Changeset - e1432caf0735
[Not reviewed]
1 6 1
MH - 3 years ago 2022-03-25 10:37:47
contact@maxhenger.nl
Replace reserved keywords with global std lib funcs
7 files changed with 47 insertions and 19 deletions:
0 comments (0 inline, 0 general)
src/protocol/ast_writer.rs
Show inline comments
 
file renamed from src/protocol/ast_printer.rs to src/protocol/ast_writer.rs
src/protocol/mod.rs
Show inline comments
 
mod arena;
 
pub(crate) mod eval;
 
pub(crate) mod input_source;
 
mod parser;
 
#[cfg(test)] mod tests;
 

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

	
 
use std::sync::Mutex;
 

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

	
 
pub use parser::type_table::TypeId;
 

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

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

	
 
impl ProtocolDescription {
 
    pub fn parse(buffer: &[u8]) -> Result<Self, String> {
 
        let source = InputSource::new(String::new(), Vec::from(buffer));
 
        let mut parser = Parser::new()?;
 
        parser.feed(source).expect("failed to feed source");
 
        
src/protocol/parser/mod.rs
Show inline comments
 
#[macro_use] mod visitor;
 
pub(crate) mod symbol_table;
 
pub(crate) mod type_table;
 
pub(crate) mod tokens;
 
pub(crate) mod token_parsing;
 
pub(crate) mod pass_tokenizer;
 
pub(crate) mod pass_symbols;
 
pub(crate) mod pass_imports;
 
pub(crate) mod pass_definitions;
 
pub(crate) mod pass_definitions_types;
 
pub(crate) mod pass_validation_linking;
 
pub(crate) mod pass_rewriting;
 
pub(crate) mod pass_typing;
 
pub(crate) mod pass_stack_size;
 

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

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

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

	
 
const REOWOLF_PATH_ENV: &'static str = "REOWOLF_ROOT"; // first lookup reowolf path
 
const REOWOLF_PATH_DIR: &'static str = "std"; // then try folder in current working directory
 

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

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

	
 
pub struct TargetArch {
 
    pub void_type_id: TypeId,
 
    pub message_type_id: TypeId,
 
    pub bool_type_id: TypeId,
 
    pub uint8_type_id: TypeId,
 
    pub uint16_type_id: TypeId,
 
    pub uint32_type_id: TypeId,
 
    pub uint64_type_id: TypeId,
 
    pub sint8_type_id: TypeId,
 
    pub sint16_type_id: TypeId,
 
    pub sint32_type_id: TypeId,
 
    pub sint64_type_id: TypeId,
 
    pub char_type_id: TypeId,
 
    pub string_type_id: TypeId,
 
    pub array_type_id: TypeId,
 
    pub slice_type_id: TypeId,
 
    pub input_type_id: TypeId,
 
    pub output_type_id: TypeId,
 
    pub pointer_type_id: TypeId,
 
}
 

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

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

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

	
 
impl Parser {
 
    pub fn new() -> Result<Self, String> {
 
        let mut parser = Parser{
 
            heap: Heap::new(),
 
            string_pool: StringPool::new(),
 
            modules: Vec::new(),
 
            symbol_table: SymbolTable::new(),
 
            type_table: TypeTable::new(),
 
            global_module_index: 0,
 
            pass_tokenizer: PassTokenizer::new(),
 
            pass_symbols: PassSymbols::new(),
 
            pass_import: PassImport::new(),
 
            pass_definitions: PassDefinitions::new(),
 
            pass_validation: PassValidationLinking::new(),
 
            pass_typing: PassTyping::new(),
 
            pass_rewriting: PassRewriting::new(),
 
            pass_stack_size: PassStackSize::new(),
 
            write_ast_to: None,
 
            arch: TargetArch::new(),
 
        };
 

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

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

	
 
        // Parse standard library
 
        parser.feed_standard_library()?;
 

	
 
        return Ok(parser)
 
    }
 

	
 
    pub fn feed(&mut self, mut source: InputSource) -> Result<(), ParseError> {
 
    /// Feeds a new InputSource to the parser, which will tokenize it and store
 
    /// it internally for later parsing (when all modules are present). Returns
 
    /// the index of the new module.
 
    pub fn feed(&mut self, mut source: InputSource) -> Result<usize, ParseError> {
 
        let mut token_buffer = TokenBuffer::new();
 
        self.pass_tokenizer.tokenize(&mut source, &mut token_buffer)?;
 

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

	
 
        Ok(())
 
        return Ok(module_index);
 
    }
 

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

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

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

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

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

	
 
        // Perform typechecking on all modules
 
        let mut queue = ResolveQueue::new();
 
        for module_idx in 0..self.modules.len() {
 
            let mut ctx = visitor::Ctx{
 
                heap: &mut self.heap,
 
                modules: &mut self.modules,
 
                module_idx,
 
                symbols: &mut self.symbol_table,
 
                types: &mut self.type_table,
 
@@ -275,90 +282,99 @@ impl Parser {
 
                types: &mut self.type_table,
 
                arch: &self.arch,
 
            };
 
            self.pass_rewriting.visit_module(&mut ctx)?;
 
            self.pass_stack_size.visit_module(&mut ctx)?;
 
        }
 

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

	
 
        Ok(())
 
    }
 

	
 
    /// Tries to find the standard library and add the files for parsing.
 
    fn feed_standard_library(&mut self) -> Result<(), String> {
 
        use std::env;
 
        use std::path::{Path, PathBuf};
 
        use std::fs;
 

	
 
        const FILES: [&'static str; 1] = [
 
            "std.global.pdl",
 
        ];
 

	
 
        // Determine base directory
 
        let (base_path, from_env) = if let Ok(path) = env::var(REOWOLF_PATH_ENV) {
 
            // Path variable is set
 
            (path, true)
 
        } else {
 
            let mut path = String::with_capacity(REOWOLF_PATH_DIR.len() + 2);
 
            path.push_str("./");
 
            path.push_str(REOWOLF_PATH_DIR);
 
            (path, false)
 
        };
 

	
 
        // Make sure directory exists
 
        let path = Path::new(&base_path);
 
        if !path.exists() {
 
            return Err(format!("std lib root directory '{}' does not exist", base_path));
 
        }
 

	
 
        // Try to load all standard library files. We might need a more unified
 
        // way to do this in the future (i.e. a "std" package, containing all
 
        // of the modules)
 
        let mut file_path = PathBuf::new();
 
        let mut first_file = true;
 

	
 
        for file in FILES {
 
            file_path.push(path);
 
            file_path.push(file);
 

	
 
            let source = fs::read(file_path.as_path());
 
            if let Err(err) = source {
 
                return Err(format!(
 
                    "failed to read std lib file '{}' in root directory '{}', because: {}",
 
                    file, base_path, err
 
                ));
 
            }
 

	
 
            let source = source.unwrap();
 
            let input_source = InputSource::new(file.to_string(), source);
 

	
 
            if let Err(err) = self.feed(input_source) {
 
            let module_index = self.feed(input_source);
 
            if let Err(err) = module_index {
 
                // A bit of a hack, but shouldn't really happen anyway: the
 
                // compiler should ship with a decent standard library (at some
 
                // point)
 
                return Err(format!("{}", err));
 
            }
 
            let module_index = module_index.unwrap();
 

	
 
            if first_file {
 
                self.global_module_index = module_index;
 
                first_file = false;
 
            }
 
        }
 

	
 
        return Ok(())
 
    }
 
}
 

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

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

	
 
    return type_table.add_builtin_data_type(concrete_type, poly_var, size, alignment);
 
}
 
\ No newline at end of file
src/protocol/parser/pass_definitions.rs
Show inline comments
 
@@ -210,192 +210,201 @@ impl PassDefinitions {
 
        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();
 
                        self.type_parser.consume_parser_type(
 
                            iter, &ctx.heap, source, &ctx.symbols, poly_vars, definition_id,
 
                            module_scope, false, None
 
                        )
 
                    },
 
                    &mut types_section, "an embedded type", Some(&mut close_pos)
 
                )?;
 
                let value = if has_embedded {
 
                    types_section.into_vec()
 
                } else {
 
                    types_section.forget();
 
                    Vec::new()
 
                };
 

	
 
                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> {
 
        // Retrieve function name
 
        consume_exact_ident(&module.source, iter, KW_FUNCTION)?;
 
        let (ident_text, _) = consume_ident(&module.source, iter)?;
 
        let stringy = String::from_utf8_lossy(ident_text).to_string();
 

	
 
        // 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.variables.start_section();
 
        consume_parameter_list(
 
            &mut self.type_parser, &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 poly_vars = ctx.heap[definition_id].poly_vars();
 
        let parser_type = self.type_parser.consume_parser_type(
 
            iter, &ctx.heap, &module.source, &ctx.symbols, poly_vars, definition_id,
 
            module_scope, false, None
 
        )?;
 

	
 
        // Consume body
 
        let (body_id, source) = self.consume_procedure_body(module, iter, ctx, definition_id, ProcedureKind::Function)?;
 
        let scope_id = ctx.heap.alloc_scope(|this| Scope::new(this, ScopeAssociation::Definition(definition_id)));
 

	
 
        // Assign everything in the preallocated AST node
 
        let function = ctx.heap[definition_id].as_procedure_mut();
 
        function.source = source;
 
        function.return_type = Some(parser_type);
 
        function.parameters = parameters;
 
        function.scope = scope_id;
 
        function.body = body_id;
 

	
 
        Ok(())
 
    }
 

	
 
    fn visit_component_definition(
 
        &mut self, module: &Module, iter: &mut TokenIter, ctx: &mut PassCtx
 
    ) -> Result<(), ParseError> {
 
        // Consume component variant and name
 
        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.variables.start_section();
 
        consume_parameter_list(
 
            &mut self.type_parser, &module.source, iter, ctx, &mut parameter_section, module_scope, definition_id
 
        )?;
 
        let parameters = parameter_section.into_vec();
 

	
 
        // Consume body
 
        let procedure_kind = ctx.heap[definition_id].as_procedure().kind;
 
        let (body_id, source) = self.consume_procedure_body(module, iter, ctx, definition_id, procedure_kind)?;
 
        let scope_id = ctx.heap.alloc_scope(|this| Scope::new(this, ScopeAssociation::Definition(definition_id)));
 

	
 
        // Assign everything in the AST node
 
        let component = ctx.heap[definition_id].as_procedure_mut();
 
        debug_assert!(component.return_type.is_none());
 
        component.source = source;
 
        component.parameters = parameters;
 
        component.scope = scope_id;
 
        component.body = body_id;
 

	
 
        Ok(())
 
    }
 

	
 
    /// Consumes a procedure's body: either a user-defined procedure, which we
 
    /// parse as normal, or a builtin function, where we'll make sure we expect
 
    /// the particular builtin.
 
    ///
 
    /// We expect that the procedure's name is already stored in the
 
    /// preallocated AST node.
 
    fn consume_procedure_body(
 
        &mut self, module: &Module, iter: &mut TokenIter, ctx: &mut PassCtx, definition_id: DefinitionId, kind: ProcedureKind
 
    ) -> Result<(BlockStatementId, ProcedureSource), ParseError> {
 
        if iter.peek() == Some(TokenKind::Pragma) {
 
        if iter.next() == Some(TokenKind::OpenCurly) && iter.peek() == Some(TokenKind::Pragma) {
 
            // Consume the placeholder "{ #builtin }" tokens
 
            iter.consume(); // opening curly brace
 
            let (pragma, pragma_start, pragma_end) = consume_pragma(&module.source, iter)?;
 
            if pragma != b"#builtin" {
 
                return Err(ParseError::new_error_str_at_span(
 
                    &module.source, InputSpan::from_positions(pragma_start, pragma_end),
 
                    "expected a '#builtin' pragma, or a function body"
 
                ));
 
            }
 

	
 
            if iter.next() != Some(TokenKind::CloseCurly) {
 
                // Just to keep the compiler writers in line ;)
 
                panic!("compiler error: when using the #builtin pragma, wrap it in curly braces");
 
            }
 
            iter.consume();
 

	
 
            // Retrieve module and procedure name
 
            assert!(module.name.is_some(), "compiler error: builtin procedure body in unnamed module");
 
            let (_, module_name) = module.name.as_ref().unwrap();
 
            let module_name = module_name.as_str();
 

	
 
            let definition = ctx.heap[definition_id].as_procedure();
 
            let procedure_name = definition.identifier.value.as_str();
 

	
 
            let source = match (module_name, procedure_name) {
 
                ("std.global", "get") => ProcedureSource::FuncGet,
 
                ("std.global", "put") => ProcedureSource::FuncPut,
 
                ("std.global", "fires") => ProcedureSource::FuncFires,
 
                ("std.global", "create") => ProcedureSource::FuncCreate,
 
                ("std.global", "length") => ProcedureSource::FuncLength,
 
                ("std.global", "assert") => ProcedureSource::FuncAssert,
 
                ("std.global", "print") => ProcedureSource::FuncPrint,
 
                _ => panic!(
 
                    "compiler error: unknown builtin procedure '{}' in module '{}'",
 
                    procedure_name, module_name
 
                ),
 
            };
 

	
 
            return Ok((BlockStatementId::new_invalid(), source));
 
        } else {
 
            let body_id = self.consume_block_statement(module, iter, ctx)?;
 
            let source = match kind {
 
                ProcedureKind::Function =>
 
                    ProcedureSource::FuncUserDefined,
 
                ProcedureKind::Primitive | ProcedureKind::Composite =>
 
                    ProcedureSource::CompUserDefined,
 
            };
 

	
 
            return Ok((body_id, source))
 
        }
 
    }
 

	
 
    /// 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) -> Result<StatementId, 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)?;
 
            return Ok(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
src/protocol/parser/pass_symbols.rs
Show inline comments
 
@@ -150,96 +150,97 @@ impl PassSymbols {
 
                    &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"
 
                ));
 
            }
 

	
 
            module.name = Some((pragma_id, module_name));
 
            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);
 

	
 
            module.version = Some((pragma_id, version as i64));
 
            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)?;
 
        println!("DEBUG: Parsing {} --- {}", String::from_utf8_lossy(kw_text).to_string(), identifier.value.as_str());
 
        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 proc_def_id = ctx.heap.alloc_procedure_definition(|this| {
 
                    ProcedureDefinition::new_empty(this, module.root_id, definition_span, ProcedureKind::Function, identifier, poly_vars)
 
                });
 
                definition_class = DefinitionClass::Function;
 
                ast_definition_id = proc_def_id.upcast();
 
            },
 
            KW_PRIMITIVE | KW_COMPOSITE => {
 
                let procedure_kind = if kw_text == KW_PRIMITIVE {
 
                    ProcedureKind::Primitive
 
                } else {
 
                    ProcedureKind::Composite
 
                };
 
                let proc_def_id = ctx.heap.alloc_procedure_definition(|this| {
src/protocol/parser/token_parsing.rs
Show inline comments
 
@@ -495,142 +495,144 @@ pub(crate) fn consume_exact_ident(source: &InputSource, iter: &mut TokenIter, ex
 
        ));
 
    }
 
    Ok(pos)
 
}
 

	
 
/// Consumes an identifier that is not a reserved keyword and returns it
 
/// together with its span.
 
pub(crate) fn consume_ident<'a>(
 
    source: &'a InputSource, iter: &mut TokenIter
 
) -> Result<(&'a [u8], InputSpan), ParseError> {
 
    let (ident, span) = consume_any_ident(source, iter)?;
 
    if is_reserved_keyword(ident) {
 
        return Err(ParseError::new_error_str_at_span(source, span, "encountered reserved keyword"));
 
    }
 

	
 
    Ok((ident, span))
 
}
 

	
 
/// Consumes an identifier and immediately intern it into the `StringPool`
 
pub(crate) fn consume_ident_interned(
 
    source: &InputSource, iter: &mut TokenIter, ctx: &mut PassCtx
 
) -> Result<Identifier, ParseError> {
 
    let (value, span) = consume_ident(source, iter)?;
 
    let value = ctx.pool.intern(value);
 
    Ok(Identifier{ span, value })
 
}
 

	
 
fn is_reserved_definition_keyword(text: &[u8]) -> bool {
 
    match text {
 
        KW_STRUCT | KW_ENUM | KW_UNION | KW_FUNCTION | KW_PRIMITIVE | KW_COMPOSITE => true,
 
        _ => false,
 
    }
 
}
 

	
 
fn is_reserved_statement_keyword(text: &[u8]) -> bool {
 
    match text {
 
        KW_IMPORT | KW_AS |
 
        KW_STMT_CHANNEL | KW_STMT_IF | KW_STMT_WHILE |
 
        KW_STMT_BREAK | KW_STMT_CONTINUE | KW_STMT_GOTO | KW_STMT_RETURN |
 
        KW_STMT_SYNC | KW_STMT_FORK | KW_STMT_NEW => true,
 
        _ => false,
 
    }
 
}
 

	
 
fn is_reserved_expression_keyword(text: &[u8]) -> bool {
 
    match text {
 
        KW_LET | KW_CAST |
 
        KW_LIT_TRUE | KW_LIT_FALSE | KW_LIT_NULL |
 
        KW_FUNC_GET | KW_FUNC_PUT | KW_FUNC_FIRES | KW_FUNC_CREATE | KW_FUNC_ASSERT | KW_FUNC_LENGTH | KW_FUNC_PRINT => true,
 
        // TODO: Remove this once global namespace errors work @nocommit
 
        // KW_FUNC_GET | KW_FUNC_PUT | KW_FUNC_FIRES | KW_FUNC_CREATE | KW_FUNC_ASSERT | KW_FUNC_LENGTH | KW_FUNC_PRINT => true,
 
        _ => false,
 
    }
 
}
 

	
 
fn is_reserved_type_keyword(text: &[u8]) -> bool {
 
    match text {
 
        KW_TYPE_IN_PORT | KW_TYPE_OUT_PORT | KW_TYPE_MESSAGE | KW_TYPE_BOOL |
 
        KW_TYPE_UINT8 | KW_TYPE_UINT16 | KW_TYPE_UINT32 | KW_TYPE_UINT64 |
 
        KW_TYPE_SINT8 | KW_TYPE_SINT16 | KW_TYPE_SINT32 | KW_TYPE_SINT64 |
 
        KW_TYPE_CHAR | KW_TYPE_STRING |
 
        KW_TYPE_INFERRED => true,
 
        _ => false,
 
    }
 
}
 

	
 
fn is_reserved_keyword(text: &[u8]) -> bool {
 
    return
 
        is_reserved_definition_keyword(text) ||
 
        is_reserved_statement_keyword(text) ||
 
        is_reserved_expression_keyword(text) ||
 
        is_reserved_type_keyword(text);
 
}
 

	
 
pub(crate) fn seek_module(modules: &[Module], root_id: RootId) -> Option<&Module> {
 
    for module in modules {
 
        if module.root_id == root_id {
 
            return Some(module)
 
        }
 
    }
 

	
 
    return None
 
}
 

	
 
/// Constructs a human-readable message indicating why there is a conflict of
 
/// symbols.
 
// Note: passing the `module_idx` is not strictly necessary, but will prevent
 
// programmer mistakes during development: we get a conflict because we're
 
// currently parsing a particular module.
 
pub(crate) fn construct_symbol_conflict_error(
 
    modules: &[Module], module_idx: usize, ctx: &PassCtx, new_symbol: &Symbol, old_symbol: &Symbol
 
) -> ParseError {
 
    let module = &modules[module_idx];
 
    let get_symbol_span_and_msg = |symbol: &Symbol| -> (String, Option<InputSpan>) {
 
        match &symbol.variant {
 
            SymbolVariant::Module(module) => {
 
                let import = &ctx.heap[module.introduced_at];
 
                return (
 
                    format!("the module aliased as '{}' imported here", symbol.name.as_str()),
 
                    Some(import.as_module().span)
 
                );
 
            },
 
            SymbolVariant::Definition(definition) => {
 
                if definition.defined_in_module.is_invalid() {
 
                    // Must be a builtin thing
 
                    return (format!("the builtin '{}'", symbol.name.as_str()), None)
 
                } else {
 
                    if let Some(import_id) = definition.imported_at {
 
                        let import = &ctx.heap[import_id];
 
                        return (
 
                            format!("the type '{}' imported here", symbol.name.as_str()),
 
                            Some(import.as_symbols().span)
 
                        );
 
                    } else {
 
                        // This is a defined symbol. So this must mean that the
 
                        // error was caused by it being defined.
 
                        debug_assert_eq!(definition.defined_in_module, module.root_id);
 

	
 
                    } else if definition.defined_in_module == module.root_id {
 
                        // This is a symbol defined in the same module
 
                        return (
 
                            format!("the type '{}' defined here", symbol.name.as_str()),
 
                            Some(definition.identifier_span)
 
                        )
 
                    } else {
 
                        // Not imported, not defined in the module, so must be
 
                        // a global
 
                        return (format!("the global '{}'", symbol.name.as_str()), None)
 
                    }
 
                }
 
            }
 
        }
 
    };
 

	
 
    let (new_symbol_msg, new_symbol_span) = get_symbol_span_and_msg(new_symbol);
 
    let (old_symbol_msg, old_symbol_span) = get_symbol_span_and_msg(old_symbol);
 
    let new_symbol_span = new_symbol_span.unwrap(); // because new symbols cannot be builtin
 

	
 
    match old_symbol_span {
 
        Some(old_symbol_span) => ParseError::new_error_at_span(
 
            &module.source, new_symbol_span, format!("symbol is defined twice: {}", new_symbol_msg)
 
        ).with_info_at_span(
 
            &module.source, old_symbol_span, format!("it conflicts with {}", old_symbol_msg)
 
        ),
 
        None => ParseError::new_error_at_span(
 
            &module.source, new_symbol_span,
 
            format!("symbol is defined twice: {} conflicts with {}", new_symbol_msg, old_symbol_msg)
 
        )
 
    }
 
}
 
\ No newline at end of file
std/std.global.pdl
Show inline comments
 
#module std.global
 

	
 
func get<T>(in<T>) -> T #builtin
 
func put<T>(out<T>, T value) -> #type_void #builtin
 
func fires<T>(#type_portlike<T>) -> bool #builtin
 
func create<T>(#type_integerlike length) -> T[] #builtin
 
func length<T>(#type_arraylike<T> array) -> u32 #builtin
 
func assert(bool condition) -> #type_void #builtin
 
func print(string message) -> #type_void #builtin
 
\ No newline at end of file
 
func get<T>(in<T> input) -> T { #builtin }
 
func put<T>(out<T> output, T value) -> #type_void { #builtin }
 
func fires<T>(#type_portlike<T>) -> bool { #builtin }
 
func create<T>(#type_integerlike length) -> T[] { #builtin }
 
func length<T>(#type_arraylike<T> array) -> u32 { #builtin }
 
func assert(bool condition) -> #type_void { #builtin }
 
func print(string message) -> #type_void { #builtin }
 
\ No newline at end of file
0 comments (0 inline, 0 general)