter.next_span();
 
            iter.consume();
 

	
 
            let left = expr;
 
            let right = self.consume_expression(module, iter, ctx)?;
 

	
 
            Ok(ctx.heap.alloc_assignment_expression(|this| AssignmentExpression{
 
                this, span, left, operation, right,
 
                parent: ExpressionParent::None,
 
                concrete_type: ConcreteType::default(),
 
            }).upcast())
 
        } else {
 
            Ok(expr)
 
        }
 
    }
 

	
 
    fn consume_conditional_expression(
 
        &mut self, module: &Module, iter: &mut TokenIter, ctx: &mut PassCtx
 
    ) -> Result<ExpressionId, ParseError> {
 
        let result = self.consume_concat_expression(module, iter, ctx)?;
 
        if let Some(TokenKind::Question) = iter.next() {
 
            let span = iter.next_span();
 
            iter.consume();
 

	
 
            let test = result;
 
            let true_expression = self.consume_expression(module, iter, ctx)?;
 
            consume_token(&module.source, iter, TokenKind::Colon)?;
 
            let false_expression = self.consume_expression(module, iter, ctx)?;
 
            Ok(ctx.heap.alloc_conditional_expression(|this| ConditionalExpression{
 
                this, span, test, true_expression, false_expression,
 
                parent: ExpressionParent::None,
 
                concrete_type: ConcreteType::default(),
 
            }).upcast())
 
        } else {
 
            Ok(result)
 
        }
 
    }
 

	
 
    fn consume_concat_expression(
 
        &mut self, module: &Module, iter: &mut TokenIter, ctx: &mut PassCtx
 
    ) -> Result<ExpressionId, ParseError> {
 
        self.consume_generic_binary_expression(
 
            module, iter, ctx,
 
            |token| match token {
 
                Some(TokenKind::At) => Some(BinaryOperator::Concatenate),
 
                _ => None
 
            },
 
            Self::consume_logical_or_expression
 
        )
 
    }
 

	
 
    fn consume_logical_or_expression(
 
        &mut self, module: &Module, iter: &mut TokenIter, ctx: &mut PassCtx
 
    ) -> Result<ExpressionId, ParseError> {
 
        self.consume_generic_binary_expression(
 
            module, iter, ctx,
 
            |token| match token {
 
                Some(TokenKind::OrOr) => Some(BinaryOperator::LogicalOr),
 
                _ => None
 
            },
 
            Self::consume_logical_and_expression
 
        )
 
    }
 

	
 
    fn consume_logical_and_expression(
 
        &mut self, module: &Module, iter: &mut TokenIter, ctx: &mut PassCtx
 
    ) -> Result<ExpressionId, ParseError> {
 
        self.consume_generic_binary_expression(
 
            module, iter, ctx,
 
            |token| match token {
 
                Some(TokenKind::AndAnd) => Some(BinaryOperator::LogicalAnd),
 
                _ => None
 
            },
 
            Self::consume_bitwise_or_expression
 
        )
 
    }
 

	
 
    fn consume_bitwise_or_expression(
 
        &mut self, module: &Module, iter: &mut TokenIter, ctx: &mut PassCtx
 
    ) -> Result<ExpressionId, ParseError> {
 
        self.consume_generic_binary_expression(
 
            module, iter, ctx,
 
            |token| match token {
 
                Some(TokenKind::Or) => Some(BinaryOperator::BitwiseOr),
 
                _ => None
 
            },
 
            Self::consume_bitwise_xor_expression
 
        )
 
    }
 

	
 
    fn consume_bitwise_xor_expression(
 
        &mut self, module: &Module, iter: &mut TokenIter, ctx: &mut PassCtx
 
    ) -> Result<ExpressionId, ParseError> {
 
        self.consume_generic_binary_expression(
 
            module, iter, ctx,
 
            |token| match token {
 
                Some(TokenKind::Caret) => Some(BinaryOperator::BitwiseXor),
 
                _ => None
 
            },
 
            Self::consume_bitwise_and_expression
 
        )
 
    }
 

	
 
    fn consume_bitwise_and_expression(
 
        &mut self, module: &Module, iter: &mut TokenIter, ctx: &mut PassCtx
 
    ) -> Result<ExpressionId, ParseError> {
 
        self.consume_generic_binary_expression(
 
            module, iter, ctx,
 
            |token| match token {
 
                Some(TokenKind::And) => Some(BinaryOperator::BitwiseAnd),
 
                _ => None
 
            },
 
            Self::consume_equality_expression
 
        )
 
    }
 

	
 
    fn consume_equality_expression(
 
        &mut self, module: &Module, iter: &mut TokenIter, ctx: &mut PassCtx
 
    ) -> Result<ExpressionId, ParseError> {
 
        self.consume_generic_binary_expression(
 
            module, iter, ctx,
 
            |token| match token {
 
                Some(TokenKind::EqualEqual) => Some(BinaryOperator::Equality),
 
                Some(TokenKind::NotEqual) => Some(BinaryOperator::Inequality),
 
                _ => None
 
            },
 
            Self::consume_relational_expression
 
        )
 
    }
 

	
 
    fn consume_relational_expression(
 
        &mut self, module: &Module, iter: &mut TokenIter, ctx: &mut PassCtx
 
    ) -> Result<ExpressionId, ParseError> {
 
        self.consume_generic_binary_expression(
 
            module, iter, ctx,
 
            |token| match token {
 
                Some(TokenKind::OpenAngle) => Some(BinaryOperator::LessThan),
 
                Some(TokenKind::CloseAngle) => Some(BinaryOperator::GreaterThan),
 
                Some(TokenKind::LessEquals) => Some(BinaryOperator::LessThanEqual),
 
                Some(TokenKind::GreaterEquals) => Some(BinaryOperator::GreaterThanEqual),
 
                _ => None
 
            },
 
            Self::consume_shift_expression
 
        )
 
    }
 

	
 
    fn consume_shift_expression(
 
        &mut self, module: &Module, iter: &mut TokenIter, ctx: &mut PassCtx
 
    ) -> Result<ExpressionId, ParseError> {
 
        self.consume_generic_binary_expression(
 
            module, iter, ctx,
 
            |token| match token {
 
                Some(TokenKind::ShiftLeft) => Some(BinaryOperator::ShiftLeft),
 
                Some(TokenKind::ShiftRight) => Some(BinaryOperator::ShiftRight),
 
                _ => None
 
            },
 
            Self::consume_add_or_subtract_expression
 
        )
 
    }
 

	
 
    fn consume_add_or_subtract_expression(
 
        &mut self, module: &Module, iter: &mut TokenIter, ctx: &mut PassCtx
 
    ) -> Result<ExpressionId, ParseError> {
 
        self.consume_generic_binary_expression(
 
            module, iter, ctx,
 
            |token| match token {
 
                Some(TokenKind::Plus) => Some(BinaryOperator::Add),
 
                Some(TokenKind::Minus) => Some(BinaryOperator::Subtract),
 
                _ => None,
 
            },
 
            Self::consume_multiply_divide_or_modulus_expression
 
        )
 
    }
 

	
 
    fn consume_multiply_divide_or_modulus_expression(
 
        &mut self, module: &Module, iter: &mut TokenIter, ctx: &mut PassCtx
 
    ) -> Result<ExpressionId, ParseError> {
 
        self.consume_generic_binary_expression(
 
            module, iter, ctx,
 
            |token| match token {
 
                Some(TokenKind::Star) => Some(BinaryOperator::Multiply),
 
                Some(TokenKind::Slash) => Some(BinaryOperator::Divide),
 
                Some(TokenKind::Percent) => Some(BinaryOperator::Remainder),
 
                _ => None
 
            },
 
            Self::consume_prefix_expression
 
        )
 
    }
 

	
 
    fn consume_prefix_expression(
 
        &mut self, module: &Module, iter: &mut TokenIter, ctx: &mut PassCtx
 
    ) -> Result<ExpressionId, ParseError> {
 
        fn parse_prefix_token(token: Option<TokenKind>) -> Option<UnaryOperation> {
 
            use TokenKind as TK;
 
            use UnaryOperation as UO;
 
            match token {
 
                Some(TK::Plus) => Some(UO::Positive),
 
                Some(TK::Minus) => Some(UO::Negative),
 
                Some(TK::PlusPlus) => Some(UO::PreIncrement),
 
                Some(TK::MinusMinus) => Some(UO::PreDecrement),
 
                Some(TK::Tilde) => Some(UO::BitwiseNot),
 
                Some(TK::Exclamation) => Some(UO::LogicalNot),
 
                _ => None
 
            }
 
        }
 

	
 
        if let Some(operation) = parse_prefix_token(iter.next()) {
 
            let span = iter.next_span();
 
            iter.consume();
 

	
 
            let expression = self.consume_prefix_expression(module, iter, ctx)?;
 
            Ok(ctx.heap.alloc_unary_expression(|this| UnaryExpression {
 
                this, span, operation, expression,
 
                parent: ExpressionParent::None,
 
                concrete_type: ConcreteType::default()
 
            }).upcast())
 
        } else {
 
            self.consume_postfix_expression(module, iter, ctx)
 
        }
 
    }
 

	
 
    fn consume_postfix_expression(
 
        &mut self, module: &Module, iter: &mut TokenIter, ctx: &mut PassCtx
 
    ) -> Result<ExpressionId, ParseError> {
 
        fn has_matching_postfix_token(token: Option<TokenKind>) -> bool {
 
            use TokenKind as TK;
 

	
 
            if token.is_none() { return false; }
 
            match token.unwrap() {
 
                TK::PlusPlus | TK::MinusMinus | TK::OpenSquare | TK::Dot => true,
 
                _ => false
 
            }
 
        }
 

	
 
        let mut result = self.consume_primary_expression(module, iter, ctx)?;
 
        let mut next = iter.next();
 
        while has_matching_postfix_token(next) {
 
            let token = next.unwrap();
 
            let mut span = iter.next_span();
 
            iter.consume();
 

	
 
            if token == TokenKind::PlusPlus {
 
                result = ctx.heap.alloc_unary_expression(|this| UnaryExpression{
 
                    this, span,
 
                    operation: UnaryOperation::PostIncrement,
 
                    expression: result,
 
                    parent: ExpressionParent::None,
 
                    concrete_type: ConcreteType::default()
 
                }).upcast();
 
            } else if token == TokenKind::MinusMinus {
 
                result = ctx.heap.alloc_unary_expression(|this| UnaryExpression{
 
                    this, span,
 
                    operation: UnaryOperation::PostDecrement,
 
                    expression: result,
 
                    parent: ExpressionParent::None,
 
                    concrete_type: ConcreteType::default()
 
                }).upcast();
 
            } else if token == TokenKind::OpenSquare {
 
                let subject = result;
 
                let from_index = self.consume_expression(module, iter, ctx)?;
 

	
 
                // Check if we have an indexing or slicing operation
 
                next = iter.next();
 
                if Some(TokenKind::DotDot) == next {
 
                    iter.consume();
 

	
 
                    let to_index = self.consume_expression(module, iter, ctx)?;
 
                    let end_span = consume_token(&module.source, iter, TokenKind::CloseSquare)?;
 
                    span.end = end_span.end;
 

	
 
                    result = ctx.heap.alloc_slicing_expression(|this| SlicingExpression{
 
                        this, span, subject, from_index, to_index,
 
                        parent: ExpressionParent::None,
 
                        concrete_type: ConcreteType::default()
 
                    }).upcast();
 
                } else if Some(TokenKind::CloseSquare) == next {
 
                    let end_span = consume_token(&module.source, iter, TokenKind::CloseSquare)?;
 
                    span.end = end_span.end;
 

	
 
                    result = ctx.heap.alloc_indexing_expression(|this| IndexingExpression{
 
                        this, span, subject,
 
                        index: from_index,
 
                        parent: ExpressionParent::None,
 
                        concrete_type: ConcreteType::default()
 
                    }).upcast();
 
                } else {
 
                    return Err(ParseError::new_error_str_at_pos(
 
                        &module.source, iter.last_valid_pos(), "unexpected token: expected ']' or '..'"
 
                    ));
 
                }
 
            } else {
 
                debug_assert_eq!(token, TokenKind::Dot);
 
                let subject = result;
 
                let (field_text, field_span) = consume_ident(&module.source, iter)?;
 
                let field = if field_text == b"length" {
 
                    Field::Length
 
                } else {
 
                    let value = ctx.pool.intern(field_text);
 
                    let identifier = Identifier{ value, span: field_span };
 
                    Field::Symbolic(FieldSymbolic{ identifier, definition: None, field_idx: 0 })
 
                };
 

	
 
                result = ctx.heap.alloc_select_expression(|this| SelectExpression{
 
                    this, span, subject, field,
 
                    parent: ExpressionParent::None,
 
                    concrete_type: ConcreteType::default()
 
                }).upcast();
 
            }
 

	
 
            next = iter.next();
 
        }
 

	
 
        Ok(result)
 
    }
 

	
 
    fn consume_primary_expression(
 
        &mut self, module: &Module, iter: &mut TokenIter, ctx: &mut PassCtx
 
    ) -> Result<ExpressionId, ParseError> {
 
        let next = iter.next();
 

	
 
        let result = if next == Some(TokenKind::OpenParen) {
 
            // Expression between parentheses
 
            iter.consume();
 
            let result = self.consume_expression(module, iter, ctx)?;
 
            consume_token(&module.source, iter, TokenKind::CloseParen)?;
 

	
 
            result
 
        } else if next == Some(TokenKind::OpenCurly) {
 
            // Array literal
 
            let (start_pos, mut end_pos) = iter.next_positions();
 
            let mut scoped_section = self.expressions.start_section();
 
            consume_comma_separated(
 
                TokenKind::OpenCurly, TokenKind::CloseCurly, &module.source, iter, ctx,
 
                |_source, iter, ctx| self.consume_expression(module, iter, ctx),
 
                &mut scoped_section, "an expression", "a list of expressions", Some(&mut end_pos)
 
            )?;
 

	
 
            ctx.heap.alloc_literal_expression(|this| LiteralExpression{
 
                this,
 
                span: InputSpan::from_positions(start_pos, end_pos),
 
                value: Literal::Array(scoped_section.into_vec()),
 
                parent: ExpressionParent::None,
 
                concrete_type: ConcreteType::default(),
 
            }).upcast()
 
        } else if next == Some(TokenKind::Integer) {
 
            let (literal, span) = consume_integer_literal(&module.source, iter, &mut self.buffer)?;
 

	
 
            ctx.heap.alloc_literal_expression(|this| LiteralExpression{
 
                this, span,
 
                value: Literal::Integer(LiteralInteger{ unsigned_value: literal, negated: false }),
 
                parent: ExpressionParent::None,
 
                concrete_type: ConcreteType::default(),
 
            }).upcast()
 
        } else if next == Some(TokenKind::String) {
 
            let span = consume_string_literal(&module.source, iter, &mut self.buffer)?;
 
            let interned = ctx.pool.intern(self.buffer.as_bytes());
 

	
 
            ctx.heap.alloc_literal_expression(|this| LiteralExpression{
 
                this, span,
 
                value: Literal::String(interned),
 
                parent: ExpressionParent::None,
 
                concrete_type: ConcreteType::default(),
 
            }).upcast()
 
        } else if next == Some(TokenKind::Character) {
 
            let (character, span) = consume_character_literal(&module.source, iter)?;
 

	
 
            ctx.heap.alloc_literal_expression(|this| LiteralExpression{
 
                this, span,
 
                value: Literal::Character(character),
 
                parent: ExpressionParent::None,
 
                concrete_type: ConcreteType::default(),
 
            }).upcast()
 
        } else if next == Some(TokenKind::Ident) {
 
            // May be a variable, a type instantiation or a function call. If we
 
            // have a single identifier that we cannot find in the type table
 
            // then we're going to assume that we're dealing with a variable.
 
            let ident_span = iter.next_span();
 
            let ident_text = module.source.section_at_span(ident_span);
 
            let symbol = ctx.symbols.get_symbol_by_name(SymbolScope::Module(module.root_id), ident_text);
 

	
 
            if symbol.is_some() {
 
                // The first bit looked like a symbol, so we're going to follow
 
                // that all the way through, assume we arrive at some kind of
 
                // function call or type instantiation
 
                use ParserTypeVariant as PTV;
 

	
 
                let symbol_scope = SymbolScope::Definition(self.cur_definition);
 
                let poly_vars = ctx.heap[self.cur_definition].poly_vars();
 
                let parser_type = consume_parser_type(
 
                    &module.source, iter, &ctx.symbols, &ctx.heap, poly_vars, symbol_scope,
 
                    self.cur_definition, true, 0
 
                )?;
 
                debug_assert!(!parser_type.elements.is_empty());
 
                match parser_type.elements[0].variant {
 
                    PTV::Definition(target_definition_id, _) => {
 
                        let definition = &ctx.heap[target_definition_id];
 
                        match definition {
 
                            Definition::Struct(_) => {
 
                                // Struct literal
 
                                let mut last_token = iter.last_valid_pos();
 
                                let mut struct_fields = Vec::new();
 
                                consume_comma_separated(
 
                                    TokenKind::OpenCurly, TokenKind::CloseCurly, &module.source, iter, ctx,
 
                                    |source, iter, ctx| {
 
                                        let identifier = consume_ident_interned(source, iter, ctx)?;
 
                                        consume_token(source, iter, TokenKind::Colon)?;
 
                                        let value = self.consume_expression(module, iter, ctx)?;
 
                                        Ok(LiteralStructField{ identifier, value, field_idx: 0 })
 
                                    },
 
                                    &mut struct_fields, "a struct field", "a list of struct field", Some(&mut last_token)
 
                                )?;
 

	
 
                                ctx.heap.alloc_literal_expression(|this| LiteralExpression{
 
                                    this,
 
                                    span: InputSpan::from_positions(ident_span.begin, last_token),
 
                                    value: Literal::Struct(LiteralStruct{
 
                                        parser_type,
 
                                        fields: struct_fields,
 
                                        definition: target_definition_id,
 
                                    }),
 
                                    parent: ExpressionParent::None,
 
                                    concrete_type: ConcreteType::default(),
 
                                }).upcast()
 
                            },
 
                            Definition::Enum(_) => {
 
                                // Enum literal: consume the variant
 
                                consume_token(&module.source, iter, TokenKind::ColonColon)?;
 
                                let variant = consume_ident_interned(&module.source, iter, ctx)?;
 

	
 
                                ctx.heap.alloc_literal_expression(|this| LiteralExpression{
 
                                    this,
 
                                    span: InputSpan::from_positions(ident_span.begin, variant.span.end),
 
                                    value: Literal::Enum(LiteralEnum{
 
                                        parser_type,
 
                                        variant,
 
                                        definition: target_definition_id,
 
                                        variant_idx: 0
 
                                    }),
 
                                    parent: ExpressionParent::None,
 
                                    concrete_type: ConcreteType::default()
 
                                }).upcast()
 
                            },
 
                            Definition::Union(_) => {
 
                                // Union literal: consume the variant
 
                                consume_token(&module.source, iter, TokenKind::ColonColon)?;
 
                                let variant = consume_ident_interned(&module.source, iter, ctx)?;
 

	
 
                                // Consume any possible embedded values
 
                                let mut end_pos = iter.last_valid_pos();
 
                                let values = self.consume_expression_list(module, iter, ctx, Some(&mut end_pos))?;
 

	
 
                                ctx.heap.alloc_literal_expression(|this| LiteralExpression{
 
                                    this,
 
                                    span: InputSpan::from_positions(ident_span.begin, end_pos),
 
                                    value: Literal::Union(LiteralUnion{
 
                                        parser_type, variant, values,
 
                                        definition: target_definition_id,
 
                                        variant_idx: 0,
 
                                    }),
 
                                    parent: ExpressionParent::None,
 
                                    concrete_type: ConcreteType::default()
 
                                }).upcast()
 
                            },
 
                            Definition::Component(_) => {
 
                                // Component instantiation
 
                                let arguments = self.consume_expression_list(module, iter, ctx, None)?;
 

	
 
                                ctx.heap.alloc_call_expression(|this| CallExpression{
 
                                    this,
 
                                    span: parser_type.elements[0].full_span, // TODO: @Span fix
 
                                    parser_type,
 
                                    method: Method::UserComponent,
 
                                    arguments,
 
                                    definition: target_definition_id,
 
                                    parent: ExpressionParent::None,
 
                                    concrete_type: ConcreteType::default(),
 
                                }).upcast()
 
                            },
 
                            Definition::Function(function_definition) => {
 
                                // Check whether it is a builtin function
 
                                let method = if function_definition.builtin {
 
                                    match function_definition.identifier.value.as_str() {
 
                                        "get" => Method::Get,
 
                                        "put" => Method::Put,
 
                                        "fires" => Method::Fires,
 
                                        "create" => Method::Create,
 
                                        "length" => Method::Length,
 
                                        "assert" => Method::Assert,
 
                                        _ => unreachable!(),
 
                                    }
 
                                } else {
 
                                    Method::UserFunction
 
                                };
 

	
 
                                // Function call: consume the arguments
 
                                let arguments = self.consume_expression_list(module, iter, ctx, None)?;
 

	
 
                                ctx.heap.alloc_call_expression(|this| CallExpression{
 
                                    this,
 
                                    span: parser_type.elements[0].full_span, // TODO: @Span fix
 
                                    parser_type,
 
                                    method,
 
                                    arguments,
 
                                    definition: target_definition_id,
 
                                    parent: ExpressionParent::None,
 
                                    concrete_type: ConcreteType::default(),
 
                                }).upcast()
 
                            }
 
                        }
 
                    },
 
                    _ => {
 
                        // TODO: Casting expressions
 
                        return Err(ParseError::new_error_str_at_span(
 
                            &module.source, parser_type.elements[0].full_span,
 
                            "unexpected type in expression, note that casting expressions are not yet implemented"
 
                        ))
 
                    }
 
                }
 
            } else {
 
                // Check for builtin keywords or builtin functions
 
                if ident_text == KW_LIT_NULL || ident_text == KW_LIT_TRUE || ident_text == KW_LIT_FALSE {
 
                    // Parse builtin literal
 
                    let value = match ident_text {
 
                        KW_LIT_NULL => Literal::Null,
 
                        KW_LIT_TRUE => Literal::True,
 
                        KW_LIT_FALSE => Literal::False,
 
                        _ => unreachable!(),
 
                    };
 

	
 
                    ctx.heap.alloc_literal_expression(|this| LiteralExpression{
 
                        this,
 
                        span: ident_span,
 
                        value,
 
                        parent: ExpressionParent::None,
 
                        concrete_type: ConcreteType::default(),
 
                    }).upcast()
 
                } else {
 
                    // I'm a bit unsure about this. One may as well have wrongfully
 
                    // typed `TypeWithTypo<Subtype>::`, then we assume that
 
                    // `TypeWithTypo` is a variable. So might want to come back to
 
                    // this later to do some silly heuristics.
 
                    iter.consume();
 
                    if Some(TokenKind::ColonColon) == iter.next() {
 
                        return Err(ParseError::new_error_str_at_span(&module.source, ident_span, "unknown identifier"));
 
                    }
 

	
 
                    let ident_text = ctx.pool.intern(ident_text);
 
                    let identifier = Identifier { span: ident_span, value: ident_text };
 

	
 
                    ctx.heap.alloc_variable_expression(|this| VariableExpression {
 
                        this,
 
                        identifier,
 
                        declaration: None,
 
                        parent: ExpressionParent::None,
 
                        concrete_type: ConcreteType::default()
 
                    }).upcast()
 
                }
 
            }
 
        } else {
 
            return Err(ParseError::new_error_str_at_pos(
 
                &module.source, iter.last_valid_pos(), "expected an expression"
 
            ));
 
        };
 

	
 
        Ok(result)
 
    }
 

	
 
    //--------------------------------------------------------------------------
 
    // Expression Utilities
 
    //--------------------------------------------------------------------------
 

	
 
    #[inline]
 
    fn consume_generic_binary_expression<
 
        M: Fn(Option<TokenKind>) -> Option<BinaryOperator>,
 
        F: Fn(&mut PassDefinitions, &Module, &mut TokenIter, &mut PassCtx) -> Result<ExpressionId, ParseError>
 
    >(
 
        &mut self, module: &Module, iter: &mut TokenIter, ctx: &mut PassCtx, match_fn: M, higher_precedence_fn: F
 
    ) -> Result<ExpressionId, ParseError> {
 
        let mut result = higher_precedence_fn(self, module, iter, ctx)?;
 
        while let Some(operation) = match_fn(iter.next()) {
 
            let span = iter.next_span();
 
            iter.consume();
 

	
 
            let left = result;
 
            let right = higher_precedence_fn(self, module, iter, ctx)?;
 

	
 
            result = ctx.heap.alloc_binary_expression(|this| BinaryExpression{
 
                this, span, left, operation, right,
 
                parent: ExpressionParent::None,
 
                concrete_type: ConcreteType::default()
 
            }).upcast();
 
        }
 

	
 
        Ok(result)
 
    }
 

	
 
    #[inline]
 
    fn consume_expression_list(
 
        &mut self, module: &Module, iter: &mut TokenIter, ctx: &mut PassCtx, end_pos: Option<&mut InputPosition>
 
    ) -> Result<Vec<ExpressionId>, ParseError> {
 
        let mut section = self.expressions.start_section();
 
        consume_comma_separated(
 
            TokenKind::OpenParen, TokenKind::CloseParen, &module.source, iter, ctx,
 
            |_source, iter, ctx| self.consume_expression(module, iter, ctx),
 
            &mut section, "an expression", "a list of expressions", end_pos
 
        )?;
 
        Ok(section.into_vec())
 
    }
 
}
 

	
 
/// Consumes a type. A type always starts with an identifier which may indicate
 
/// a builtin type or a user-defined type. The fact that it may contain
 
/// polymorphic arguments makes it a tree-like structure. Because we cannot rely
 
/// on knowing the exact number of polymorphic arguments we do not check for
 
/// these.
 
///
 
/// Note that the first depth index is used as a hack.
 
// TODO: @Optimize, @Span fix
 
fn consume_parser_type(
 
    source: &InputSource, iter: &mut TokenIter, symbols: &SymbolTable, heap: &Heap, poly_vars: &[Identifier],
 
    cur_scope: SymbolScope, wrapping_definition: DefinitionId, allow_inference: bool, first_angle_depth: i32,
 
) -> Result<ParserType, ParseError> {
 
    struct Entry{
 
        element: ParserTypeElement,
 
        depth: i32,
 
    }
 

	
 
    fn insert_array_before(elements: &mut Vec<Entry>, depth: i32, span: InputSpan) {
 
        let index = elements.iter().rposition(|e| e.depth == depth).unwrap();
 
        elements.insert(index, Entry{
 
            element: ParserTypeElement{ full_span: span, variant: ParserTypeVariant::Array },
 
            depth,
 
        });
 
    }
 

	
 
    // Most common case we just have one type, perhaps with some array
 
    // annotations.
 
    let element = consume_parser_type_ident(source, iter, symbols, heap, poly_vars, cur_scope, wrapping_definition, allow_inference)?;
 
    if iter.next() != Some(TokenKind::OpenAngle) {
 
        let mut num_array = 0;
 
        while iter.next() == Some(TokenKind::OpenSquare) {
 
            iter.consume();
 
            consume_token(source, iter, TokenKind::CloseSquare)?;
 
            num_array += 1;
 
        }
 

	
 
        let array_span = element.full_span;
 
        let mut elements = Vec::with_capacity(num_array + 1);
 
        for _ in 0..num_array {
 
            elements.push(ParserTypeElement{ full_span: array_span, variant: ParserTypeVariant::Array });
 
        }
 
        elements.push(element);
 

	
 
        return Ok(ParserType{ elements });
 
    };
 

	
 
    // We have a polymorphic specification. So we start by pushing the item onto
 
    // our stack, then start adding entries together with the angle-brace depth
 
    // at which they're found.
 
    let mut elements = Vec::new();
 
    elements.push(Entry{ element, depth: 0 });
 

	
 
    // Start out with the first '<' consumed.
 
    iter.consume();
 
    enum State { Ident, Open, Close, Comma }
 
    let mut state = State::Open;
 
    let mut angle_depth = first_angle_depth + 1;
 

	
 
    loop {
 
        let next = iter.next();
 

	
 
        match state {
 
            State::Ident => {
 
                // Just parsed an identifier, may expect comma, angled braces,
 
                // or the tokens indicating an array
 
                if Some(TokenKind::OpenAngle) == next {
 
                    angle_depth += 1;
 
                    state = State::Open;
 
                } else if Some(TokenKind::CloseAngle) == next {
 
                    angle_depth -= 1;
 
                    state = State::Close;
 
                } else if Some(TokenKind::ShiftRight) == next {
 
                    angle_depth -= 2;
 
                    state = State::Close;
 
                } else if Some(TokenKind::Comma) == next {
 
                    state = State::Comma;
 
                } else if Some(TokenKind::OpenSquare) == next {
 
                    let (start_pos, _) = iter.next_positions();
 
                    iter.consume(); // consume opening square
 
                    if iter.next() != Some(TokenKind::CloseSquare) {
 
                        return Err(ParseError::new_error_str_at_pos(
 
                            source, iter.last_valid_pos(),
 
                            "unexpected token: expected ']'"
 
                        ));
 
                    }
 
                    let (_, end_pos) = iter.next_positions();
 
                    let array_span = InputSpan::from_positions(start_pos, end_pos);
 
                    insert_array_before(&mut elements, angle_depth, array_span);
 
                } else {
 
                    return Err(ParseError::new_error_str_at_pos(
 
                        source, iter.last_valid_pos(),
 
                        "unexpected token: expected '<', '>', ',' or '['")
 
                    );
 
                }
 

	
 
                iter.consume();
 
            },
 
            State::Open => {
 
                // Just parsed an opening angle bracket, expecting an identifier
 
                let element = consume_parser_type_ident(source, iter, symbols, heap, poly_vars, cur_scope, wrapping_definition, allow_inference)?;
 
                elements.push(Entry{ element, depth: angle_depth });
 
                state = State::Ident;
 
            },
 
            State::Close => {
 
                // Just parsed 1 or 2 closing angle brackets, expecting comma,
 
                // more closing brackets or the tokens indicating an array
 
                if Some(TokenKind::Comma) == next {
 
                    state = State::Comma;
 
                } else if Some(TokenKind::CloseAngle) == next {
 
                    angle_depth -= 1;
 
                    state = State::Close;
 
                } else if Some(TokenKind::ShiftRight) == next {
 
                    angle_depth -= 2;
 
                    state = State::Close;
 
                } else if Some(TokenKind::OpenSquare) == next {
 
                    let (start_pos, _) = iter.next_positions();
 
                    iter.consume();
 
                    if iter.next() != Some(TokenKind::CloseSquare) {
 
                        return Err(ParseError::new_error_str_at_pos(
 
                            source, iter.last_valid_pos(),
 
                            "unexpected token: expected ']'"
 
                        ));
 
                    }
 
                    let (_, end_pos) = iter.next_positions();
 
                    let array_span = InputSpan::from_positions(start_pos, end_pos);
 
                    insert_array_before(&mut elements, angle_depth, array_span);
 
                } else {
 
                    return Err(ParseError::new_error_str_at_pos(
 
                        source, iter.last_valid_pos(),
 
                        "unexpected token: expected ',', '>', or '['")
 
                    );
 
                }
 

	
 
                iter.consume();
 
            },
 
            State::Comma => {
 
                // Just parsed a comma, expecting an identifier or more closing
 
                // braces
 
                if Some(TokenKind::Ident) == next {
 
                    let element = consume_parser_type_ident(source, iter, symbols, heap, poly_vars, cur_scope, wrapping_definition, allow_inference)?;
 
                    elements.push(Entry{ element, depth: angle_depth });
 
                    state = State::Ident;
 
                } else if Some(TokenKind::CloseAngle) == next {
 
                    iter.consume();
 
                    angle_depth -= 1;
 
                    state = State::Close;
 
                } else if Some(TokenKind::ShiftRight) == next {
 
                    iter.consume();
 
                    angle_depth -= 2;
 
                    state = State::Close;
 
                } else {
 
                    return Err(ParseError::new_error_str_at_pos(
 
                        source, iter.last_valid_pos(),
 
                        "unexpected token: expected '>' or a type name"
 
                    ));
 
                }
 
            }
 
        }
 

	
 
        if angle_depth < 0 {
 
            return Err(ParseError::new_error_str_at_pos(source, iter.last_valid_pos(), "unmatched '>'"));
 
        } else if angle_depth == 0 {
 
            break;
 
        }
 
    }
 

	
 
    // If here then we found the correct number of angle braces. But we still
 
    // need to make sure that each encountered type has the correct number of
 
    // embedded types.
 
    let mut idx = 0;
 
    while idx < elements.len() {
 
        let cur_element = &elements[idx];
 
        let expected_subtypes = cur_element.element.variant.num_embedded();
 
        let mut encountered_subtypes = 0;
 
        for peek_idx in idx + 1..elements.len() {
 
            let peek_element = &elements[peek_idx];
 
            if peek_element.depth == cur_element.depth + 1 {
 
                encountered_subtypes += 1;
 
            } else if peek_element.depth <= cur_element.depth {
 
                break;
 
            }
 
        }
 

	
 
        if expected_subtypes != encountered_subtypes {
 
            if encountered_subtypes == 0 {
 
                // Case where we have elided the embedded types, all of them
 
                // should be inferred.
 
                if !allow_inference {
 
                    return Err(ParseError::new_error_str_at_span(
 
                        source, cur_element.element.full_span,
 
                        "type inference is not allowed here"
 
                    ));
 
                }
 

	
 
                // Insert the missing types
 
                let inserted_span = cur_element.element.full_span;
 
                let inserted_depth = cur_element.depth + 1;
 
                elements.reserve(expected_subtypes);
 
                for _ in 0..expected_subtypes {
 
                    elements.insert(idx + 1, Entry{
 
                        element: ParserTypeElement{ full_span: inserted_span, variant: ParserTypeVariant::Inferred },
 
                        depth: inserted_depth,
 
                    });
 
                }
 
            } else {
 
                // Mismatch in number of embedded types
 
                let expected_args_text = if expected_subtypes == 1 {
 
                    "polymorphic argument"
 
                } else {
 
                    "polymorphic arguments"
 
                };
 

	
 
                let maybe_infer_text = if allow_inference {
 
                    " (or none, to perform implicit type inference)"
 
                } else {
 
                    ""
 
                };
 

	
 
                return Err(ParseError::new_error_at_span(
 
                    source, cur_element.element.full_span,
 
                    format!(
 
                        "expected {} {}{}, but {} were provided",
 
                        expected_subtypes, expected_args_text, maybe_infer_text, encountered_subtypes
 
                    )
 
                ));
 
            }
 
        }
 

	
 
        idx += 1;
 
    }
 

	
 
    let mut constructed_elements = Vec::with_capacity(elements.len());
 
    for element in elements.into_iter() {
 
        constructed_elements.push(element.element);
 
    }
 

	
 
    Ok(ParserType{ elements: constructed_elements })
 
}
 

	
 
/// Consumes an identifier for which we assume that it resolves to some kind of
 
/// type. Once we actually arrive at a type we will stop parsing. Hence there
 
/// may be trailing '::' tokens in the iterator.
 
fn consume_parser_type_ident(
 
    source: &InputSource, iter: &mut TokenIter, symbols: &SymbolTable, heap: &Heap, poly_vars: &[Identifier],
 
    mut scope: SymbolScope, wrapping_definition: DefinitionId, allow_inference: bool,
 
) -> Result<ParserTypeElement, ParseError> {
 
    use ParserTypeVariant as PTV;
 
    let (mut type_text, mut type_span) = consume_any_ident(source, iter)?;
 

	
 
    let variant = match type_text {
 
        KW_TYPE_MESSAGE => PTV::Message,
 
        KW_TYPE_BOOL => PTV::Bool,
 
        KW_TYPE_UINT8 => PTV::UInt8,
 
        KW_TYPE_UINT16 => PTV::UInt16,
 
        KW_TYPE_UINT32 => PTV::UInt32,
 
        KW_TYPE_UINT64 => PTV::UInt64,
 
        KW_TYPE_SINT8 => PTV::SInt8,
 
        KW_TYPE_SINT16 => PTV::SInt16,
 
        KW_TYPE_SINT32 => PTV::SInt32,
 
        KW_TYPE_SINT64 => PTV::SInt64,
 
        KW_TYPE_IN_PORT => PTV::Input,
 
        KW_TYPE_OUT_PORT => PTV::Output,
 
        KW_TYPE_CHAR => PTV::Character,
 
        KW_TYPE_STRING => PTV::String,
 
        KW_TYPE_INFERRED => {
 
            if !allow_inference {
 
                return Err(ParseError::new_error_str_at_span(source, type_span, "type inference is not allowed here"));
 
            }
 

	
 
            PTV::Inferred
 
        },
 
        _ => {
 
            // Must be some kind of symbolic type
 
            let mut type_kind = None;
 
            for (poly_idx, poly_var) in poly_vars.iter().enumerate() {
 
                if poly_var.value.as_bytes() == type_text {
 
                    type_kind = Some(PTV::PolymorphicArgument(wrapping_definition, poly_idx));
 
                }
 
            }
 

	
 
            if type_kind.is_none() {
 
                // Check symbol table for definition. To be fair, the language
 
                // only allows a single namespace for now. That said:
 
                let last_symbol = symbols.get_symbol_by_name(scope, type_text);
 
                if last_symbol.is_none() {
 
                    return Err(ParseError::new_error_str_at_span(source, type_span, "unknown type"));
 
                }
 
                let mut last_symbol = last_symbol.unwrap();
 

	
 
                loop {
 
                    match &last_symbol.variant {
 
                        SymbolVariant::Module(symbol_module) => {
 
                            // Expecting more identifiers
 
                            if Some(TokenKind::ColonColon) != iter.next() {
 
                                return Err(ParseError::new_error_str_at_span(source, type_span, "expected type but got module"));
 
                            }
 

	
 
                            consume_token(source, iter, TokenKind::ColonColon)?;
 

	
 
                            // Consume next part of type and prepare for next
 
                            // lookup loop
 
                            let (next_text, next_span) = consume_any_ident(source, iter)?;
 
                            let old_text = type_text;
 
                            type_text = next_text;
 
                            type_span.end = next_span.end;
 
                            scope = SymbolScope::Module(symbol_module.root_id);
 

	
 
                            let new_symbol = symbols.get_symbol_by_name_defined_in_scope(scope, type_text);
 
                            if new_symbol.is_none() {
 
                                return Err(ParseError::new_error_at_span(
 
                                    source, next_span,
 
                                    format!(
 
                                        "unknown type '{}' in module '{}'",
 
                                        String::from_utf8_lossy(type_text),
 
                                        String::from_utf8_lossy(old_text)
 
                                    )
 
                                ));
 
                            }
 

	
src/protocol/parser/pass_imports.rs
Show inline comments
 
use crate::protocol::ast::*;
 
use super::symbol_table::*;
 
use super::{Module, ModuleCompilationPhase, PassCtx};
 
use super::tokens::*;
 
use super::token_parsing::*;
 
use crate::protocol::input_source::{InputSource as InputSource, InputSpan, ParseError};
 
use crate::collections::*;
 

	
 
/// Parses all the imports in the module tokens. Is applied after the
 
/// definitions and name of modules are resolved. Hence we should be able to
 
/// resolve all symbols to their appropriate module/definition.
 
pub(crate) struct PassImport {
 
    imports: Vec<ImportId>,
 
    found_symbols: Vec<(AliasedSymbol, SymbolDefinition)>,
 
    scoped_symbols: Vec<Symbol>,
 
}
 

	
 
impl PassImport {
 
    pub(crate) fn new() -> Self {
 
        Self{
 
            imports: Vec::with_capacity(32),
 
            found_symbols: Vec::with_capacity(32),
 
            scoped_symbols: Vec::with_capacity(32),
 
        }
 
    }
 
    pub(crate) fn parse(&mut self, modules: &mut [Module], module_idx: usize, ctx: &mut PassCtx) -> Result<(), ParseError> {
 
        let module = &modules[module_idx];
 
        let module_range = &module.tokens.ranges[0];
 
        debug_assert!(modules.iter().all(|m| m.phase >= ModuleCompilationPhase::SymbolsScanned));
 
        debug_assert_eq!(module.phase, ModuleCompilationPhase::SymbolsScanned);
 
        debug_assert_eq!(module_range.range_kind, TokenRangeKind::Module);
 

	
 
        let mut range_idx = module_range.first_child_idx;
 
        loop {
 
            let range_idx_usize = range_idx as usize;
 
            let cur_range = &module.tokens.ranges[range_idx_usize];
 

	
 
            if cur_range.range_kind == TokenRangeKind::Import {
 
                self.visit_import_range(modules, module_idx, ctx, range_idx_usize)?;
 
            }
 

	
 
            if cur_range.next_sibling_idx == NO_SIBLING {
 
                break;
 
            } else {
 
                range_idx = cur_range.next_sibling_idx;
 
            }
 
        }
 

	
 
        let root = &mut ctx.heap[module.root_id];
 
        root.imports.extend(self.imports.drain(..));
 

	
 
        let module = &mut modules[module_idx];
 
        module.phase = ModuleCompilationPhase::ImportsResolved;
 

	
 
        Ok(())
 
    }
 

	
 
    pub(crate) fn visit_import_range(
 
        &mut self, modules: &[Module], module_idx: usize, ctx: &mut PassCtx, range_idx: usize
 
    ) -> Result<(), ParseError> {
 
        let module = &modules[module_idx];
 
        let import_range = &module.tokens.ranges[range_idx];
 
        debug_assert_eq!(import_range.range_kind, TokenRangeKind::Import);
 

	
 
        let mut iter = module.tokens.iter_range(import_range);
 

	
 
        // Consume "import"
 
        let (_import_ident, import_span) =
 
            consume_any_ident(&module.source, &mut iter)?;
 
        debug_assert_eq!(_import_ident, KW_IMPORT);
 

	
 
        // Consume module name
 
        let (module_name, module_name_span) = consume_domain_ident(&module.source, &mut iter)?;
 
        let target_root_id = ctx.symbols.get_module_by_name(module_name);
 
        if target_root_id.is_none() {
 
            return Err(ParseError::new_error_at_span(
 
                &module.source, module_name_span,
 
                format!("could not resolve module '{}'", String::from_utf8_lossy(module_name))
 
            ));
 
        }
 
        let module_name = ctx.pool.intern(module_name);
 
        let module_identifier = Identifier{ span: module_name_span, value: module_name };
 
        let target_root_id = target_root_id.unwrap();
 

	
 
        // Check for subsequent characters (alias, multiple imported symbols)
 
        let next = iter.next();
 
        let import_id;
 

	
 
        if has_ident(&module.source, &mut iter, b"as") {
 
            // Alias for module
 
            iter.consume();
 
            let alias_identifier = consume_ident_interned(&module.source, &mut iter, ctx)?;
 
            let alias_name = alias_identifier.value.clone();
 

	
 
            import_id = ctx.heap.alloc_import(|this| Import::Module(ImportModule{
 
                this,
 
                span: import_span,
 
                module: module_identifier,
 
                alias: alias_identifier,
 
                module_id: target_root_id
 
            }));
 
            ctx.symbols.insert_symbol(SymbolScope::Module(module.root_id), Symbol{
 

	
 
            if let Err((new_symbol, old_symbol)) = ctx.symbols.insert_symbol(SymbolScope::Module(module.root_id), Symbol{
 
                name: alias_name,
 
                variant: SymbolVariant::Module(SymbolModule{
 
                    root_id: target_root_id,
 
                    introduced_at: import_id,
 
                }),
 
            });
 
            }) {
 
                return Err(construct_symbol_conflict_error(modules, module_idx, ctx, &new_symbol, &old_symbol));
 
            }
 
        } else if Some(TokenKind::ColonColon) == next {
 
            iter.consume();
 

	
 
            // Helper function to consume symbols, their alias, and the
 
            // definition the symbol is pointing to.
 
            fn consume_symbol_and_maybe_alias<'a>(
 
                source: &'a InputSource, iter: &mut TokenIter, ctx: &mut PassCtx,
 
                module_name: &StringRef<'static>, module_root_id: RootId,
 
            ) -> Result<(AliasedSymbol, SymbolDefinition), ParseError> {
 
                // Consume symbol name and make sure it points to an existing definition
 
                let symbol_identifier = consume_ident_interned(source, iter, ctx)?;
 

	
 
                // Consume alias text if specified
 
                let alias_identifier = if peek_ident(source, iter) == Some(b"as") {
 
                    // Consume alias
 
                    iter.consume();
 
                    Some(consume_ident_interned(source, iter, ctx)?)
 
                } else {
 
                    None
 
                };
 

	
 
                let target = ctx.symbols.get_symbol_by_name_defined_in_scope(
 
                    SymbolScope::Module(module_root_id), symbol_identifier.value.as_bytes()
 
                );
 

	
 
                if target.is_none() {
 
                    return Err(ParseError::new_error_at_span(
 
                        source, symbol_identifier.span,
 
                        format!(
 
                            "could not find symbol '{}' within module '{}'",
 
                            symbol_identifier.value.as_str(), module_name.as_str()
 
                        )
 
                    ));
 
                }
 
                let target = target.unwrap();
 
                debug_assert_ne!(target.class(), SymbolClass::Module);
 
                let target_definition = target.variant.as_definition();
 

	
 
                Ok((
 
                    AliasedSymbol{
 
                        name: symbol_identifier,
 
                        alias: alias_identifier,
 
                        definition_id: target_definition.definition_id,
 
                    },
 
                    target_definition.clone()
 
                ))
 
            }
 

	
 
            let next = iter.next();
 

	
 
            if Some(TokenKind::Ident) == next {
 
                // Importing a single symbol
 
                iter.consume();
 
                let (imported_symbol, symbol_definition) = consume_symbol_and_maybe_alias(
 
                    &module.source, &mut iter, ctx, &module_identifier.value, target_root_id
 
                )?;
 

	
 
                let alias_identifier = match imported_symbol.alias.as_ref() {
 
                    Some(alias) => alias.clone(),
 
                    None => imported_symbol.name.clone(),
 
                };
 

	
 
                import_id = ctx.heap.alloc_import(|this| Import::Symbols(ImportSymbols{
 
                    this,
 
                    span: InputSpan::from_positions(import_span.begin, alias_identifier.span.end),
 
                    module: module_identifier,
 
                    module_id: target_root_id,
 
                    symbols: vec![imported_symbol],
 
                }));
 
                if let Err((new_symbol, old_symbol)) = ctx.symbols.insert_symbol(
 
                    SymbolScope::Module(module.root_id),
 
                    Symbol{
 
                        name: alias_identifier.value,
 
                        variant: SymbolVariant::Definition(symbol_definition.into_imported(import_id))
 
                    }
 
                ) {
 
                    return Err(construct_symbol_conflict_error(
 
                        modules, module_idx, ctx, &new_symbol, &old_symbol
 
                    ));
 
                }
 
            } else if Some(TokenKind::OpenCurly) == next {
 
                // Importing multiple symbols
 
                let mut end_of_list = iter.last_valid_pos();
 
                consume_comma_separated(
 
                    TokenKind::OpenCurly, TokenKind::CloseCurly, &module.source, &mut iter, ctx,
 
                    |source, iter, ctx| consume_symbol_and_maybe_alias(
 
                        source, iter, ctx, &module_identifier.value, target_root_id
 
                    ),
 
                    &mut self.found_symbols, "a symbol", "a list of symbols to import", Some(&mut end_of_list)
 
                )?;
 

	
 
                // Preallocate import
 
                import_id = ctx.heap.alloc_import(|this| Import::Symbols(ImportSymbols {
 
                    this,
 
                    span: InputSpan::from_positions(import_span.begin, end_of_list),
 
                    module: module_identifier,
 
                    module_id: target_root_id,
 
                    symbols: Vec::with_capacity(self.found_symbols.len()),
 
                }));
 

	
 
                // Fill import symbols while inserting symbols in the
 
                // appropriate scope in the symbol table.
 
                let import = ctx.heap[import_id].as_symbols_mut();
 

	
 
                for (imported_symbol, symbol_definition) in self.found_symbols.drain(..) {
 
                    let import_name = match imported_symbol.alias.as_ref() {
 
                        Some(import) => import.value.clone(),
 
                        None => imported_symbol.name.value.clone()
 
                    };
 

	
 
                    import.symbols.push(imported_symbol);
 
                    if let Err((new_symbol, old_symbol)) = ctx.symbols.insert_symbol(
 
                        SymbolScope::Module(module.root_id), Symbol{
 
                            name: import_name,
 
                            variant: SymbolVariant::Definition(symbol_definition.into_imported(import_id))
 
                        }
 
                    ) {
 
                        return Err(construct_symbol_conflict_error(modules, module_idx, ctx, &new_symbol, &old_symbol));
 
                    }
 
                }
 
            } else if Some(TokenKind::Star) == next {
 
                // Import all symbols from the module
 
                let star_span = iter.next_span();
 

	
 
                iter.consume();
 
                self.scoped_symbols.clear();
 
                let _found = ctx.symbols.get_all_symbols_defined_in_scope(
 
                    SymbolScope::Module(target_root_id),
 
                    &mut self.scoped_symbols
 
                );
 
                debug_assert!(_found); // even modules without symbols should have a scope
 

	
 
                // Preallocate import
 
                import_id = ctx.heap.alloc_import(|this| Import::Symbols(ImportSymbols{
 
                    this,
 
                    span: InputSpan::from_positions(import_span.begin, star_span.end),
 
                    module: module_identifier,
 
                    module_id: target_root_id,
 
                    symbols: Vec::with_capacity(self.scoped_symbols.len())
 
                }));
 

	
 
                // Fill import AST node and symbol table
 
                let import = ctx.heap[import_id].as_symbols_mut();
 

	
 
                for symbol in self.scoped_symbols.drain(..) {
 
                    let symbol_name = symbol.name;
 
                    match symbol.variant {
 
                        SymbolVariant::Definition(symbol_definition) => {
 
                            import.symbols.push(AliasedSymbol{
 
                                name: Identifier{ span: star_span, value: symbol_name.clone() },
 
                                alias: None,
 
                                definition_id: symbol_definition.definition_id,
 
                            });
 

	
 
                            if let Err((new_symbol, old_symbol)) = ctx.symbols.insert_symbol(
 
                                SymbolScope::Module(module.root_id),
 
                                Symbol{
 
                                    name: symbol_name,
 
                                    variant: SymbolVariant::Definition(symbol_definition.into_imported(import_id))
 
                                }
 
                            ) {
 
                                return Err(construct_symbol_conflict_error(modules, module_idx, ctx, &new_symbol, &old_symbol));
 
                            }
 
                        },
 
                        _ => unreachable!(),
 
                    }
 
                }
 
            } else {
 
                return Err(ParseError::new_error_str_at_pos(
 
                    &module.source, iter.last_valid_pos(), "expected symbol name, '{' or '*'"
 
                ));
 
            }
 
        } else {
 
            // Assume implicit alias
 
            let module_name_str = module_identifier.value.clone();
 
            let last_ident_start = module_name_str.as_str().rfind('.').map_or(0, |v| v + 1);
 
            let alias_text = &module_name_str.as_bytes()[last_ident_start..];
 
            let alias = ctx.pool.intern(alias_text);
 
            let alias_span = InputSpan::from_positions(
 
                module_name_span.begin.with_offset(last_ident_start as u32),
 
                module_name_span.end
 
            );
 
            let alias_identifier = Identifier{ span: alias_span, value: alias.clone() };
 

	
 
            import_id = ctx.heap.alloc_import(|this| Import::Module(ImportModule{
 
                this,
 
                span: InputSpan::from_positions(import_span.begin, module_identifier.span.end),
 
                module: module_identifier,
 
                alias: alias_identifier,
 
                module_id: target_root_id,
 
            }));
 
            if let Err((new_symbol, old_symbol)) = ctx.symbols.insert_symbol(SymbolScope::Module(module.root_id), Symbol{
 
                name: alias,
 
                variant: SymbolVariant::Module(SymbolModule{
 
                    root_id: target_root_id,
 
                    introduced_at: import_id
 
                })
 
            }) {
 
                return Err(construct_symbol_conflict_error(modules, module_idx, ctx, &new_symbol, &old_symbol));
 
            }
 
        }
 

	
 
        // By now the `import_id` is set, just need to make sure that the import
 
        // properly ends with a semicolon
 
        consume_token(&module.source, &mut iter, TokenKind::SemiColon)?;
 
        self.imports.push(import_id);
 

	
 
        Ok(())
 
    }
 
}
src/protocol/parser/pass_symbols.rs
Show inline comments
 
use crate::protocol::ast::*;
 
use super::symbol_table::*;
 
use crate::protocol::input_source::{ParseError, InputSpan};
 
use super::tokens::*;
 
use super::token_parsing::*;
 
use super::{Module, ModuleCompilationPhase, PassCtx};
 

	
 
/// Scans the module and finds all module-level type definitions. These will be
 
/// added to the symbol table such that during AST-construction we know which
 
/// identifiers point to types. Will also parse all pragmas to determine module
 
/// names.
 
pub(crate) struct PassSymbols {
 
    symbols: Vec<Symbol>,
 
    pragmas: Vec<PragmaId>,
 
    imports: Vec<ImportId>,
 
    definitions: Vec<DefinitionId>,
 
    buffer: String,
 
    has_pragma_version: bool,
 
    has_pragma_module: bool,
 
}
 

	
 
impl PassSymbols {
 
    pub(crate) fn new() -> Self {
 
        Self{
 
            symbols: Vec::with_capacity(128),
 
            pragmas: Vec::with_capacity(8),
 
            imports: Vec::with_capacity(32),
 
            definitions: Vec::with_capacity(128),
 
            buffer: String::with_capacity(128),
 
            has_pragma_version: false,
 
            has_pragma_module: false,
 
        }
 
    }
 

	
 
    fn reset(&mut self) {
 
        self.symbols.clear();
 
        self.pragmas.clear();
 
        self.imports.clear();
 
        self.definitions.clear();
 
        self.has_pragma_version = false;
 
        self.has_pragma_module = false;
 
    }
 

	
 
    pub(crate) fn parse(&mut self, modules: &mut [Module], module_idx: usize, ctx: &mut PassCtx) -> Result<(), ParseError> {
 
        self.reset();
 

	
 
        let module = &mut modules[module_idx];
 
        let module_range = &module.tokens.ranges[0];
 

	
 
        debug_assert_eq!(module.phase, ModuleCompilationPhase::Tokenized);
 
        debug_assert_eq!(module_range.range_kind, TokenRangeKind::Module);
 
        debug_assert!(module.root_id.is_invalid()); // not set yet,
 

	
 
        // Preallocate root in the heap
 
        let root_id = ctx.heap.alloc_protocol_description(|this| {
 
            Root{
 
                this,
 
                pragmas: Vec::new(),
 
                imports: Vec::new(),
 
                definitions: Vec::new(),
 
            }
 
        });
 
        module.root_id = root_id;
 

	
 
        // Retrieve first range index, then make immutable borrow
 
        let mut range_idx = module_range.first_child_idx;
 
        let module = &modules[module_idx];
 

	
 
        // Visit token ranges to detect definitions and pragmas
 
        loop {
 
            let range_idx_usize = range_idx as usize;
 
            let cur_range = &module.tokens.ranges[range_idx_usize];
 
            let next_sibling_idx = cur_range.next_sibling_idx;
 
            let range_kind = cur_range.range_kind;
 

	
 
            // Parse if it is a definition or a pragma
 
            if range_kind == TokenRangeKind::Definition {
 
                self.visit_definition_range(modules, module_idx, ctx, range_idx_usize)?;
 
            } else if range_kind == TokenRangeKind::Pragma {
 
                self.visit_pragma_range(modules, module_idx, ctx, range_idx_usize)?;
 
            }
 

	
 
            if next_sibling_idx == NO_SIBLING {
 
                break;
 
            } else {
 
                range_idx = next_sibling_idx;
 
            }
 
        }
 

	
 
        // Add the module's symbol scope and the symbols we just parsed
 
        let module_scope = SymbolScope::Module(root_id);
 
        ctx.symbols.insert_scope(None, module_scope);
 
        for symbol in self.symbols.drain(..) {
 
            ctx.symbols.insert_scope(Some(module_scope), SymbolScope::Definition(symbol.variant.as_definition().definition_id));
 
            if let Err((new_symbol, old_symbol)) = ctx.symbols.insert_symbol(module_scope, symbol) {
 
                return Err(construct_symbol_conflict_error(modules, module_idx, ctx, &new_symbol, &old_symbol))
 
            }
 
        }
 

	
 
        // Modify the preallocated root
 
        let root = &mut ctx.heap[root_id];
 
        root.pragmas.extend(self.pragmas.drain(..));
 
        root.definitions.extend(self.definitions.drain(..));
 

	
 
        let module = &mut modules[module_idx];
 
        module.phase = ModuleCompilationPhase::SymbolsScanned;
 

	
 
        Ok(())
 
    }
 

	
 
    fn visit_pragma_range(&mut self, modules: &[Module], module_idx: usize, ctx: &mut PassCtx, range_idx: usize) -> Result<(), ParseError> {
 
        let module = &modules[module_idx];
 
        let range = &module.tokens.ranges[range_idx];
 
        let mut iter = module.tokens.iter_range(range);
 

	
 
        // Consume pragma name
 
        let (pragma_section, pragma_start, _) = consume_pragma(&module.source, &mut iter)?;
 

	
 
        // Consume pragma values
 
        if pragma_section == b"#module" {
 
            // Check if name is defined twice within the same file
 
            if self.has_pragma_module {
 
                return Err(ParseError::new_error_str_at_pos(&module.source, pragma_start, "module name is defined twice"));
 
            }
 

	
 
            // Consume the domain-name
 
            let (module_name, module_span) = consume_domain_ident(&module.source, &mut iter)?;
 
            if iter.next().is_some() {
 
                return Err(ParseError::new_error_str_at_pos(&module.source, iter.last_valid_pos(), "expected end of #module pragma after module name"));
 
            }
 

	
 
            // Add to heap and symbol table
 
            let pragma_span = InputSpan::from_positions(pragma_start, module_span.end);
 
            let module_name = ctx.pool.intern(module_name);
 
            let pragma_id = ctx.heap.alloc_pragma(|this| Pragma::Module(PragmaModule{
 
                this,
 
                span: pragma_span,
 
                value: Identifier{ span: module_span, value: module_name.clone() },
 
            }));
 
            self.pragmas.push(pragma_id);
 

	
 
            if let Err(other_module_root_id) = ctx.symbols.insert_module(module_name, module.root_id) {
 
                // Naming conflict
 
                let this_module = &modules[module_idx];
 
                let other_module = seek_module(modules, other_module_root_id).unwrap();
 
                let other_module_pragma_id = other_module.name.as_ref().map(|v| (*v).0).unwrap();
 
                let other_pragma = ctx.heap[other_module_pragma_id].as_module();
 
                return Err(ParseError::new_error_str_at_span(
 
                    &this_module.source, pragma_span, "conflict in module name"
 
                ).with_info_str_at_span(
 
                    &other_module.source, other_pragma.span, "other module is defined here"
 
                ));
 
            }
 
            self.has_pragma_module = true;
 
        } else if pragma_section == b"#version" {
 
            // Check if version is defined twice within the same file
 
            if self.has_pragma_version {
 
                return Err(ParseError::new_error_str_at_pos(&module.source, pragma_start, "module version is defined twice"));
 
            }
 

	
 
            // Consume the version pragma
 
            let (version, version_span) = consume_integer_literal(&module.source, &mut iter, &mut self.buffer)?;
 
            let pragma_id = ctx.heap.alloc_pragma(|this| Pragma::Version(PragmaVersion{
 
                this,
 
                span: InputSpan::from_positions(pragma_start, version_span.end),
 
                version,
 
            }));
 
            self.pragmas.push(pragma_id);
 
            self.has_pragma_version = true;
 
        } else {
 
            // Custom pragma, maybe we support this in the future, but for now
 
            // we don't.
 
            return Err(ParseError::new_error_str_at_pos(&module.source, pragma_start, "illegal pragma name"));
 
        }
 

	
 
        Ok(())
 
    }
 

	
 
    fn visit_definition_range(&mut self, modules: &[Module], module_idx: usize, ctx: &mut PassCtx, range_idx: usize) -> Result<(), ParseError> {
 
        let module = &modules[module_idx];
 
        let range = &module.tokens.ranges[range_idx];
 
        let definition_span = InputSpan::from_positions(
 
            module.tokens.start_pos(range),
 
            module.tokens.end_pos(range)
 
        );
 
        let mut iter = module.tokens.iter_range(range);
 

	
 
        // First ident must be type of symbol
 
        let (kw_text, _) = consume_any_ident(&module.source, &mut iter).unwrap();
 

	
 
        // Retrieve identifier of definition
 
        let identifier = consume_ident_interned(&module.source, &mut iter, ctx)?;
 
        let mut poly_vars = Vec::new();
 
        maybe_consume_comma_separated(
 
            TokenKind::OpenAngle, TokenKind::CloseAngle, &module.source, &mut iter, ctx,
 
            |source, iter, ctx| consume_ident_interned(source, iter, ctx),
 
            &mut poly_vars, "a polymorphic variable", None
 
        )?;
 
        let ident_text = identifier.value.clone(); // because we need it later
 
        let ident_span = identifier.span.clone();
 

	
 
        // Reserve space in AST for definition and add it to the symbol table
 
        let definition_class;
 
        let ast_definition_id;
 
        match kw_text {
 
            KW_STRUCT => {
 
                let struct_def_id = ctx.heap.alloc_struct_definition(|this| {
 
                    StructDefinition::new_empty(this, module.root_id, definition_span, identifier, poly_vars)
 
                });
 
                definition_class = DefinitionClass::Struct;
 
                ast_definition_id = struct_def_id.upcast();
 
            },
 
            KW_ENUM => {
 
                let enum_def_id = ctx.heap.alloc_enum_definition(|this| {
 
                    EnumDefinition::new_empty(this, module.root_id, definition_span, identifier, poly_vars)
 
                });
 
                definition_class = DefinitionClass::Enum;
 
                ast_definition_id = enum_def_id.upcast();
 
            },
 
            KW_UNION => {
 
                let union_def_id = ctx.heap.alloc_union_definition(|this| {
 
                    UnionDefinition::new_empty(this, module.root_id, definition_span, identifier, poly_vars)
 
                });
 
                definition_class = DefinitionClass::Union;
 
                ast_definition_id = union_def_id.upcast()
 
            },
 
            KW_FUNCTION => {
 
                let func_def_id = ctx.heap.alloc_function_definition(|this| {
 
                    FunctionDefinition::new_empty(this, module.root_id, definition_span, identifier, poly_vars)
 
                });
 
                definition_class = DefinitionClass::Function;
 
                ast_definition_id = func_def_id.upcast();
 
            },
 
            KW_PRIMITIVE | KW_COMPOSITE => {
 
                let component_variant = if kw_text == KW_PRIMITIVE {
 
                    ComponentVariant::Primitive
 
                } else {
 
                    ComponentVariant::Composite
 
                };
 
                let comp_def_id = ctx.heap.alloc_component_definition(|this| {
 
                    ComponentDefinition::new_empty(this, module.root_id, definition_span, component_variant, identifier, poly_vars)
 
                });
 
                definition_class = DefinitionClass::Component;
 
                ast_definition_id = comp_def_id.upcast();
 
            },
 
            _ => unreachable!("encountered keyword '{}' in definition range", String::from_utf8_lossy(kw_text)),
 
        }
 

	
 
        let symbol = Symbol{
 
            name: ident_text,
 
            variant: SymbolVariant::Definition(SymbolDefinition{
 
                defined_in_module: module.root_id,
 
                defined_in_scope: SymbolScope::Module(module.root_id),
 
                definition_span,
 
                identifier_span: ident_span,
 
                imported_at: None,
 
                class: definition_class,
 
                definition_id: ast_definition_id,
 
            }),
 
        };
 
        self.symbols.push(symbol);
 
        self.definitions.push(ast_definition_id);
 

	
 
        Ok(())
 
    }
 
}
 
\ No newline at end of file
src/protocol/parser/pass_tokenizer.rs
Show inline comments
 
use crate::protocol::input_source::{
 
    InputSource as InputSource,
 
    ParseError,
 
    InputPosition as InputPosition,
 
};
 

	
 
use super::tokens::*;
 
use super::token_parsing::*;
 

	
 
/// Tokenizer is a reusable parser to tokenize multiple source files using the
 
/// same allocated buffers. In a well-formed program, we produce a consistent
 
/// tree of token ranges such that we may identify tokens that represent a
 
/// defintion or an import before producing the entire AST.
 
///
 
/// If the program is not well-formed then the tree may be inconsistent, but we
 
/// will detect this once we transform the tokens into the AST. To ensure a
 
/// consistent AST-producing phase we will require the import to have balanced
 
/// curly braces
 
pub(crate) struct PassTokenizer {
 
    // Stack of input positions of opening curly braces, used to detect
 
    // unmatched opening braces, unmatched closing braces are detected
 
    // immediately.
 
    curly_stack: Vec<InputPosition>,
 
    // Points to an element in the `TokenBuffer.ranges` variable.
 
    stack_idx: usize,
 
}
 

	
 
impl PassTokenizer {
 
    pub(crate) fn new() -> Self {
 
        Self{
 
            curly_stack: Vec::with_capacity(32),
 
            stack_idx: 0
 
        }
 
    }
 

	
 
    pub(crate) fn tokenize(&mut self, source: &mut InputSource, target: &mut TokenBuffer) -> Result<(), ParseError> {
 
        // Assert source and buffer are at start
 
        debug_assert_eq!(source.pos().offset, 0);
 
        debug_assert!(target.tokens.is_empty());
 
        debug_assert!(target.ranges.is_empty());
 

	
 
        // Set up for tokenization by pushing the first range onto the stack.
 
        // This range may get transformed into the appropriate range kind later,
 
        // see `push_range` and `pop_range`.
 
        self.stack_idx = 0;
 
        target.ranges.push(TokenRange{
 
            parent_idx: NO_RELATION,
 
            range_kind: TokenRangeKind::Module,
 
            curly_depth: 0,
 
            start: 0,
 
            end: 0,
 
            num_child_ranges: 0,
 
            first_child_idx: NO_RELATION,
 
            last_child_idx: NO_RELATION,
 
            next_sibling_idx: NO_RELATION,
 
        });
 

	
 
        // Main tokenization loop
 
        while let Some(c) = source.next() {
 
            let token_index = target.tokens.len() as u32;
 

	
 
            if is_char_literal_start(c) {
 
                self.consume_char_literal(source, target)?;
 
            } else if is_string_literal_start(c) {
 
                self.consume_string_literal(source, target)?;
 
            } else if is_identifier_start(c) {
 
                let ident = self.consume_identifier(source, target)?;
 

	
 
                if demarks_definition(ident) {
 
                    self.push_range(target, TokenRangeKind::Definition, token_index);
 
                } else if demarks_import(ident) {
 
                    self.push_range(target, TokenRangeKind::Import, token_index);
 
                }
 
            } else if is_integer_literal_start(c) {
 
                self.consume_number(source, target)?;
 
            } else if is_pragma_start_or_pound(c) {
 
                let was_pragma = self.consume_pragma_or_pound(c, source, target)?;
 
                if was_pragma {
 
                    self.push_range(target, TokenRangeKind::Pragma, token_index);
 
                }
 
            } else if self.is_line_comment_start(c, source) {
 
                self.consume_line_comment(source, target)?;
 
            } else if self.is_block_comment_start(c, source) {
 
                self.consume_block_comment(source, target)?;
 
            } else if is_whitespace(c) {
 
                let contained_newline = self.consume_whitespace(source);
 
                if contained_newline {
 
                    let range = &target.ranges[self.stack_idx];
 
                    if range.range_kind == TokenRangeKind::Pragma {
 
                        self.pop_range(target, target.tokens.len() as u32);
 
                    }
 
                }
 
            } else {
 
                let was_punctuation = self.maybe_parse_punctuation(c, source, target)?;
 
                if let Some((token, token_pos)) = was_punctuation {
 
                    if token == TokenKind::OpenCurly {
 
                        self.curly_stack.push(token_pos);
 
                    } else if token == TokenKind::CloseCurly {
 
                        // Check if this marks the end of a range we're
 
                        // currently processing
 
                        if self.curly_stack.is_empty() {
 
                            return Err(ParseError::new_error_str_at_pos(
 
                                source, token_pos, "unmatched closing curly brace '}'"
 
                            ));
 
                        }
 

	
 
                        self.curly_stack.pop();
 

	
 
                        let range = &target.ranges[self.stack_idx];
 
                        if range.range_kind == TokenRangeKind::Definition && range.curly_depth == self.curly_stack.len() as u32 {
 
                            self.pop_range(target, target.tokens.len() as u32);
 
                        }
 

	
 
                        // Exit early if we have more closing curly braces than
 
                        // opening curly braces
 
                    } else if token == TokenKind::SemiColon {
 
                        // Check if this marks the end of an import
 
                        let range = &target.ranges[self.stack_idx];
 
                        if range.range_kind == TokenRangeKind::Import {
 
                            self.pop_range(target, target.tokens.len() as u32);
 
                        }
 
                    }
 
                } else {
 
                    return Err(ParseError::new_error_str_at_pos(
 
                        source, source.pos(), "unexpected character"
 
                    ));
 
                }
 
            }
 
        }
 

	
 
        // End of file, check if our state is correct
 
        if let Some(error) = source.had_error.take() {
 
            return Err(error);
 
        }
 

	
 
        if !self.curly_stack.is_empty() {
 
            // Let's not add a lot of heuristics and just tell the programmer
 
            // that something is wrong
 
            let last_unmatched_open = self.curly_stack.pop().unwrap();
 
            return Err(ParseError::new_error_str_at_pos(
 
                source, last_unmatched_open, "unmatched opening curly brace '{'"
 
            ));
 
        }
 

	
 
        // Ranges that did not depend on curly braces may have missing tokens.
 
        // So close all of the active tokens
 
        while self.stack_idx != 0 {
 
            self.pop_range(target, target.tokens.len() as u32);
 
        }
 

	
 
        // And finally, we may have a token range at the end that doesn't belong
 
        // to a range yet, so insert a "code" range if this is the case.
 
        debug_assert_eq!(self.stack_idx, 0);
 
        let last_registered_idx = target.ranges[0].end;
 
        let last_token_idx = target.tokens.len() as u32;
 
        if target.ranges[0].end != last_token_idx {
 

	
 
        if last_registered_idx != last_token_idx {
 
            self.add_code_range(target, 0, last_registered_idx, last_token_idx);
 
        }
 

	
 
        // TODO: @remove once I'm sure the algorithm works. For now it is better
 
        //  if the debugging is a little more expedient
 
        if cfg!(debug_assertions) {
 
            // For each range make sure its children make sense
 
            for parent_idx in 0..target.ranges.len() {
 
                let cur_range = &target.ranges[parent_idx];
 
                if cur_range.num_child_ranges == 0 {
 
                    assert_eq!(cur_range.first_child_idx, NO_RELATION);
 
                    assert_eq!(cur_range.last_child_idx, NO_RELATION);
 
                } else {
 
                    assert_ne!(cur_range.first_child_idx, NO_RELATION);
 
                    assert_ne!(cur_range.last_child_idx, NO_RELATION);
 

	
 
                    let mut child_counter = 0u32;
 
                    let mut last_valid_child_idx = cur_range.first_child_idx;
 
                    let mut child_idx = cur_range.first_child_idx;
 
                    while child_idx != NO_RELATION {
 
                        let child_range = &target.ranges[child_idx as usize];
 
                        assert_eq!(child_range.parent_idx, parent_idx as i32);
 
                        last_valid_child_idx = child_idx;
 
                        child_idx = child_range.next_sibling_idx;
 
                        child_counter += 1;
 
                    }
 

	
 
                    assert_eq!(cur_range.last_child_idx, last_valid_child_idx);
 
                    assert_eq!(cur_range.num_child_ranges, child_counter);
 
                }
 
            }
 
        }
 

	
 
        Ok(())
 
    }
 

	
 
    fn is_line_comment_start(&self, first_char: u8, source: &InputSource) -> bool {
 
        return first_char == b'/' && Some(b'/') == source.lookahead(1);
 
    }
 

	
 
    fn is_block_comment_start(&self, first_char: u8, source: &InputSource) -> bool {
 
        return first_char == b'/' && Some(b'*') == source.lookahead(1);
 
    }
 

	
 
    fn maybe_parse_punctuation(
 
        &mut self, first_char: u8, source: &mut InputSource, target: &mut TokenBuffer
 
    ) -> Result<Option<(TokenKind, InputPosition)>, ParseError> {
 
        debug_assert!(first_char != b'#', "'#' needs special handling");
 
        debug_assert!(first_char != b'\'', "'\'' needs special handling");
 
        debug_assert!(first_char != b'"', "'\"' needs special handling");
 

	
 
        let pos = source.pos();
 
        let token_kind;
 
        if first_char == b'!' {
 
            source.consume();
 
            if Some(b'=') == source.next() {
 
                source.consume();
 
                token_kind = TokenKind::NotEqual;
 
            } else {
 
                token_kind = TokenKind::Exclamation;
 
            }
 
        } else if first_char == b'%' {
 
            source.consume();
 
            if Some(b'=') == source.next() {
 
                source.consume();
 
                token_kind = TokenKind::PercentEquals;
 
            } else {
 
                token_kind = TokenKind::Percent;
 
            }
 
        } else if first_char == b'&' {
 
            source.consume();
 
            let next = source.next();
 
            if Some(b'&') == next {
 
                source.consume();
 
                token_kind = TokenKind::AndAnd;
 
            } else if Some(b'=') == next {
 
                source.consume();
 
                token_kind = TokenKind::AndEquals;
 
            } else {
 
                token_kind = TokenKind::And;
 
            }
 
        } else if first_char == b'(' {
 
            source.consume();
 
            token_kind = TokenKind::OpenParen;
 
        } else if first_char == b')' {
 
            source.consume();
 
            token_kind = TokenKind::CloseParen;
 
        } else if first_char == b'*' {
 
            source.consume();
 
            if let Some(b'=') = source.next() {
 
                source.consume();
 
                token_kind = TokenKind::StarEquals;
 
            } else {
 
                token_kind = TokenKind::Star;
 
            }
 
        } else if first_char == b'+' {
 
            source.consume();
 
            let next = source.next();
 
            if Some(b'+') == next {
 
                source.consume();
 
                token_kind = TokenKind::PlusPlus;
 
            } else if Some(b'=') == next {
 
                source.consume();
 
                token_kind = TokenKind::PlusEquals;
 
            } else {
 
                token_kind = TokenKind::Plus;
 
            }
 
        } else if first_char == b',' {
 
            source.consume();
 
            token_kind = TokenKind::Comma;
 
        } else if first_char == b'-' {
 
            source.consume();
 
            let next = source.next();
 
            if Some(b'-') == next {
 
                source.consume();
 
                token_kind = TokenKind::MinusMinus;
 
            } else if Some(b'>') == next {
 
                source.consume();
 
                token_kind = TokenKind::ArrowRight;
 
            } else if Some(b'=') == next {
 
                source.consume();
 
                token_kind = TokenKind::MinusEquals;
 
            } else {
 
                token_kind = TokenKind::Minus;
 
            }
 
        } else if first_char == b'.' {
 
            source.consume();
 
            if let Some(b'.') = source.next() {
 
                source.consume();
 
                token_kind = TokenKind::DotDot;
 
            } else {
 
                token_kind = TokenKind::Dot
 
            }
 
        } else if first_char == b'/' {
 
            source.consume();
 
            debug_assert_ne!(Some(b'/'), source.next());
 
            debug_assert_ne!(Some(b'*'), source.next());
 
            if let Some(b'=') = source.next() {
 
                source.consume();
 
                token_kind = TokenKind::SlashEquals;
 
            } else {
 
                token_kind = TokenKind::Slash;
 
            }
 
        } else if first_char == b':' {
 
            source.consume();
 
            if let Some(b':') = source.next() {
 
                source.consume();
 
                token_kind = TokenKind::ColonColon;
 
            } else {
 
                token_kind = TokenKind::Colon;
 
            }
 
        } else if first_char == b';' {
 
            source.consume();
 
            token_kind = TokenKind::SemiColon;
 
        } else if first_char == b'<' {
 
            source.consume();
 
            let next = source.next();
 
            if let Some(b'<') = next {
 
                source.consume();
 
                if let Some(b'=') = source.next() {
 
                    source.consume();
 
                    token_kind = TokenKind::ShiftLeftEquals;
 
                } else {
 
                    token_kind = TokenKind::ShiftLeft;
 
                }
 
            } else if let Some(b'=') = next {
 
                source.consume();
 
                token_kind = TokenKind::LessEquals;
 
            } else {
 
                token_kind = TokenKind::OpenAngle;
 
            }
 
        } else if first_char == b'=' {
 
            source.consume();
 
            if let Some(b'=') = source.next() {
 
                source.consume();
 
                token_kind = TokenKind::EqualEqual;
 
            } else {
 
                token_kind = TokenKind::Equal;
 
            }
 
        } else if first_char == b'>' {
 
            source.consume();
 
            let next = source.next();
 
            if Some(b'>') == next {
 
                source.consume();
 
                if Some(b'=') == source.next() {
 
                    source.consume();
 
                    token_kind = TokenKind::ShiftRightEquals;
 
                } else {
 
                    token_kind = TokenKind::ShiftRight;
 
                }
 
            } else if Some(b'=') == next {
 
                source.consume();
 
                token_kind = TokenKind::GreaterEquals;
 
            } else {
 
                token_kind = TokenKind::CloseAngle;
 
            }
 
        } else if first_char == b'?' {
 
            source.consume();
 
            token_kind = TokenKind::Question;
 
        } else if first_char == b'@' {
 
            source.consume();
 
            token_kind = TokenKind::At;
 
        } else if first_char == b'[' {
 
            source.consume();
 
            token_kind = TokenKind::OpenSquare;
 
        } else if first_char == b']' {
 
            source.consume();
 
            token_kind = TokenKind::CloseSquare;
 
        } else if first_char == b'^' {
 
            source.consume();
 
            if let Some(b'=') = source.next() {
 
                source.consume();
 
                token_kind = TokenKind::CaretEquals;
 
            } else {
 
                token_kind = TokenKind::Caret;
 
            }
 
        } else if first_char == b'{' {
 
            source.consume();
 
            token_kind = TokenKind::OpenCurly;
 
        } else if first_char == b'|' {
 
            source.consume();
 
            let next = source.next();
 
            if Some(b'|') == next {
 
                source.consume();
 
                token_kind = TokenKind::OrOr;
 
            } else if Some(b'=') == next {
 
                source.consume();
 
                token_kind = TokenKind::OrEquals;
 
            } else {
 
                token_kind = TokenKind::Or;
 
            }
 
        } else if first_char == b'}' {
 
            source.consume();
 
            token_kind = TokenKind::CloseCurly;
 
        } else if first_char == b'~' {
 
            source.consume();
 
            token_kind = TokenKind::Tilde;
 
        } else {
 
            self.check_ascii(source)?;
 
            return Ok(None);
 
        }
 

	
 
        target.tokens.push(Token::new(token_kind, pos));
 
        Ok(Some((token_kind, pos)))
 
    }
 

	
 
    fn consume_char_literal(&mut self, source: &mut InputSource, target: &mut TokenBuffer) -> Result<(), ParseError> {
 
        let begin_pos = source.pos();
 

	
 
        // Consume the leading quote
 
        debug_assert!(source.next().unwrap() == b'\'');
 
        source.consume();
 

	
 
        let mut prev_char = b'\'';
 
        while let Some(c) = source.next() {
 
            if !c.is_ascii() {
 
                return Err(ParseError::new_error_str_at_pos(source, source.pos(), "non-ASCII character in char literal"));
 
            }
 
            source.consume();
 

	
 
            // Make sure ending quote was not escaped
 
            if c == b'\'' && prev_char != b'\\' {
 
                prev_char = c;
 
                break;
 
            }
 

	
 
            prev_char = c;
 
        }
 

	
 
        if prev_char != b'\'' {
 
            // Unterminated character literal, reached end of file.
 
            return Err(ParseError::new_error_str_at_pos(source, begin_pos, "encountered unterminated character literal"));
 
        }
 

	
 
        let end_pos = source.pos();
 

	
 
        target.tokens.push(Token::new(TokenKind::Character, begin_pos));
 
        target.tokens.push(Token::new(TokenKind::SpanEnd, end_pos));
 

	
 
        Ok(())
 
    }
 

	
 
    fn consume_string_literal(&mut self, source: &mut InputSource, target: &mut TokenBuffer) -> Result<(), ParseError> {
 
        let begin_pos = source.pos();
 

	
 
        // Consume the leading double quotes
 
        debug_assert!(source.next().unwrap() == b'"');
 
        source.consume();
 

	
 
        let mut prev_char = b'"';
 
        while let Some(c) = source.next() {
 
            if !c.is_ascii() {
 
                return Err(ParseError::new_error_str_at_pos(source, source.pos(), "non-ASCII character in string literal"));
 
            }
 

	
 
            source.consume();
 
            if c == b'"' && prev_char != b'\\' {
 
                prev_char = c;
 
                break;
 
            }
 

	
 
            prev_char = c;
 
        }
 

	
 
        if prev_char != b'"' {
 
            // Unterminated string literal
 
            return Err(ParseError::new_error_str_at_pos(source, begin_pos, "encountered unterminated string literal"));
 
        }
 

	
 
        let end_pos = source.pos();
 
        target.tokens.push(Token::new(TokenKind::String, begin_pos));
 
        target.tokens.push(Token::new(TokenKind::SpanEnd, end_pos));
 

	
 
        Ok(())
 
    }
 

	
 
    fn consume_pragma_or_pound(&mut self, first_char: u8, source: &mut InputSource, target: &mut TokenBuffer) -> Result<bool, ParseError> {
 
        let start_pos = source.pos();
 
        debug_assert_eq!(first_char, b'#');
 
        source.consume();
 

	
 
        let next = source.next();
 
        if next.is_none() || !is_identifier_start(next.unwrap()) {
 
            // Just a pound sign
 
            target.tokens.push(Token::new(TokenKind::Pound, start_pos));
 
            Ok(false)
 
        } else {
 
            // Pound sign followed by identifier
 
            source.consume();
 
            while let Some(c) = source.next() {
 
                if !is_identifier_remaining(c) {
 
                    break;
 
                }
 
                source.consume();
 
            }
 

	
 
            self.check_ascii(source)?;
 

	
 
            let end_pos = source.pos();
 
            target.tokens.push(Token::new(TokenKind::Pragma, start_pos));
 
            target.tokens.push(Token::new(TokenKind::SpanEnd, end_pos));
 
            Ok(true)
 
        }
 
    }
 

	
 
    fn consume_line_comment(&mut self, source: &mut InputSource, target: &mut TokenBuffer) -> Result<(), ParseError> {
 
        let begin_pos = source.pos();
 

	
 
        // Consume the leading "//"
 
        debug_assert!(source.next().unwrap() == b'/' && source.lookahead(1).unwrap() == b'/');
 
        source.consume();
 
        source.consume();
 

	
 
        let mut prev_char = b'/';
 
        let mut cur_char = b'/';
 
        while let Some(c) = source.next() {
 
            prev_char = cur_char;
 
            cur_char = c;
 

	
 
            if c == b'\n' {
 
                // End of line, note that the newline is not consumed
 
                break;
 
            }
 

	
 
            source.consume();
 
        }
 

	
 
        let mut end_pos = source.pos();
 
        debug_assert_eq!(begin_pos.line, end_pos.line);
 

	
 
        // Modify offset to not include the newline characters
 
        if cur_char == b'\n' {
 
            if prev_char == b'\r' {
 
                end_pos.offset -= 2;
 
            } else {
 
                end_pos.offset -= 1;
 
            }
 
            // Consume final newline
 
            source.consume();
 
        } else {
 
            // End of comment was due to EOF
 
            debug_assert!(source.next().is_none())
 
        }
 

	
 
        target.tokens.push(Token::new(TokenKind::LineComment, begin_pos));
 
        target.tokens.push(Token::new(TokenKind::SpanEnd, end_pos));
 

	
 
        Ok(())
 
    }
 

	
 
    fn consume_block_comment(&mut self, source: &mut InputSource, target: &mut TokenBuffer) -> Result<(), ParseError> {
 
        let begin_pos = source.pos();
 

	
 
        // Consume the leading "/*"
 
        debug_assert!(source.next().unwrap() == b'/' && source.lookahead(1).unwrap() == b'*');
 
        source.consume();
 
        source.consume();
 

	
 
        // Explicitly do not put prev_char at "*", because then "/*/" would
 
        // represent a valid and closed block comment
 
        let mut prev_char = b' ';
 
        let mut is_closed = false;
 
        while let Some(c) = source.next() {
 
            source.consume();
 
            if prev_char == b'*' && c == b'/' {
 
                // End of block comment
 
                is_closed = true;
 
                break;
 
            }
 
            prev_char = c;
 
        }
 

	
 
        if !is_closed {
 
            return Err(ParseError::new_error_str_at_pos(
 
                source, source.pos(), "encountered unterminated block comment")
 
            );
 
        }
 

	
 
        let end_pos = source.pos();
 
        target.tokens.push(Token::new(TokenKind::BlockComment, begin_pos));
 
        target.tokens.push(Token::new(TokenKind::SpanEnd, end_pos));
 

	
 
        Ok(())
 
    }
 

	
 
    fn consume_identifier<'a>(&mut self, source: &'a mut InputSource, target: &mut TokenBuffer) -> Result<&'a [u8], ParseError> {
 
        let begin_pos = source.pos();
 
        debug_assert!(is_identifier_start(source.next().unwrap()));
 
        source.consume();
 

	
 
        // Keep reading until no more identifier
 
        while let Some(c) = source.next() {
 
            if !is_identifier_remaining(c) {
 
                break;
 
            }
 

	
 
            source.consume();
 
        }
 
        self.check_ascii(source)?;
 

	
 
        let end_pos = source.pos();
 
        target.tokens.push(Token::new(TokenKind::Ident, begin_pos));
 
        target.tokens.push(Token::new(TokenKind::SpanEnd, end_pos));
 
        Ok(source.section_at_pos(begin_pos, end_pos))
 
    }
 

	
 
    fn consume_number(&mut self, source: &mut InputSource, target: &mut TokenBuffer) -> Result<(), ParseError> {
 
        let begin_pos = source.pos();
 
        debug_assert!(is_integer_literal_start(source.next().unwrap()));
 
        source.consume();
 

	
 
        // Keep reading until it doesn't look like a number anymore
 
        while let Some(c) = source.next() {
 
            if !maybe_number_remaining(c) {
 
                break;
 
            }
 

	
 
            source.consume();
 
        }
 
        self.check_ascii(source)?;
 

	
 
        let end_pos = source.pos();
 
        target.tokens.push(Token::new(TokenKind::Integer, begin_pos));
 
        target.tokens.push(Token::new(TokenKind::SpanEnd, end_pos));
 

	
 
        Ok(())
 
    }
 

	
 
    // Consumes whitespace and returns whether or not the whitespace contained
 
    // a newline.
 
    fn consume_whitespace(&self, source: &mut InputSource) -> bool {
 
        debug_assert!(is_whitespace(source.next().unwrap()));
 

	
 
        let mut has_newline = false;
 
        while let Some(c) = source.next() {
 
            if !is_whitespace(c) {
 
                break;
 
            }
 

	
 
            if c == b'\n' {
 
                has_newline = true;
 
            }
 
            source.consume();
 
        }
 

	
 
        has_newline
 
    }
 

	
 
    fn add_code_range(
 
        &mut self, target: &mut TokenBuffer, parent_idx: i32,
 
        code_start_idx: u32, code_end_idx: u32
 
    ) {
 
        let new_range_idx = target.ranges.len() as i32;
 
        let parent_range = &mut target.ranges[parent_idx as usize];
 
        debug_assert_ne!(parent_range.end, code_start_idx, "called push_code_range without a need to do so");
 

	
 
        let sibling_idx = parent_range.last_child_idx;
 

	
 
        parent_range.last_child_idx = new_range_idx;
 
        parent_range.end = code_end_idx;
 
        parent_range.num_child_ranges += 1;
 

	
 
        let curly_depth = self.curly_stack.len() as u32;
 
        target.ranges.push(TokenRange{
 
            parent_idx,
 
            range_kind: TokenRangeKind::Code,
 
            curly_depth,
 
            start: code_start_idx,
 
            end: code_end_idx,
 
            num_child_ranges: 0,
 
            first_child_idx: NO_RELATION,
 
            last_child_idx: NO_RELATION,
 
            next_sibling_idx: new_range_idx + 1, // we're going to push this range below
 
        });
 

	
 
        // Fix up the sibling indices
 
        if sibling_idx != NO_RELATION {
 
            let sibling_range = &mut target.ranges[sibling_idx as usize];
 
            sibling_range.next_sibling_idx = new_range_idx;
 
        }
 
    }
 

	
 
    fn push_range(&mut self, target: &mut TokenBuffer, range_kind: TokenRangeKind, first_token_idx: u32) {
 
        let new_range_idx = target.ranges.len() as i32;
 
        let parent_idx = self.stack_idx as i32;
 
        let parent_range = &mut target.ranges[self.stack_idx];
 
        let curly_depth = self.curly_stack.len() as u32;
 

	
 
        if parent_range.first_child_idx == NO_RELATION {
 
            parent_range.first_child_idx = new_range_idx;
 
        }
 

	
 
        if parent_range.end != first_token_idx {
 
            // We popped a range, processed some intermediate tokens and now
 
            // enter a new range. Those intermediate tokens do not belong to a
 
            // particular range yet. So we put them in a "code" range.
 

	
 
            // Remember last sibling from parent (if any)
 
            let sibling_idx = parent_range.last_child_idx;
 

	
 
            // Push the code range
 
            let code_start_idx = parent_range.end;
 
            let code_end_idx = first_token_idx;
 

	
 
            parent_range.last_child_idx = new_range_idx;
 
            parent_range.end = code_end_idx;
 
            parent_range.num_child_ranges += 1;
 

	
 
            target.ranges.push(TokenRange{
 
                parent_idx,
 
                range_kind: TokenRangeKind::Code,
 
                curly_depth,
 
                start: code_start_idx,
 
                end: code_end_idx,
 
                num_child_ranges: 0,
 
                first_child_idx: NO_RELATION,
 
                last_child_idx: NO_RELATION,
 
                next_sibling_idx: new_range_idx + 1, // we're going to push this range below
 
            });
 

	
 
            // Fix up the sibling indices
 
            if sibling_idx != NO_RELATION {
 
                let sibling_range = &mut target.ranges[sibling_idx as usize];
 
                sibling_range.next_sibling_idx = new_range_idx;
 
            }
 
        let last_registered_idx = parent_range.end;
 
        if last_registered_idx != first_token_idx {
 
            self.add_code_range(target, parent_idx, last_registered_idx, first_token_idx);
 
        }
 

	
 
        // Push the new range
 
        self.stack_idx = target.ranges.len();
 
        let curly_depth = self.curly_stack.len() as u32;
 
        target.ranges.push(TokenRange{
 
            parent_idx,
 
            range_kind,
 
            curly_depth,
 
            start: first_token_idx,
 
            end: first_token_idx, // modified when popped
 
            num_child_ranges: 0,
 
            first_child_idx: NO_RELATION,
 
            last_child_idx: NO_RELATION,
 
            next_sibling_idx: NO_RELATION
 
        })
 
    }
 

	
 
    fn pop_range(&mut self, target: &mut TokenBuffer, end_token_idx: u32) {
 
        let popped_idx = self.stack_idx as i32;
 
        let popped_range = &mut target.ranges[self.stack_idx];
 
        debug_assert!(self.stack_idx != 0, "attempting to pop top-level range");
 

	
 
        // Fix up the current range before going back to parent
 
        popped_range.end = end_token_idx;
 
        debug_assert_ne!(popped_range.start, end_token_idx);
 

	
 
        // Go back to parent and fix up its child pointers, but remember the
 
        // last child, so we can link it to the newly popped range.
 
        self.stack_idx = popped_range.parent_idx as usize;
 
        let parent = &mut target.ranges[self.stack_idx];
 
        if parent.first_child_idx == NO_RELATION {
 
            parent.first_child_idx = popped_idx;
 
        }
 
        let prev_sibling_idx = parent.last_child_idx;
 
        parent.last_child_idx = popped_idx;
 
        parent.end = end_token_idx;
 
        parent.num_child_ranges += 1;
 

	
 
        // Fix up the sibling (if it exists)
 
        if prev_sibling_idx != NO_RELATION {
 
            let sibling = &mut target.ranges[prev_sibling_idx as usize];
 
            sibling.next_sibling_idx = popped_idx;
 
        }
 
    }
 

	
 

	
 
    fn check_ascii(&self, source: &InputSource) -> Result<(), ParseError> {
 
        match source.next() {
 
            Some(c) if !c.is_ascii() => {
 
                Err(ParseError::new_error_str_at_pos(source, source.pos(), "encountered a non-ASCII character"))
 
            },
 
            _else => {
 
                Ok(())
 
            },
 
        }
 
    }
 
}
 

	
 
// Helpers for characters
 
fn demarks_definition(ident: &[u8]) -> bool {
 
    return
 
        ident == KW_STRUCT ||
 
            ident == KW_ENUM ||
 
            ident == KW_UNION ||
 
            ident == KW_FUNCTION ||
 
            ident == KW_PRIMITIVE ||
 
            ident == KW_COMPOSITE
 
}
 

	
 
fn demarks_import(ident: &[u8]) -> bool {
 
    return ident == KW_IMPORT;
 
}
 

	
 
fn is_whitespace(c: u8) -> bool {
 
    c.is_ascii_whitespace()
 
}
 

	
 
fn is_char_literal_start(c: u8) -> bool {
 
    return c == b'\'';
 
}
 

	
 
fn is_string_literal_start(c: u8) -> bool {
 
    return c == b'"';
 
}
 

	
 
fn is_pragma_start_or_pound(c: u8) -> bool {
 
    return c == b'#';
 
}
 

	
 
fn is_identifier_start(c: u8) -> bool {
 
    return
 
        (c >= b'a' && c <= b'z') ||
 
            (c >= b'A' && c <= b'Z') ||
 
            c == b'_'
 
}
 

	
 
fn is_identifier_remaining(c: u8) -> bool {
 
    return
 
        (c >= b'0' && c <= b'9') ||
 
            (c >= b'a' && c <= b'z') ||
 
            (c >= b'A' && c <= b'Z') ||
 
            c == b'_'
 
}
 

	
 
fn is_integer_literal_start(c: u8) -> bool {
 
    return c >= b'0' && c <= b'9';
 
}
 

	
 
fn maybe_number_remaining(c: u8) -> bool {
 
    return
 
        (c == b'b' || c == b'B' || c == b'o' || c == b'O' || c == b'x' || c == b'X') ||
 
            (c >= b'0' && c <= b'9') ||
 
            c == b'_';
 
}
 

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

	
 
    // TODO: Remove at some point
 
    #[test]
 
    fn test_tokenizer() {
 
        let mut source = InputSource::new_test("
 

	
 
        #version 500
 
        # hello 2
 

	
 
        import std.reo::*;
 

	
 
        struct Thing {
 
            int a: 5,
 
        }
 
        enum Hello {
 
            A,
 
            B
 
        }
 

	
 
        // Hello hello, is it me you are looking for?
 
        // I can seee it in your eeeyes
 

	
 
        func something(int a, int b, int c) -> byte {
 
            int a = 5;
 
            struct Inner {
 
                int a
 
            }
 
            struct City {
 
                int b
 
            }
 
            /* Waza
 
            How are you doing
 
            Things in here yo
 
            /* */ */
 

	
 
            a = a + 5 * 2;
 
            struct Pressure {
 
                int d
 
            }
 
        }
 
        ");
 
        let mut t = PassTokenizer::new();
 
        let mut buffer = TokenBuffer::new();
 
        t.tokenize(&mut source, &mut buffer).expect("tokenize");
 

	
 
        println!("Ranges:\n");
 
        for (idx, range) in buffer.ranges.iter().enumerate() {
 
            println!("[{}] {:?}", idx, range)
 
        }
 

	
 
        println!("Tokens:\n");
 
        let mut iter = buffer.tokens.iter().enumerate();
 
        while let Some((idx, token)) = iter.next() {
 
            match token.kind {
 
                TokenKind::Ident | TokenKind::Pragma | TokenKind::Integer |
 
                TokenKind::String | TokenKind::Character | TokenKind::LineComment |
 
                TokenKind::BlockComment => {
 
                    let (_, end) = iter.next().unwrap();
 
                    println!("[{}] {:?} ......", idx, token.kind);
 
                    assert_eq!(end.kind, TokenKind::SpanEnd);
 
                    let text = source.section_at_pos(token.pos, end.pos);
 
                    println!("{}", String::from_utf8_lossy(text));
 
                },
 
                _ => {
 
                    println!("[{}] {:?}", idx, token.kind);
 
                }
 
            }
 
        }
 
    }
 
}
 
\ No newline at end of file

Changeset was too big and was cut off... Show full diff anyway

0 comments (0 inline, 0 general)