Changeset - d7baa792c2c2
[Not reviewed]
src/protocol/input_source.rs
Show inline comments
 
use std::fmt;
 
use std::sync::{RwLock, RwLockReadGuard};
 
use std::fmt::Write;
 

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

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

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

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

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

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

	
 
    #[cfg(test)]
 
    pub fn new_test(input: &str) -> Self {
 
        let bytes = Vec::from(input.as_bytes());
 
        return Self::new(String::from("test"), bytes)
 
    }
 

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

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

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

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

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

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

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

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

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

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

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

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

	
 
        lookup.push(self.input.len() as u32); // for lookup_line_end
 
        lookup.push(self.input.len() as u32 + 1); // for lookup_line_end, intentionally adding one character
 
        debug_assert_eq!(self.line as usize + 2, lookup.len(), "remove me: i am a testing assert and sometimes invalid");
 

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

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

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

	
 
        // Compensate for newlines and a potential carriage feed
 
        if self.input[offset_usize] == b'\n' {
 
            if offset_usize > 0 && self.input[offset_usize] == b'\r' {
 
                offset - 2
 
            } else {
 
        // Compensate for newlines and a potential carriage feed. Note that the
 
        // end position is exclusive. So we only need to compensate for a
 
        // "\r\n"
 
        if offset_usize > 0 && offset_usize < self.input.len() && self.input[offset_usize] == b'\n' && self.input[offset_usize - 1] == b'\r' {
 
            offset - 1
 
            }
 
        } else {
 
            offset
 
        }
 
    }
 
}
 

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

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

	
 
#[derive(Debug)]
 
pub struct ParseErrorStatement {
 
    pub(crate) statement_kind: StatementKind,
 
    pub(crate) context_kind: ContextKind,
 
    pub(crate) start_line: u32,
 
    pub(crate) start_column: u32,
 
    pub(crate) end_line: u32,
 
    pub(crate) end_column: u32,
 
    pub(crate) filename: String,
 
    pub(crate) context: String,
 
    pub(crate) message: String,
 
}
 

	
 
impl ParseErrorStatement {
 
    fn from_source_at_pos(statement_kind: StatementKind, source: &InputSource, position: InputPosition, message: String) -> Self {
 
        // Seek line start and end
 
        let line_start = source.lookup_line_start_offset(position.line);
 
        let line_end = source.lookup_line_end_offset(position.line);
 
        let context = Self::create_context(source, line_start as usize, line_end as usize);
 
        debug_assert!(position.offset >= line_start);
 
        let column = position.offset - line_start + 1;
 

	
 
        Self{
 
            statement_kind,
 
            context_kind: ContextKind::SingleLine,
 
            start_line: position.line,
 
            start_column: column,
 
            end_line: position.line,
 
            end_column: column + 1,
 
            filename: source.filename.clone(),
 
            context,
 
            message,
 
        }
 
    }
 

	
 
    fn from_source_at_span(statement_kind: StatementKind, source: &InputSource, span: InputSpan, message: String) -> Self {
 
        debug_assert!(span.end.line >= span.begin.line);
 
        debug_assert!(span.end.offset >= span.begin.offset);
 

	
 
        let first_line_start = source.lookup_line_start_offset(span.begin.line);
 
        let last_line_start = source.lookup_line_start_offset(span.end.line);
 
        let last_line_end = source.lookup_line_end_offset(span.end.line);
 
        let context = Self::create_context(source, first_line_start as usize, last_line_end as usize);
 
        debug_assert!(span.begin.offset >= first_line_start);
 
        let start_column = span.begin.offset - first_line_start + 1;
 
        let end_column = span.end.offset - last_line_start + 1;
 

	
 
        let context_kind = if span.begin.line == span.end.line {
 
            ContextKind::SingleLine
 
        } else {
 
            ContextKind::MultiLine
 
        };
 

	
 
        Self{
 
            statement_kind,
 
            context_kind,
 
            start_line: span.begin.line,
 
            start_column,
 
            end_line: span.end.line,
 
            end_column,
 
            filename: source.filename.clone(),
 
            context,
 
            message,
 
        }
 
    }
 

	
 
    /// Produces context from source
 
    fn create_context(source: &InputSource, start: usize, end: usize) -> String {
 
        let context_raw = &source.input[start..end];
 
        String::from_utf8_lossy(context_raw).to_string()
 
    }
 
}
 

	
 
impl fmt::Display for ParseErrorStatement {
 
    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
 
        // Write kind of statement and message
 
        match self.statement_kind {
 
            StatementKind::Info => f.write_str(" INFO: ")?,
 
            StatementKind::Error => f.write_str("ERROR: ")?,
 
        }
 
        f.write_str(&self.message)?;
 
        f.write_char('\n')?;
 

	
 
        // Write originating file/line/column
 
        f.write_str(" +- ")?;
 
        if !self.filename.is_empty() {
 
            write!(f, "in {} ", self.filename)?;
 
        }
 

	
 
        match self.context_kind {
 
            ContextKind::SingleLine => writeln!(f, " at {}:{}", self.start_line, self.start_column),
 
            ContextKind::MultiLine => writeln!(
 
                f, " from {}:{} to {}:{}",
 
                self.start_line, self.start_column, self.end_line, self.end_column
 
            )
 
        }?;
 

	
 
        // Helper function for writing context: converting tabs into 4 spaces
 
        // (oh, the controversy!) and creating an annotated line
 
        fn transform_context(source: &str, target: &mut String) {
 
            for char in source.chars() {
 
                if char == '\t' {
 
                    target.push_str("    ");
 
                } else {
 
                    target.push(char);
 
                }
 
            }
 
        }
 

	
 
        fn extend_annotation(first_col: u32, last_col: u32, source: &str, target: &mut String, extend_char: char) {
 
            debug_assert!(first_col > 0 && last_col > first_col);
 

	
 
            // If the first index exceeds the size of the context then we should
 
            // have a message placed at the newline character
 
            let first_idx = first_col as usize - 1;
 
            let last_idx = last_col as usize - 1;
 
            if first_idx >= source.len() {
 
                // If any of these fail then the logic behind reporting errors
 
                // is incorrect.
 
                debug_assert_eq!(first_idx, source.len());
 
                debug_assert_eq!(first_idx + 1, last_idx);
 
                target.push(extend_char);
 
            } else {
 
                for (char_idx, char) in source.chars().enumerate().skip(first_idx) {
 
                    if char_idx == last_idx as usize {
 
                        break;
 
                    }
 

	
 
                    if char == '\t' {
 
                        for _ in 0..4 { target.push(extend_char); }
 
                    } else {
 
                        target.push(extend_char);
 
                    }
 
                }
 
            }
 
        }
 

	
 
        // Write source context
 
        writeln!(f, " | ")?;
 

	
 
        let mut context = String::with_capacity(128);
 
        let mut annotation = String::with_capacity(128);
 

	
 
        match self.context_kind {
 
            ContextKind::SingleLine => {
 
                // Write single line of context with indicator for the offending
 
                // span underneath.
 
                context.push_str(" |  ");
 
                transform_context(&self.context, &mut context);
 
                context.push('\n');
 
                f.write_str(&context)?;
 

	
 
                annotation.push_str(" | ");
 
                extend_annotation(1, self.start_column + 1, &self.context, &mut annotation, ' ');
 
                extend_annotation(self.start_column, self.end_column, &self.context, &mut annotation, '~');
 
                annotation.push('\n');
 

	
 
                f.write_str(&annotation)?;
 
            },
 
            ContextKind::MultiLine => {
 
                // Annotate all offending lines
 
                // - first line
 
                let mut lines = self.context.lines();
 
                let first_line = lines.next().unwrap();
 
                transform_context(first_line, &mut context);
 
                writeln!(f, " |- {}", &context)?;
 

	
 
                // - remaining lines
 
                let mut last_line = first_line;
 
                while let Some(cur_line) = lines.next() {
 
                    context.clear();
 
                    transform_context(cur_line, &mut context);
 
                    writeln!(f, " |  {}", &context)?;
 
                    last_line = cur_line;
 
                }
 

	
 
                // - underline beneath last line
 
                annotation.push_str(" \\__");
 
                extend_annotation(1, self.end_column, &last_line, &mut annotation, '_');
 
                annotation.push_str("/\n");
 
                f.write_str(&annotation)?;
 
            }
 
        }
 

	
 
        Ok(())
 
    }
 
}
 

	
 
#[derive(Debug)]
 
pub struct ParseError {
 
    pub(crate) statements: Vec<ParseErrorStatement>
 
}
 

	
 
impl fmt::Display for ParseError {
 
    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
 
        if self.statements.is_empty() {
 
            return Ok(())
 
        }
 

	
 
        self.statements[0].fmt(f)?;
 
        for statement in self.statements.iter().skip(1) {
 
            writeln!(f)?;
 
            statement.fmt(f)?;
 
        }
 

	
 
        Ok(())
 
    }
 
}
 

	
 
impl ParseError {
 
    pub fn new_error_at_pos(source: &InputSource, position: InputPosition, message: String) -> Self {
 
        Self{ statements: vec!(ParseErrorStatement::from_source_at_pos(
 
            StatementKind::Error, source, position, message
 
        )) }
 
    }
 

	
 
    pub fn new_error_str_at_pos(source: &InputSource, position: InputPosition, message: &str) -> Self {
 
        Self{ statements: vec!(ParseErrorStatement::from_source_at_pos(
 
            StatementKind::Error, source, position, message.to_string()
 
        )) }
 
    }
 

	
 
    pub fn new_error_at_span(source: &InputSource, span: InputSpan, message: String) -> Self {
 
        Self{ statements: vec!(ParseErrorStatement::from_source_at_span(
 
            StatementKind::Error, source, span, message
 
        )) }
 
    }
 

	
 
    pub fn new_error_str_at_span(source: &InputSource, span: InputSpan, message: &str) -> Self {
 
        Self{ statements: vec!(ParseErrorStatement::from_source_at_span(
 
            StatementKind::Error, source, span, message.to_string()
 
        )) }
 
    }
 

	
 
    pub fn with_at_pos(mut self, error_type: StatementKind, source: &InputSource, position: InputPosition, message: String) -> Self {
 
        self.statements.push(ParseErrorStatement::from_source_at_pos(error_type, source, position, message));
 
        self
 
    }
 

	
 
    pub fn with_at_span(mut self, error_type: StatementKind, source: &InputSource, span: InputSpan, message: String) -> Self {
 
        self.statements.push(ParseErrorStatement::from_source_at_span(error_type, source, span, message.to_string()));
 
        self
 
    }
 

	
 
    pub fn with_info_at_pos(self, source: &InputSource, position: InputPosition, msg: String) -> Self {
 
        self.with_at_pos(StatementKind::Info, source, position, msg)
 
    }
 

	
 
    pub fn with_info_str_at_pos(self, source: &InputSource, position: InputPosition, msg: &str) -> Self {
 
        self.with_at_pos(StatementKind::Info, source, position, msg.to_string())
 
    }
 

	
 
    pub fn with_info_at_span(self, source: &InputSource, span: InputSpan, msg: String) -> Self {
 
        self.with_at_span(StatementKind::Info, source, span, msg)
 
    }
 

	
 
    pub fn with_info_str_at_span(self, source: &InputSource, span: InputSpan, msg: &str) -> Self {
 
        self.with_at_span(StatementKind::Info, source, span, msg.to_string())
 
    }
 
}
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: 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: 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 => {}
 
            }
 

	
 
                TokenRangeKind::Pragma | TokenRangeKind::Import => {
 
                    // Already fully parsed, fall through and go to next range
 
                },
 
                TokenRangeKind::Definition | TokenRangeKind::Code => {
 
                    // Visit range even if it is a "code" range to provide
 
                    // proper error messages.
 
                    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 types_section, "an embedded type", Some(&mut close_pos)
 
                )?;
 
                let value = if has_embedded {
 
                    UnionVariantValue::Embedded(types_section.into_vec())
 
                } else {
 
                    types_section.forget();
 
                    UnionVariantValue::None
 
                };
 

	
 
                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)
 
@@ -1101,769 +1105,828 @@ impl PassDefinitions {
 
            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)
 
                                    &mut struct_fields, "a struct field", "a list of struct fields", 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))?;
 
                                let mut end_pos = variant.span.end;
 
                                let values = if Some(TokenKind::OpenParen) == iter.next() {
 
                                    self.consume_expression_list(module, iter, ctx, Some(&mut end_pos))?
 
                                } else {
 
                                    Vec::new()
 
                                };
 

	
 
                                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 {
 
                    iter.consume();
 

	
 
                    // 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.
 
                    // Not a builtin literal, but also not a known type. So we
 
                    // assume it is a variable expression. Although if we do,
 
                    // then if a programmer mistyped a struct/function name the
 
                    // error messages will be rather cryptic. For polymorphic
 
                    // arguments we can't really do anything at all (because it
 
                    // uses the '<' token). In the other cases we try to provide
 
                    // a better error message.
 
                    iter.consume();
 
                    if Some(TokenKind::ColonColon) == iter.next() {
 
                    let next = iter.next();
 
                    if Some(TokenKind::ColonColon) == next {
 
                        return Err(ParseError::new_error_str_at_span(&module.source, ident_span, "unknown identifier"));
 
                    } else if Some(TokenKind::OpenParen) == next {
 
                        return Err(ParseError::new_error_str_at_span(
 
                            &module.source, ident_span,
 
                            "unknown identifier, did you mistype a union variant's or a function's name?"
 
                        ));
 
                    } else if Some(TokenKind::OpenCurly) == next {
 
                        return Err(ParseError::new_error_str_at_span(
 
                            &module.source, ident_span,
 
                            "unknown identifier, did you mistype a struct type's name?"
 
                        ))
 
                    }
 

	
 
                    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
 
// TODO: @Optimize, @Span fix, @Cleanup
 
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,
 
    }
 

	
 
    // After parsing the array modified "[]", we need to insert an array type
 
    // before the most recently parsed type.
 
    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.
 
    // annotations. This is both the hot-path, and simplifies the state machine
 
    // that follows and is responsible for parsing more complicated types.
 
    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 num_embedded = element.variant.num_embedded();
 
        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);
 
        let mut elements = Vec::with_capacity(num_array + num_embedded + 1);
 
        for _ in 0..num_array {
 
            elements.push(ParserTypeElement{ full_span: array_span, variant: ParserTypeVariant::Array });
 
        }
 
        elements.push(element);
 

	
 
        if num_embedded != 0 {
 
            if !allow_inference {
 
                return Err(ParseError::new_error_str_at_span(source, array_span, "type inference is not allowed here"));
 
            }
 

	
 
            for _ in 0..num_embedded {
 
                elements.push(ParserTypeElement { full_span: array_span, variant: ParserTypeVariant::Inferred });
 
            }
 
        }
 

	
 
        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"
 
                };
 
                // Mismatch in number of embedded types, produce a neat error
 
                // message.
 
                let type_name = String::from_utf8_lossy(source.section_at_span(cur_element.element.full_span));
 
                fn polymorphic_name_text(num: usize) -> &'static str {
 
                    if num == 1 { "polymorphic argument" } else { "polymorphic arguments" }
 
                }
 
                fn were_or_was(num: usize) -> &'static str {
 
                    if num == 1 { "was" } else { "were" }
 
                }
 

	
 
                if expected_subtypes == 0 {
 
                    return Err(ParseError::new_error_at_span(
 
                        source, cur_element.element.full_span,
 
                        format!(
 
                            "the type '{}' is not polymorphic, yet {} {} {} provided",
 
                            type_name, encountered_subtypes, polymorphic_name_text(encountered_subtypes),
 
                            were_or_was(encountered_subtypes)
 
                        )
 
                    ));
 
                }
 

	
 
                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
 
                        "expected {} {}{} for the type '{}', but {} {} provided",
 
                        expected_subtypes, polymorphic_name_text(expected_subtypes),
 
                        maybe_infer_text, type_name, encountered_subtypes,
 
                        were_or_was(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"));
 
                                return Err(ParseError::new_error_str_at_span(source, type_span, "expected a type but got a 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,
 
                                // If the type is imported in the module then notify the programmer
 
                                // that imports do not leak outside of a module
 
                                let type_name = String::from_utf8_lossy(type_text);
 
                                let module_name = String::from_utf8_lossy(old_text);
 
                                let suffix = if symbols.get_symbol_by_name(scope, type_text).is_some() {
 
                                    format!(
 
                                        "unknown type '{}' in module '{}'",
 
                                        String::from_utf8_lossy(type_text),
 
                                        String::from_utf8_lossy(old_text)
 
                                        ". The module '{}' does import '{}', but these imports are not visible to other modules",
 
                                        &module_name, &type_name
 
                                    )
 
                                } else {
 
                                    String::new()
 
                                };
 

	
 
                                return Err(ParseError::new_error_at_span(
 
                                    source, next_span,
 
                                    format!("unknown type '{}' in module '{}'{}", type_name, module_name, suffix)
 
                                ));
 
                            }
 

	
 
                            last_symbol = new_symbol.unwrap();
 
                        },
 
                        SymbolVariant::Definition(symbol_definition) => {
 
                            let num_poly_vars = heap[symbol_definition.definition_id].poly_vars().len();
 
                            type_kind = Some(PTV::Definition(symbol_definition.definition_id, num_poly_vars));
 
                            break;
 
                        }
 
                    }
 
                }
 
            }
 

	
 
            debug_assert!(type_kind.is_some());
 
            type_kind.unwrap()
 
        },
 
    };
 

	
 
    Ok(ParserTypeElement{ full_span: type_span, variant })
 
}
 

	
 
/// Consumes polymorphic variables and throws them on the floor.
 
fn consume_polymorphic_vars_spilled(source: &InputSource, iter: &mut TokenIter, _ctx: &mut PassCtx) -> Result<(), ParseError> {
 
    maybe_consume_comma_separated_spilled(
 
        TokenKind::OpenAngle, TokenKind::CloseAngle, source, iter, _ctx,
 
        |source, iter, _ctx| {
 
            consume_ident(source, iter)?;
 
            Ok(())
 
        }, "a polymorphic variable"
 
    )?;
 
    Ok(())
 
}
 

	
 
/// Consumes the parameter list to functions/components
 
fn consume_parameter_list(
 
    source: &InputSource, iter: &mut TokenIter, ctx: &mut PassCtx,
 
    target: &mut ScopedSection<ParameterId>, scope: SymbolScope, definition_id: DefinitionId
 
) -> Result<(), ParseError> {
 
    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...
 
            let (start_pos, _) = iter.next_positions();
 
            let parser_type = consume_parser_type(
 
                source, iter, &ctx.symbols, &ctx.heap, poly_vars, scope,
 
                definition_id, false, 0
 
            )?;
 
            let identifier = consume_ident_interned(source, iter, ctx)?;
 
            let parameter_id = ctx.heap.alloc_parameter(|this| Parameter{
 
                this,
 
                span: InputSpan::from_positions(start_pos, identifier.span.end),
 
                parser_type,
 
                identifier
 
            });
 
            Ok(parameter_id)
 
        },
 
        target, "a parameter", "a parameter list", None
 
    )
 
}
 
\ No newline at end of file
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
 
            }));
 

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

	
 
        // 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;
 
@@ -455,425 +455,426 @@ impl PassTokenizer {
 
                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
 
        code_start_idx: u32, code_end_idx: u32, next_sibling_idx: i32
 
    ) {
 
        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");
 
        debug_assert_ne!(parent_range.end, code_end_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
 
            next_sibling_idx,
 
        });
 

	
 
        // 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];
 

	
 
        if parent_range.first_child_idx == NO_RELATION {
 
            parent_range.first_child_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);
 
            self.add_code_range(target, parent_idx, last_registered_idx, first_token_idx, new_range_idx + 1);
 
        }
 

	
 
        // 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 {
 
    // Note: hex range includes the possible binary indicator 'b' and 'B';
 
    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'o' || c == b'O' || c == b'x' || c == b'X') ||
 
            (c >= b'0' && c <= b'9') || (c >= b'A' && c <= b'F') || (c >= b'a' && c <= b'f') ||
 
            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
src/protocol/parser/pass_validation_linking.rs
Show inline comments
 
@@ -405,385 +405,385 @@ impl Visitor2 for PassValidationLinking {
 

	
 
    fn visit_unary_expr(&mut self, ctx: &mut Ctx, id: UnaryExpressionId) -> VisitorResult {
 
        let unary_expr = &mut ctx.heap[id];
 
        let expr_id = unary_expr.expression;
 

	
 
        let old_expr_parent = self.expr_parent;
 
        unary_expr.parent = old_expr_parent;
 

	
 
        self.expr_parent = ExpressionParent::Expression(id.upcast(), 0);
 
        self.visit_expr(ctx, expr_id)?;
 
        self.expr_parent = old_expr_parent;
 

	
 
        Ok(())
 
    }
 

	
 
    fn visit_indexing_expr(&mut self, ctx: &mut Ctx, id: IndexingExpressionId) -> VisitorResult {
 
        let upcast_id = id.upcast();
 
        let indexing_expr = &mut ctx.heap[id];
 

	
 
        let subject_expr_id = indexing_expr.subject;
 
        let index_expr_id = indexing_expr.index;
 

	
 
        let old_expr_parent = self.expr_parent;
 
        indexing_expr.parent = old_expr_parent;
 

	
 
        self.expr_parent = ExpressionParent::Expression(upcast_id, 0);
 
        self.visit_expr(ctx, subject_expr_id)?;
 
        self.expr_parent = ExpressionParent::Expression(upcast_id, 1);
 
        self.visit_expr(ctx, index_expr_id)?;
 
        self.expr_parent = old_expr_parent;
 

	
 
        Ok(())
 
    }
 

	
 
    fn visit_slicing_expr(&mut self, ctx: &mut Ctx, id: SlicingExpressionId) -> VisitorResult {
 
        let upcast_id = id.upcast();
 
        let slicing_expr = &mut ctx.heap[id];
 

	
 
        let subject_expr_id = slicing_expr.subject;
 
        let from_expr_id = slicing_expr.from_index;
 
        let to_expr_id = slicing_expr.to_index;
 

	
 
        let old_expr_parent = self.expr_parent;
 
        slicing_expr.parent = old_expr_parent;
 

	
 
        self.expr_parent = ExpressionParent::Expression(upcast_id, 0);
 
        self.visit_expr(ctx, subject_expr_id)?;
 
        self.expr_parent = ExpressionParent::Expression(upcast_id, 1);
 
        self.visit_expr(ctx, from_expr_id)?;
 
        self.expr_parent = ExpressionParent::Expression(upcast_id, 2);
 
        self.visit_expr(ctx, to_expr_id)?;
 
        self.expr_parent = old_expr_parent;
 

	
 
        Ok(())
 
    }
 

	
 
    fn visit_select_expr(&mut self, ctx: &mut Ctx, id: SelectExpressionId) -> VisitorResult {
 
        let select_expr = &mut ctx.heap[id];
 
        let expr_id = select_expr.subject;
 

	
 
        let old_expr_parent = self.expr_parent;
 
        select_expr.parent = old_expr_parent;
 

	
 
        self.expr_parent = ExpressionParent::Expression(id.upcast(), 0);
 
        self.visit_expr(ctx, expr_id)?;
 
        self.expr_parent = old_expr_parent;
 

	
 
        Ok(())
 
    }
 

	
 
    fn visit_literal_expr(&mut self, ctx: &mut Ctx, id: LiteralExpressionId) -> VisitorResult {
 
        let literal_expr = &mut ctx.heap[id];
 
        let old_expr_parent = self.expr_parent;
 
        literal_expr.parent = old_expr_parent;
 

	
 
        match &mut literal_expr.value {
 
            Literal::Null | Literal::True | Literal::False |
 
            Literal::Character(_) | Literal::String(_) | Literal::Integer(_) => {
 
                // Just the parent has to be set, done above
 
            },
 
            Literal::Struct(literal) => {
 
                let upcast_id = id.upcast();
 
                // Retrieve type definition
 
                let type_definition = ctx.types.get_base_definition(&literal.definition).unwrap();
 
                let struct_definition = type_definition.definition.as_struct();
 

	
 
                // Make sure all fields are specified, none are specified twice
 
                // and all fields exist on the struct definition
 
                let mut specified = Vec::new(); // TODO: @performance
 
                specified.resize(struct_definition.fields.len(), false);
 

	
 
                for field in &mut literal.fields {
 
                    // Find field in the struct definition
 
                    let field_idx = struct_definition.fields.iter().position(|v| v.identifier == field.identifier);
 
                    if field_idx.is_none() {
 
                        let field_span = field.identifier.span;
 
                        let literal = ctx.heap[id].value.as_struct();
 
                        let ast_definition = &ctx.heap[literal.definition];
 
                        return Err(ParseError::new_error_at_span(
 
                            &ctx.module.source, field_span, format!(
 
                                "This field does not exist on the struct '{}'",
 
                                ast_definition.identifier().value.as_str()
 
                            )
 
                        ));
 
                    }
 
                    field.field_idx = field_idx.unwrap();
 

	
 
                    // Check if specified more than once
 
                    if specified[field.field_idx] {
 
                        return Err(ParseError::new_error_str_at_span(
 
                            &ctx.module.source, field.identifier.span,
 
                            "This field is specified more than once"
 
                        ));
 
                    }
 

	
 
                    specified[field.field_idx] = true;
 
                }
 

	
 
                if !specified.iter().all(|v| *v) {
 
                    // Some fields were not specified
 
                    let mut not_specified = String::new();
 
                    let mut num_not_specified = 0;
 
                    for (def_field_idx, is_specified) in specified.iter().enumerate() {
 
                        if !is_specified {
 
                            if !not_specified.is_empty() { not_specified.push_str(", ") }
 
                            let field_ident = &struct_definition.fields[def_field_idx].identifier;
 
                            not_specified.push_str(field_ident.value.as_str());
 
                            num_not_specified += 1;
 
                        }
 
                    }
 

	
 
                    debug_assert!(num_not_specified > 0);
 
                    let msg = if num_not_specified == 1 {
 
                        format!("not all fields are specified, '{}' is missing", not_specified)
 
                    } else {
 
                        format!("not all fields are specified, [{}] are missing", not_specified)
 
                    };
 
                    return Err(ParseError::new_error_at_span(
 
                        &ctx.module.source, literal.parser_type.elements[0].full_span, msg
 
                    ));
 
                }
 

	
 
                // Need to traverse fields expressions in struct and evaluate
 
                // the poly args
 
                let mut expr_section = self.expression_buffer.start_section();
 
                for field in &literal.fields {
 
                    expr_section.push(field.value);
 
                }
 

	
 
                for expr_idx in 0..expr_section.len() {
 
                    let expr_id = expr_section[expr_idx];
 
                    self.expr_parent = ExpressionParent::Expression(upcast_id, expr_idx as u32);
 
                    self.visit_expr(ctx, expr_id)?;
 
                }
 

	
 
                expr_section.forget();
 
            },
 
            Literal::Enum(literal) => {
 
                // Make sure the variant exists
 
                let type_definition = ctx.types.get_base_definition(&literal.definition).unwrap();
 
                let enum_definition = type_definition.definition.as_enum();
 

	
 
                let variant_idx = enum_definition.variants.iter().position(|v| {
 
                    v.identifier == literal.variant
 
                });
 

	
 
                if variant_idx.is_none() {
 
                    let literal = ctx.heap[id].value.as_enum();
 
                    let ast_definition = ctx.heap[literal.definition].as_enum();
 
                    return Err(ParseError::new_error_at_span(
 
                        &ctx.module.source, literal.parser_type.elements[0].full_span, format!(
 
                            "the variant '{}' does not exist on the enum '{}'",
 
                            literal.variant.value.as_str(), ast_definition.identifier.value.as_str()
 
                        )
 
                    ));
 
                }
 

	
 
                literal.variant_idx = variant_idx.unwrap();
 
            },
 
            Literal::Union(literal) => {
 
                // Make sure the variant exists
 
                let type_definition = ctx.types.get_base_definition(&literal.definition).unwrap();
 
                let union_definition = type_definition.definition.as_union();
 

	
 
                let variant_idx = union_definition.variants.iter().position(|v| {
 
                    v.identifier == literal.variant
 
                });
 
                if variant_idx.is_none() {
 
                    let literal = ctx.heap[id].value.as_union();
 
                    let ast_definition = ctx.heap[literal.definition].as_union();
 
                    return Err(ParseError::new_error_at_span(
 
                        &ctx.module.source, literal.parser_type.elements[0].full_span, format!(
 
                            "the variant does '{}' does not exist on the union '{}'",
 
                            "the variant '{}' does not exist on the union '{}'",
 
                            literal.variant.value.as_str(), ast_definition.identifier.value.as_str()
 
                        )
 
                    ));
 
                }
 

	
 
                literal.variant_idx = variant_idx.unwrap();
 

	
 
                // Make sure the number of specified values matches the expected
 
                // number of embedded values in the union variant.
 
                let union_variant = &union_definition.variants[literal.variant_idx];
 
                if union_variant.embedded.len() != literal.values.len() {
 
                    let literal = ctx.heap[id].value.as_union();
 
                    let ast_definition = ctx.heap[literal.definition].as_union();
 
                    return Err(ParseError::new_error_at_span(
 
                        &ctx.module.source, literal.parser_type.elements[0].full_span, format!(
 
                            "The variant '{}' of union '{}' expects {} embedded values, but {} were specified",
 
                            literal.variant.value.as_str(), ast_definition.identifier.value.as_str(),
 
                            union_variant.embedded.len(), literal.values.len()
 
                        ),
 
                    ))
 
                }
 

	
 
                // Traverse embedded values of union (if any) and evaluate the
 
                // polymorphic arguments
 
                let upcast_id = id.upcast();
 
                let mut expr_section = self.expression_buffer.start_section();
 
                for value in &literal.values {
 
                    expr_section.push(*value);
 
                }
 

	
 
                for expr_idx in 0..expr_section.len() {
 
                    let expr_id = expr_section[expr_idx];
 
                    self.expr_parent = ExpressionParent::Expression(upcast_id, expr_idx as u32);
 
                    self.visit_expr(ctx, expr_id)?;
 
                }
 

	
 
                expr_section.forget();
 
            },
 
            Literal::Array(literal) => {
 
                // Visit all expressions in the array
 
                let upcast_id = id.upcast();
 
                let expr_section = self.expression_buffer.start_section_initialized(literal);
 
                for expr_idx in 0..expr_section.len() {
 
                    let expr_id = expr_section[expr_idx];
 
                    self.expr_parent = ExpressionParent::Expression(upcast_id, expr_idx as u32);
 
                    self.visit_expr(ctx, expr_id)?;
 
                }
 

	
 
                expr_section.forget();
 
            }
 
        }
 

	
 
        self.expr_parent = old_expr_parent;
 

	
 
        Ok(())
 
    }
 

	
 
    fn visit_call_expr(&mut self, ctx: &mut Ctx, id: CallExpressionId) -> VisitorResult {
 
        let call_expr = &mut ctx.heap[id];
 

	
 
        // Check whether the method is allowed to be called within the code's
 
        // context (in sync, definition type, etc.)
 
        let mut expected_wrapping_new_stmt = false;
 
        match &mut call_expr.method {
 
            Method::Get => {
 
                if !self.def_type.is_primitive() {
 
                    return Err(ParseError::new_error_str_at_span(
 
                        &ctx.module.source, call_expr.span,
 
                        "a call to 'get' may only occur in primitive component definitions"
 
                    ));
 
                }
 
                if self.in_sync.is_none() {
 
                    return Err(ParseError::new_error_str_at_span(
 
                        &ctx.module.source, call_expr.span,
 
                        "a call to 'get' may only occur inside synchronous blocks"
 
                    ));
 
                }
 
            },
 
            Method::Put => {
 
                if !self.def_type.is_primitive() {
 
                    return Err(ParseError::new_error_str_at_span(
 
                        &ctx.module.source, call_expr.span,
 
                        "a call to 'put' may only occur in primitive component definitions"
 
                    ));
 
                }
 
                if self.in_sync.is_none() {
 
                    return Err(ParseError::new_error_str_at_span(
 
                        &ctx.module.source, call_expr.span,
 
                        "a call to 'put' may only occur inside synchronous blocks"
 
                    ));
 
                }
 
            },
 
            Method::Fires => {
 
                if !self.def_type.is_primitive() {
 
                    return Err(ParseError::new_error_str_at_span(
 
                        &ctx.module.source, call_expr.span,
 
                        "a call to 'fires' may only occur in primitive component definitions"
 
                    ));
 
                }
 
                if self.in_sync.is_none() {
 
                    return Err(ParseError::new_error_str_at_span(
 
                        &ctx.module.source, call_expr.span,
 
                        "a call to 'fires' may only occur inside synchronous blocks"
 
                    ));
 
                }
 
            },
 
            Method::Create => {},
 
            Method::Length => {},
 
            Method::Assert => {
 
                if self.def_type.is_function() {
 
                    return Err(ParseError::new_error_str_at_span(
 
                        &ctx.module.source, call_expr.span,
 
                        "assert statement may only occur in components"
 
                    ));
 
                }
 
                if self.in_sync.is_none() {
 
                    return Err(ParseError::new_error_str_at_span(
 
                        &ctx.module.source, call_expr.span,
 
                        "assert statements may only occur inside synchronous blocks"
 
                    ));
 
                }
 
            },
 
            Method::UserFunction => {},
 
            Method::UserComponent => {
 
                expected_wrapping_new_stmt = true;
 
            },
 
        }
 

	
 
        if expected_wrapping_new_stmt {
 
            if !self.expr_parent.is_new() {
 
                return Err(ParseError::new_error_str_at_span(
 
                    &ctx.module.source, call_expr.span,
 
                    "cannot call a component, it can only be instantiated by using 'new'"
 
                ));
 
            }
 
        } else {
 
            if self.expr_parent.is_new() {
 
                return Err(ParseError::new_error_str_at_span(
 
                    &ctx.module.source, call_expr.span,
 
                    "only components can be instantiated, this is a function"
 
                ));
 
            }
 
        }
 

	
 
        // Check the number of arguments
 
        let call_definition = ctx.types.get_base_definition(&call_expr.definition).unwrap();
 
        let num_expected_args = match &call_definition.definition {
 
            DefinedTypeVariant::Function(definition) => definition.arguments.len(),
 
            DefinedTypeVariant::Component(definition) => definition.arguments.len(),
 
            v => unreachable!("encountered {} type in call expression", v.type_class()),
 
        };
 

	
 
        let num_provided_args = call_expr.arguments.len();
 
        if num_provided_args != num_expected_args {
 
            let argument_text = if num_expected_args == 1 { "argument" } else { "arguments" };
 
            return Err(ParseError::new_error_at_span(
 
                &ctx.module.source, call_expr.span, format!(
 
                    "expected {} {}, but {} were provided",
 
                    num_expected_args, argument_text, num_provided_args
 
                )
 
            ));
 
        }
 

	
 
        // Recurse into all of the arguments and set the expression's parent
 
        let upcast_id = id.upcast();
 

	
 
        let section = self.expression_buffer.start_section_initialized(&call_expr.arguments);
 
        let old_expr_parent = self.expr_parent;
 
        call_expr.parent = old_expr_parent;
 

	
 
        for arg_expr_idx in 0..section.len() {
 
            let arg_expr_id = section[arg_expr_idx];
 
            self.expr_parent = ExpressionParent::Expression(upcast_id, arg_expr_idx as u32);
 
            self.visit_expr(ctx, arg_expr_id)?;
 
        }
 

	
 
        section.forget();
 
        self.expr_parent = old_expr_parent;
 

	
 
        Ok(())
 
    }
 

	
 
    fn visit_variable_expr(&mut self, ctx: &mut Ctx, id: VariableExpressionId) -> VisitorResult {
 
        let var_expr = &ctx.heap[id];
 
        let variable_id = self.find_variable(ctx, self.relative_pos_in_block, &var_expr.identifier)?;
 
        let var_expr = &mut ctx.heap[id];
 
        var_expr.declaration = Some(variable_id);
 
        var_expr.parent = self.expr_parent;
 

	
 
        Ok(())
 
    }
 
}
src/protocol/parser/symbol_table.rs
Show inline comments
 
@@ -2,313 +2,310 @@
 
///
 
/// The datastructure used to lookup symbols within particular scopes. Scopes
 
/// may be module-level or definition level, although imports and definitions
 
/// within definitions are currently not allowed.
 
///
 
/// TODO: Once the compiler has matured, find out ways to optimize to prevent
 
///     the repeated HashMap lookup.
 

	
 
use std::collections::HashMap;
 
use std::collections::hash_map::Entry;
 

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

	
 
const RESERVED_SYMBOLS: usize = 32;
 

	
 
#[derive(Debug, Clone, Copy, Hash, PartialEq, Eq)]
 
pub enum SymbolScope {
 
    Global,
 
    Module(RootId),
 
    Definition(DefinitionId),
 
}
 

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

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

	
 
impl DefinitionClass {
 
    fn as_symbol_class(&self) -> SymbolClass {
 
        match self {
 
            DefinitionClass::Struct => SymbolClass::Struct,
 
            DefinitionClass::Enum => SymbolClass::Enum,
 
            DefinitionClass::Union => SymbolClass::Union,
 
            DefinitionClass::Function => SymbolClass::Function,
 
            DefinitionClass::Component => SymbolClass::Component,
 
        }
 
    }
 
}
 

	
 
struct ScopedSymbols {
 
    scope: SymbolScope,
 
    parent_scope: Option<SymbolScope>,
 
    child_scopes: Vec<SymbolScope>,
 
    symbols: Vec<Symbol>,
 
}
 

	
 
impl ScopedSymbols {
 
    fn get_symbol<'a>(&'a self, name: &StringRef) -> Option<&'a Symbol> {
 
        for symbol in self.symbols.iter() {
 
            if symbol.name == *name {
 
                return Some(symbol);
 
            }
 
        }
 

	
 
        None
 
    }
 
}
 

	
 
#[derive(Debug, Clone)]
 
pub struct SymbolModule {
 
    pub root_id: RootId,
 
    pub introduced_at: ImportId,
 
}
 

	
 
#[derive(Debug, Clone)]
 
pub struct SymbolDefinition {
 
    // Definition location (not necessarily the place where the symbol
 
    // is introduced, as it may be imported). Builtin symbols will have invalid
 
    // spans and module IDs
 
    pub defined_in_module: RootId,
 
    pub defined_in_scope: SymbolScope,
 
    pub definition_span: InputSpan, // full span of definition
 
    pub identifier_span: InputSpan, // span of just the identifier
 
    // Location where the symbol is introduced in its scope
 
    pub imported_at: Option<ImportId>,
 
    // Definition in the heap, with a utility enum to determine its
 
    // class if the ID is not needed.
 
    pub class: DefinitionClass,
 
    pub definition_id: DefinitionId,
 
}
 

	
 
impl SymbolDefinition {
 
    /// Clones the entire data structure, but replaces the `imported_at` field
 
    /// with the supplied `ImportId`.
 
    pub(crate) fn into_imported(mut self, imported_at: ImportId) -> Self {
 
        self.imported_at = Some(imported_at);
 
        self
 
    }
 
}
 

	
 
#[derive(Debug, Clone)]
 
pub enum SymbolVariant {
 
    Module(SymbolModule),
 
    Definition(SymbolDefinition),
 
}
 

	
 
impl SymbolVariant {
 
    /// Returns the span at which the item was introduced. For an imported
 
    /// item (all modules, and imported types) this returns the span of the
 
    /// import. For a defined type this returns the span of the identifier
 
    pub(crate) fn span_of_introduction(&self, heap: &Heap) -> InputSpan {
 
        match self {
 
            SymbolVariant::Module(v) => heap[v.introduced_at].span(),
 
            SymbolVariant::Definition(v) => if let Some(import_id) = v.imported_at {
 
                heap[import_id].span()
 
            } else {
 
                v.identifier_span
 
            },
 
        }
 
    }
 

	
 
    pub(crate) fn as_definition(&self) -> &SymbolDefinition {
 
        match self {
 
            SymbolVariant::Module(_) => unreachable!("called 'as_definition' on {:?}", self),
 
            SymbolVariant::Definition(v) => v,
 
        }
 
    }
 
}
 

	
 
/// TODO: @Cleanup - remove clone everywhere
 
#[derive(Debug, Clone)]
 
pub struct Symbol {
 
    pub name: StringRef<'static>,
 
    pub variant: SymbolVariant,
 
}
 

	
 
impl Symbol {
 
    pub(crate) fn class(&self) -> SymbolClass {
 
        match &self.variant {
 
            SymbolVariant::Module(_) => SymbolClass::Module,
 
            SymbolVariant::Definition(data) => data.class.as_symbol_class(),
 
        }
 
    }
 
}
 

	
 
pub struct SymbolTable {
 
    module_lookup: HashMap<StringRef<'static>, RootId>,
 
    scope_lookup: HashMap<SymbolScope, ScopedSymbols>,
 
}
 

	
 
impl SymbolTable {
 
    pub(crate) fn new() -> Self {
 
        Self{
 
            module_lookup: HashMap::new(),
 
            scope_lookup: HashMap::new(),
 
        }
 
    }
 
    /// Inserts a new module by its name. Upon module naming conflict the
 
    /// previously associated `RootId` will be returned.
 
    pub(crate) fn insert_module(&mut self, module_name: StringRef<'static>, root_id: RootId) -> Result<(), RootId> {
 
        match self.module_lookup.entry(module_name) {
 
            Entry::Occupied(v) => {
 
                Err(*v.get())
 
            },
 
            Entry::Vacant(v) => {
 
                v.insert(root_id);
 
                Ok(())
 
            }
 
        }
 
    }
 

	
 
    /// Retrieves module `RootId` by name
 
    pub(crate) fn get_module_by_name(&mut self, name: &[u8]) -> Option<RootId> {
 
        let string_ref = StringRef::new(name);
 
        self.module_lookup.get(&string_ref).map(|v| *v)
 
    }
 

	
 
    /// Inserts a new symbol scope. The parent must have been added to the
 
    /// symbol table before.
 
    pub(crate) fn insert_scope(&mut self, parent_scope: Option<SymbolScope>, new_scope: SymbolScope) {
 
        debug_assert!(
 
            parent_scope.is_none() || self.scope_lookup.contains_key(parent_scope.as_ref().unwrap()),
 
            "inserting scope {:?} but parent {:?} does not exist", new_scope, parent_scope
 
        );
 
        debug_assert!(!self.scope_lookup.contains_key(&new_scope), "inserting scope {:?}, but it already exists", new_scope);
 

	
 
        println!("DEBUG: Inserting scope {:?} with parent {:?}", new_scope, parent_scope);
 

	
 
        if let Some(parent_scope) = parent_scope {
 
            let parent = self.scope_lookup.get_mut(&parent_scope).unwrap();
 
            parent.child_scopes.push(new_scope);
 
        }
 

	
 
        let scope = ScopedSymbols {
 
            scope: new_scope,
 
            parent_scope,
 
            child_scopes: Vec::with_capacity(RESERVED_SYMBOLS),
 
            symbols: Vec::with_capacity(RESERVED_SYMBOLS)
 
        };
 
        self.scope_lookup.insert(new_scope, scope);
 
    }
 

	
 
    /// Inserts a symbol into a particular scope. The symbol's name may not
 
    /// exist in the scope or any of its parents. If it does collide then the
 
    /// symbol will be returned, together with the symbol that has the same
 
    /// name.
 
    // Note: we do not return a reference because Rust doesn't like it.
 
    pub(crate) fn insert_symbol(&mut self, in_scope: SymbolScope, symbol: Symbol) -> Result<(), (Symbol, Symbol)> {
 
        debug_assert!(self.scope_lookup.contains_key(&in_scope), "inserting symbol {}, but scope {:?} does not exist", symbol.name.as_str(), in_scope);
 
        println!("DEBUG: Inserting symbol {:?} in scope {:?}", symbol, in_scope);
 
        let mut seek_scope = in_scope;
 
        loop {
 
            let scoped_symbols = self.scope_lookup.get(&seek_scope).unwrap();
 
            for existing_symbol in scoped_symbols.symbols.iter() {
 
                if symbol.name == existing_symbol.name {
 
                    return Err((symbol, existing_symbol.clone()))
 
                }
 
            }
 

	
 
            match scoped_symbols.parent_scope {
 
                Some(parent_scope) => { seek_scope = parent_scope; },
 
                None => { break; }
 
            }
 
        }
 

	
 
        // If here, then there is no collision
 
        let scoped_symbols = self.scope_lookup.get_mut(&in_scope).unwrap();
 
        scoped_symbols.symbols.push(symbol);
 
        Ok(())
 
    }
 

	
 
    /// Retrieves a symbol by name by searching in a particular scope and that scope's parents. The
 
    /// returned symbol may both be imported as defined within any of the searched scopes.
 
    pub(crate) fn get_symbol_by_name(
 
        &self, mut in_scope: SymbolScope, name: &[u8]
 
    ) -> Option<&Symbol> {
 
        let string_ref = StringRef::new(name);
 
        loop {
 
            let scope = self.scope_lookup.get(&in_scope);
 
            if scope.is_none() {
 
                return None;
 
            }
 
            let scope = scope.unwrap();
 

	
 
            if let Some(symbol) = scope.get_symbol(&string_ref) {
 
                return Some(symbol);
 
            } else {
 
                // Could not find symbol in current scope, seek in the parent scope if it exists
 
                match &scope.parent_scope {
 
                    Some(parent_scope) => { in_scope = *parent_scope; },
 
                    None => return None,
 
                }
 
            }
 
        }
 
    }
 

	
 
    /// Retrieves a symbol by name by searching in a particular scope and that scope's parents. The
 
    /// returned symbol must be defined within any of the searched scopes and may not be imported.
 
    /// In case such an imported symbol exists then this function still returns `None`.
 
    pub(crate) fn get_symbol_by_name_defined_in_scope(
 
        &self, in_scope: SymbolScope, name: &[u8]
 
    ) -> Option<&Symbol> {
 
        match self.get_symbol_by_name(in_scope, name) {
 
            Some(symbol) => {
 
                match &symbol.variant {
 
                    SymbolVariant::Module(_) => {
 
                        None // in-scope modules are always imported
 
                    },
 
                    SymbolVariant::Definition(variant) => {
 
                        if variant.imported_at.is_some() || variant.defined_in_scope == SymbolScope::Global {
 
                            // Symbol is imported or lives in the global scope.
 
                            // Things in the global scope are defined by the
 
                            // compiler.
 
                            None
 
                        } else {
 
                            Some(symbol)
 
                        }
 
                    }
 
                }
 
            },
 
            None => None,
 
        }
 
    }
 

	
 
    /// Retrieves all symbols that are defined within a particular scope. Imported symbols are
 
    /// ignored. Returns `true` if the scope was found (which may contain 0 defined symbols) and
 
    /// `false` if the scope was not found.
 
    pub(crate) fn get_all_symbols_defined_in_scope(&self, in_scope: SymbolScope, target: &mut Vec<Symbol>) -> bool {
 
        match self.scope_lookup.get(&in_scope) {
 
            Some(scope) => {
 
                for symbol in &scope.symbols {
 
                    if let SymbolVariant::Definition(definition) = &symbol.variant {
 
                        if definition.imported_at.is_some() {
 
                            continue;
 
                        }
 

	
 
                        // Defined in scope, so push onto target
 
                        target.push(symbol.clone());
 
                    }
 
                }
 

	
 
                true
 
            },
 
            None => false,
 
        }
 
    }
 
}
 
\ No newline at end of file
src/protocol/parser/token_parsing.rs
Show inline comments
 
@@ -94,416 +94,418 @@ pub(crate) trait Extendable {
 
impl<T> Extendable for Vec<T> {
 
    type Value = T;
 

	
 
    #[inline]
 
    fn push(&mut self, v: Self::Value) {
 
        (self as &mut Vec<T>).push(v);
 
    }
 
}
 

	
 
impl<T: Sized> Extendable for ScopedSection<T> {
 
    type Value = T;
 

	
 
    #[inline]
 
    fn push(&mut self, v: Self::Value) {
 
        (self as &mut ScopedSection<T>).push(v);
 
    }
 
}
 

	
 
/// Consumes a domain-name identifier: identifiers separated by a dot. For
 
/// simplification of later parsing and span identification the domain-name may
 
/// contain whitespace, but must reside on the same line.
 
pub(crate) fn consume_domain_ident<'a>(
 
    source: &'a InputSource, iter: &mut TokenIter
 
) -> Result<(&'a [u8], InputSpan), ParseError> {
 
    let (_, mut span) = consume_ident(source, iter)?;
 
    while let Some(TokenKind::Dot) = iter.next() {
 
        iter.consume();
 
        let (_, new_span) = consume_ident(source, iter)?;
 
        span.end = new_span.end;
 
    }
 

	
 
    // Not strictly necessary, but probably a reasonable restriction: this
 
    // simplifies parsing of module naming and imports.
 
    if span.begin.line != span.end.line {
 
        return Err(ParseError::new_error_str_at_span(source, span, "module names may not span multiple lines"));
 
    }
 

	
 
    // If module name consists of a single identifier, then it may not match any
 
    // of the reserved keywords
 
    let section = source.section_at_pos(span.begin, span.end);
 
    if is_reserved_keyword(section) {
 
        return Err(ParseError::new_error_str_at_span(source, span, "encountered reserved keyword"));
 
    }
 

	
 
    Ok((source.section_at_pos(span.begin, span.end), span))
 
}
 

	
 
/// Consumes a specific expected token. Be careful to only call this with tokens
 
/// that do not have a variable length.
 
pub(crate) fn consume_token(source: &InputSource, iter: &mut TokenIter, expected: TokenKind) -> Result<InputSpan, ParseError> {
 
    if Some(expected) != iter.next() {
 
        return Err(ParseError::new_error_at_pos(
 
            source, iter.last_valid_pos(),
 
            format!("expected '{}'", expected.token_chars())
 
        ));
 
    }
 
    let span = iter.next_span();
 
    iter.consume();
 
    Ok(span)
 
}
 

	
 
/// Consumes a comma separated list until the closing delimiter is encountered
 
pub(crate) fn consume_comma_separated_until<T, F, E>(
 
    close_delim: TokenKind, source: &InputSource, iter: &mut TokenIter, ctx: &mut PassCtx,
 
    mut consumer_fn: F, target: &mut E, item_name_and_article: &'static str,
 
    close_pos: Option<&mut InputPosition>
 
) -> Result<(), ParseError>
 
    where F: FnMut(&InputSource, &mut TokenIter, &mut PassCtx) -> Result<T, ParseError>,
 
          E: Extendable<Value=T>
 
{
 
    let mut had_comma = true;
 
    let mut next;
 
    loop {
 
        next = iter.next();
 
        if Some(close_delim) == next {
 
            if let Some(close_pos) = close_pos {
 
                // If requested return the position of the closing delimiter
 
                let (_, new_close_pos) = iter.next_positions();
 
                *close_pos = new_close_pos;
 
            }
 
            iter.consume();
 
            break;
 
        } else if !had_comma || next.is_none() {
 
            return Err(ParseError::new_error_at_pos(
 
                source, iter.last_valid_pos(),
 
                format!("expected a '{}', or {}", close_delim.token_chars(), item_name_and_article)
 
            ));
 
        }
 

	
 
        let new_item = consumer_fn(source, iter, ctx)?;
 
        target.push(new_item);
 

	
 
        next = iter.next();
 
        had_comma = next == Some(TokenKind::Comma);
 
        if had_comma {
 
            iter.consume();
 
        }
 
    }
 

	
 
    Ok(())
 
}
 

	
 
/// Consumes a comma-separated list of items if the opening delimiting token is
 
/// encountered. If not, then the iterator will remain at its current position.
 
/// Note that the potential cases may be:
 
/// - No opening delimiter encountered, then we return `false`.
 
/// - Both opening and closing delimiter encountered, but no items.
 
/// - Opening and closing delimiter encountered, and items were processed.
 
/// - Found an opening delimiter, but processing an item failed.
 
pub(crate) fn maybe_consume_comma_separated<T, F, E>(
 
    open_delim: TokenKind, close_delim: TokenKind, source: &InputSource, iter: &mut TokenIter, ctx: &mut PassCtx,
 
    consumer_fn: F, target: &mut E, item_name_and_article: &'static str,
 
    close_pos: Option<&mut InputPosition>
 
) -> Result<bool, ParseError>
 
    where F: FnMut(&InputSource, &mut TokenIter, &mut PassCtx) -> Result<T, ParseError>,
 
          E: Extendable<Value=T>
 
{
 
    if Some(open_delim) != iter.next() {
 
        return Ok(false);
 
    }
 

	
 
    // Opening delimiter encountered, so must parse the comma-separated list.
 
    iter.consume();
 
    consume_comma_separated_until(close_delim, source, iter, ctx, consumer_fn, target, item_name_and_article, close_pos)?;
 

	
 
    Ok(true)
 
}
 

	
 
pub(crate) fn maybe_consume_comma_separated_spilled<F: FnMut(&InputSource, &mut TokenIter, &mut PassCtx) -> Result<(), ParseError>>(
 
    open_delim: TokenKind, close_delim: TokenKind, source: &InputSource,
 
    iter: &mut TokenIter, ctx: &mut PassCtx,
 
    mut consumer_fn: F, item_name_and_article: &'static str
 
) -> Result<bool, ParseError> {
 
    let mut next = iter.next();
 
    if Some(open_delim) != next {
 
        return Ok(false);
 
    }
 

	
 
    iter.consume();
 
    let mut had_comma = true;
 
    loop {
 
        next = iter.next();
 
        if Some(close_delim) == next {
 
            iter.consume();
 
            break;
 
        } else if !had_comma {
 
            return Err(ParseError::new_error_at_pos(
 
                source, iter.last_valid_pos(),
 
                format!("expected a '{}', or {}", close_delim.token_chars(), item_name_and_article)
 
            ));
 
        }
 

	
 
        consumer_fn(source, iter, ctx)?;
 
        next = iter.next();
 
        had_comma = next == Some(TokenKind::Comma);
 
        if had_comma {
 
            iter.consume();
 
        }
 
    }
 

	
 
    Ok(true)
 
}
 

	
 
/// Consumes a comma-separated list and expected the opening and closing
 
/// characters to be present. The returned array may still be empty
 
pub(crate) fn consume_comma_separated<T, F, E>(
 
    open_delim: TokenKind, close_delim: TokenKind, source: &InputSource,
 
    iter: &mut TokenIter, ctx: &mut PassCtx,
 
    consumer_fn: F, target: &mut E, item_name_and_article: &'static str,
 
    list_name_and_article: &'static str, close_pos: Option<&mut InputPosition>
 
) -> Result<(), ParseError>
 
    where F: FnMut(&InputSource, &mut TokenIter, &mut PassCtx) -> Result<T, ParseError>,
 
          E: Extendable<Value=T>
 
{
 
    let first_pos = iter.last_valid_pos();
 
    match maybe_consume_comma_separated(
 
        open_delim, close_delim, source, iter, ctx, consumer_fn, target,
 
        item_name_and_article, close_pos
 
    ) {
 
        Ok(true) => Ok(()),
 
        Ok(false) => {
 
            return Err(ParseError::new_error_at_pos(
 
                source, first_pos,
 
                format!("expected {}", list_name_and_article)
 
            ));
 
        },
 
        Err(err) => Err(err)
 
    }
 
}
 

	
 
/// Consumes an integer literal, may be binary, octal, hexadecimal or decimal,
 
/// and may have separating '_'-characters.
 
/// TODO: @Cleanup, @Performance
 
pub(crate) fn consume_integer_literal(source: &InputSource, iter: &mut TokenIter, buffer: &mut String) -> Result<(u64, InputSpan), ParseError> {
 
    if Some(TokenKind::Integer) != iter.next() {
 
        return Err(ParseError::new_error_str_at_pos(source, iter.last_valid_pos(), "expected an integer literal"));
 
    }
 
    let integer_span = iter.next_span();
 
    iter.consume();
 

	
 
    let integer_text = source.section_at_span(integer_span);
 

	
 
    // Determine radix and offset from prefix
 
    let (radix, input_offset, radix_name) =
 
        if integer_text.starts_with(b"0b") || integer_text.starts_with(b"0B") {
 
            // Binary number
 
            (2, 2, "binary")
 
        } else if integer_text.starts_with(b"0o") || integer_text.starts_with(b"0O") {
 
            // Octal number
 
            (8, 2, "octal")
 
        } else if integer_text.starts_with(b"0x") || integer_text.starts_with(b"0X") {
 
            // Hexadecimal number
 
            (16, 2, "hexadecimal")
 
        } else {
 
            (10, 0, "decimal")
 
        };
 

	
 
    // Take out any of the separating '_' characters
 
    buffer.clear();
 
    for char_idx in input_offset..integer_text.len() {
 
        let char = integer_text[char_idx];
 
        if char == b'_' {
 
            continue;
 
        }
 
        if !char.is_ascii_digit() {
 

	
 
        if !((char >= b'0' && char <= b'9') || (char >= b'A' && char <= b'F') || (char >= b'a' || char <= b'f')) {
 
            return Err(ParseError::new_error_at_span(
 
                source, integer_span,
 
                format!("incorrectly formatted {} number", radix_name)
 
            ));
 
        }
 
        buffer.push(char::from(char));
 
    }
 

	
 
    // Use the cleaned up string to convert to integer
 
    match u64::from_str_radix(&buffer, radix) {
 
        Ok(number) => Ok((number, integer_span)),
 
        Err(_) => Err(ParseError::new_error_at_span(
 
            source, integer_span,
 
            format!("incorrectly formatted {} number", radix_name)
 
        )),
 
    }
 
}
 

	
 
/// Consumes a character literal. We currently support a limited number of
 
/// backslash-escaped characters
 
pub(crate) fn consume_character_literal(
 
    source: &InputSource, iter: &mut TokenIter
 
) -> Result<(char, InputSpan), ParseError> {
 
    if Some(TokenKind::Character) != iter.next() {
 
        return Err(ParseError::new_error_str_at_pos(source, iter.last_valid_pos(), "expected a character literal"));
 
    }
 
    let span = iter.next_span();
 
    iter.consume();
 

	
 
    let char_text = source.section_at_span(span);
 
    if !char_text.is_ascii() {
 
        return Err(ParseError::new_error_str_at_span(
 
            source, span, "expected an ASCII character literal"
 
        ));
 
    }
 

	
 
    match char_text.len() {
 
        0 => return Err(ParseError::new_error_str_at_span(source, span, "too little characters in character literal")),
 
        1 => {
 
            // We already know the text is ascii, so just throw an error if we have the escape
 
            // character.
 
            if char_text[0] == b'\\' {
 
                return Err(ParseError::new_error_str_at_span(source, span, "escape character without subsequent character"));
 
            }
 
            return Ok((char_text[0] as char, span));
 
        },
 
        2 => {
 
            if char_text[0] == b'\\' {
 
                let result = parse_escaped_character(source, iter.last_valid_pos(), char_text[1])?;
 
                return Ok((result, span))
 
            }
 
        },
 
        _ => {}
 
    }
 

	
 
    return Err(ParseError::new_error_str_at_span(source, span, "too many characters in character literal"))
 
}
 

	
 
/// Consumes a string literal. We currently support a limited number of
 
/// backslash-escaped characters. Note that the result is stored in the
 
/// buffer.
 
pub(crate) fn consume_string_literal(
 
    source: &InputSource, iter: &mut TokenIter, buffer: &mut String
 
) -> Result<InputSpan, ParseError> {
 
    if Some(TokenKind::String) != iter.next() {
 
        return Err(ParseError::new_error_str_at_pos(source, iter.last_valid_pos(), "expected a string literal"));
 
    }
 

	
 
    buffer.clear();
 
    let span = iter.next_span();
 
    iter.consume();
 

	
 
    let text = source.section_at_span(span);
 
    if !text.is_ascii() {
 
        return Err(ParseError::new_error_str_at_span(source, span, "expected an ASCII string literal"));
 
    }
 
    buffer.reserve(text.len());
 

	
 
    let mut was_escape = false;
 
    for idx in 0..text.len() {
 
        let cur = text[idx];
 
        if cur != b'\\' {
 
            if was_escape {
 
                let to_push = parse_escaped_character(source, iter.last_valid_pos(), cur)?;
 
                buffer.push(to_push);
 
            } else {
 
                buffer.push(cur as char);
 
            }
 
            was_escape = false;
 
        } else {
 
            was_escape = true;
 
        }
 
    }
 

	
 
    debug_assert!(!was_escape); // because otherwise we couldn't have ended the string literal
 

	
 
    Ok(span)
 
}
 

	
 
fn parse_escaped_character(source: &InputSource, pos: InputPosition, v: u8) -> Result<char, ParseError> {
 
    let result = match v {
 
        b'r' => '\r',
 
        b'n' => '\n',
 
        b't' => '\t',
 
        b'0' => '\0',
 
        b'\\' => '\\',
 
        b'\'' => '\'',
 
        b'"' => '"',
 
        v => return Err(ParseError::new_error_at_pos(
 
            source, pos, format!("unexpected escaped character '{}'", v)
 
        )),
 
    };
 
    Ok(result)
 
}
 

	
 
pub(crate) fn consume_pragma<'a>(source: &'a InputSource, iter: &mut TokenIter) -> Result<(&'a [u8], InputPosition, InputPosition), ParseError> {
 
    if Some(TokenKind::Pragma) != iter.next() {
 
        return Err(ParseError::new_error_str_at_pos(source, iter.last_valid_pos(), "expected a pragma"));
 
    }
 
    let (pragma_start, pragma_end) = iter.next_positions();
 
    iter.consume();
 
    Ok((source.section_at_pos(pragma_start, pragma_end), pragma_start, pragma_end))
 
}
 

	
 
pub(crate) fn has_ident(source: &InputSource, iter: &mut TokenIter, expected: &[u8]) -> bool {
 
    peek_ident(source, iter).map_or(false, |section| section == expected)
 
}
 

	
 
pub(crate) fn peek_ident<'a>(source: &'a InputSource, iter: &mut TokenIter) -> Option<&'a [u8]> {
 
    if Some(TokenKind::Ident) == iter.next() {
 
        let (start, end) = iter.next_positions();
 
        return Some(source.section_at_pos(start, end))
 
    }
 

	
 
    None
 
}
 

	
 
/// Consumes any identifier and returns it together with its span. Does not
 
/// check if the identifier is a reserved keyword.
 
pub(crate) fn consume_any_ident<'a>(
 
    source: &'a InputSource, iter: &mut TokenIter
 
) -> Result<(&'a [u8], InputSpan), ParseError> {
 
    if Some(TokenKind::Ident) != iter.next() {
 
        return Err(ParseError::new_error_str_at_pos(source, iter.last_valid_pos(), "expected an identifier"));
 
    }
 
    let (ident_start, ident_end) = iter.next_positions();
 
    iter.consume();
 
    Ok((source.section_at_pos(ident_start, ident_end), InputSpan::from_positions(ident_start, ident_end)))
 
}
 

	
 
/// Consumes a specific identifier. May or may not be a reserved keyword.
 
pub(crate) fn consume_exact_ident(source: &InputSource, iter: &mut TokenIter, expected: &[u8]) -> Result<InputSpan, ParseError> {
 
    let (ident, pos) = consume_any_ident(source, iter)?;
 
    if ident != expected {
 
        debug_assert!(expected.is_ascii());
 
        return Err(ParseError::new_error_at_pos(
 
            source, iter.last_valid_pos(),
 
            format!("expected the text '{}'", &String::from_utf8_lossy(expected))
 
        ));
 
    }
 
    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,
 
    }
 
}
 

	
src/protocol/tests/parser_imports.rs
Show inline comments
 
/// parser_imports.rs
 
///
 
/// Simple import tests
 

	
 
use super::*;
 

	
 
#[test]
 
fn test_module_import() {
 
    Tester::new("single domain name")
 
        .with_source("
 
        #module external
 
        struct Foo { s32 field }
 
        ")
 
        .with_source("
 
        import external;
 
        s32 caller() {
 
        func caller() -> s32 {
 
            auto a = external::Foo{ field: 0 };
 
            return a.field;
 
        }
 
        ")
 
        .compile()
 
        .expect_ok();
 

	
 
    Tester::new("multi domain name")
 
        .with_source("
 
        #module external.domain
 
        struct Foo { s32 field }
 
        ")
 
        .with_source("
 
        import external.domain;
 
        s32 caller() {
 
        func caller() -> s32 {
 
            auto a = domain::Foo{ field: 0 };
 
            return a.field;
 
        }
 
        ")
 
        .compile()
 
        .expect_ok();
 

	
 
    Tester::new("aliased domain name")
 
        .with_source("
 
        #module external
 
        struct Foo { s32 field }
 
        ")
 
        .with_source("
 
        import external as aliased;
 
        s32 caller() {
 
        func caller() -> s32 {
 
            auto a = aliased::Foo{ field: 0 };
 
            return a.field;
 
        }
 
        ")
 
        .compile()
 
        .expect_ok();
 
}
 

	
 
#[test]
 
fn test_single_symbol_import() {
 
    Tester::new("specific symbol")
 
        .with_source("
 
        #module external
 
        struct Foo { s32 field }
 
        ")
 
        .with_source("
 
        import external::Foo;
 
        s32 caller() {
 
        func caller() -> s32 {
 
            auto a = Foo{ field: 1 };
 
            auto b = Foo{ field: 2 };
 
            return a.field + b.field;
 
        }")
 
        .compile()
 
        .expect_ok();
 

	
 
    Tester::new("specific aliased symbol")
 
        .with_source("
 
        #module external
 
        struct Foo { s32 field }
 
        ")
 
        .with_source("
 
        import external::Foo as Bar;
 
        s32 caller() {
 
        func caller() -> s32 {
 
            return Bar{ field: 0 }.field;
 
        }
 
        ")
 
        .compile()
 
        .expect_ok();
 

	
 
    // TODO: Re-enable once std lib is properly implemented
 
    // Tester::new("import all")
 
    //     .with_source("
 
    //     #module external
 
    //     struct Foo { s32 field }
 
    //     ")
 
    //     .with_source("
 
    //     import external::*;
 
    //     s32 caller() { return Foo{field:0}.field; }
 
    //     ")
 
    //     .compile()
 
    //     .expect_ok();
 
}
 

	
 
#[test]
 
fn test_multi_symbol_import() {
 
    Tester::new("specific symbols")
 
        .with_source("
 
        #module external
 
        struct Foo { s8 f }
 
        struct Bar { s8 b }
 
        ")
 
        .with_source("
 
        import external::{Foo, Bar};
 
        s8 caller() {
 
        func caller() -> s8 {
 
            return Foo{f:0}.f + Bar{b:1}.b;
 
        }
 
        ")
 
        .compile()
 
        .expect_ok();
 

	
 
    Tester::new("aliased symbols")
 
        .with_source("
 
        #module external
 
        struct Foo { s8 in_foo }
 
        struct Bar { s8 in_bar }
 
        ")
 
        .with_source("
 
        import external::{Foo as Bar, Bar as Foo};
 
        s8 caller() {
 
        func caller() -> s8 {
 
            return Foo{in_bar:0}.in_bar + Bar{in_foo:0}.in_foo;    
 
        }")
 
        .compile()
 
        .expect_ok();
 

	
 
    // TODO: Re-enable once std lib is properly implemented
 
    // Tester::new("import all")
 
    //     .with_source("
 
    //     #module external
 
    //     struct Foo { s8 f };
 
    //     struct Bar { s8 b };
 
    //     ")
 
    //     .with_source("
 
    //     import external::*;
 
    //     s8 caller() {
 
    //         auto f = Foo{f:0};
 
    //         auto b = Bar{b:0};
 
    //         return f.f + b.b;
 
    //     }
 
    //     ")
 
    //     .compile()
 
    //     .expect_ok();
 
    Tester::new("import all")
 
        .with_source("
 
        #module external
 
        struct Foo { s8 f }
 
        struct Bar { s8 b }
 
        ")
 
        .with_source("
 
        import external::*;
 
        func caller() -> s8 {
 
            auto f = Foo{f:0};
 
            auto b = Bar{b:0};
 
            return f.f + b.b;
 
        }
 
        ")
 
        .compile()
 
        .expect_ok();
 
}
 

	
 
#[test]
 
fn test_illegal_import_use() {
 
    Tester::new("unexpected polymorphic args")
 
        .with_source("
 
        #module external
 
        struct Foo { s8 f }
 
        ")
 
        .with_source("
 
        import external;
 
        s8 caller() {
 
        func caller() -> s8 {
 
            auto foo = external::Foo<s32>{ f: 0 };
 
            return foo.f;
 
        }
 
        ")
 
        .compile()
 
        .expect_err()
 
        .error(|e| { e
 
            .assert_msg_has(0, "the type Foo is not polymorphic");
 
            .assert_msg_has(0, "the type 'external::Foo' is not polymorphic");
 
        });
 

	
 
    Tester::new("mismatched polymorphic args")
 
        .with_source("
 
        #module external
 
        struct Foo<T>{ T f }
 
        ")
 
        .with_source("
 
        import external;
 
        s8 caller() {
 
        func caller() -> s8 {
 
            auto foo = external::Foo<s8, s32>{ f: 0 };
 
            return foo.f;
 
        }")
 
        .compile()
 
        .expect_err()
 
        .error(|e| { e
 
            .assert_msg_has(0, "expected 1 polymorphic")
 
            .assert_msg_has(0, "2 were specified");
 
            .assert_msg_has(0, "2 were provided");
 
        });
 

	
 
    Tester::new("module as type")
 
        .with_source("
 
        #module external
 
        ")
 
        .with_source("
 
        import external;
 
        s8 caller() {
 
        func caller() -> s8 {
 
            auto foo = external{ f: 0 };
 
            return 0;
 
        }
 
        ")
 
        .compile()
 
        .expect_err()
 
        .error(|e| { e
 
            .assert_msg_has(0, "resolved to a namespace");
 
            .assert_msg_has(0, "expected a type but got a module");
 
        });
 

	
 
    Tester::new("more namespaces than needed, not polymorphic")
 
    Tester::new("missing type")
 
        .with_source("
 
        #module external
 
        struct Foo { s8 f }
 
        struct Bar {}
 
        ")
 
        .with_source("
 
        import external;
 
        s8 caller() {
 
            auto foo = external::Foo::f{ f: 0 };
 
            return 0;
 
        }")
 
        import external::Foo;
 
        ")
 
        .compile()
 
        .expect_err()
 
        .error(|e| { e
 
            .assert_msg_has(0, "not fully resolve this identifier")
 
            .assert_msg_has(0, "able to match 'external::Foo'");
 
            .assert_msg_has(0, "could not find symbol 'Foo' within module 'external'")
 
            .assert_occurs_at(0, "Foo");
 
        });
 

	
 
    Tester::new("import from another import")
 
        .with_source("
 
        #module mod1
 
        struct Foo { s8 f }
 
        ")
 
        .with_source("
 
        #module mod2
 
        import mod1::Foo;
 
        struct Bar { Foo f }
 
        ")
 
        .with_source("
 
        import mod2;
 
        s8 caller() {
 
        func caller() -> s8 {
 
            auto bar = mod2::Bar{ f: mod2::Foo{ f: 0 } };
 
            return var.f.f;
 
        }")
 
        .compile()
 
        .expect_err()
 
        .error(|e| { e
 
            .assert_msg_has(0, "Could not resolve this identifier")
 
            .assert_occurs_at(0, "mod2::Foo");
 
            .assert_msg_has(0, "unknown type 'Foo' in module 'mod2'")
 
            .assert_msg_has(0, "module 'mod2' does import 'Foo'")
 
            .assert_occurs_at(0, "Foo");
 
        });
 
}
 
\ No newline at end of file
src/protocol/tests/parser_inference.rs
Show inline comments
 
/// parser_inference.rs
 
///
 
/// Simple tests for the type inferences
 

	
 
use super::*;
 

	
 
#[test]
 
fn test_integer_inference() {
 
    Tester::new_single_source_expect_ok(
 
        "by arguments",
 
        "
 
        func call(u8 b, u16 s, u32 i, u64 l) -> u32 {
 
            auto b2 = b;
 
            auto s2 = s;
 
            auto i2 = i;
 
            auto l2 = l;
 
            return i2;
 
        }
 
        "
 
    ).for_function("call", |f| { f
 
        .for_variable("b2", |v| { v
 
            .assert_parser_type("auto")
 
            .assert_concrete_type("u8");
 
        })
 
        .for_variable("s2", |v| { v
 
            .assert_parser_type("auto")
 
            .assert_concrete_type("u16");
 
        })
 
        .for_variable("i2", |v| { v
 
            .assert_parser_type("auto")
 
            .assert_concrete_type("u32");
 
        })
 
        .for_variable("l2", |v| { v
 
            .assert_parser_type("auto")
 
            .assert_concrete_type("u64");
 
        });
 
    });
 

	
 
    Tester::new_single_source_expect_ok(
 
        "by assignment",
 
        "
 
        func call() -> u32 {
 
            u8 b1 = 0; u16 s1 = 0; u32 i1 = 0; u64 l1 = 0;
 
            auto b2 = b1;
 
            auto s2 = s1;
 
            auto i2 = i1;
 
            auto l2 = l1;
 
            return 0;
 
        }"
 
    ).for_function("call", |f| { f
 
        .for_variable("b2", |v| { v
 
            .assert_parser_type("auto")
 
            .assert_concrete_type("u8");
 
        })
 
        .for_variable("s2", |v| { v
 
            .assert_parser_type("auto")
 
            .assert_concrete_type("u16");
 
        })
 
        .for_variable("i2", |v| { v
 
            .assert_parser_type("auto")
 
            .assert_concrete_type("u32");
 
        })
 
        .for_variable("l2", |v| { v
 
            .assert_parser_type("auto")
 
            .assert_concrete_type("u64");
 
        });
 
    });
 
}
 

	
 
#[test]
 
fn test_binary_expr_inference() {
 
    Tester::new_single_source_expect_ok(
 
        "compatible types",
 
        "func call() -> s32 {
 
            s8 b0 = 0;
 
            s8 b1 = 1;
 
            s16 s0 = 0;
 
            s16 s1 = 1;
 
            s32 i0 = 0;
 
            s32 i1 = 1;
 
            s64 l0 = 0;
 
            s64 l1 = 1;
 
            auto b = b0 + b1;
 
            auto s = s0 + s1;
 
            auto i = i0 + i1;
 
            auto l = l0 + l1;
 
            return i;
 
        }"
 
    ).for_function("call", |f| { f
 
        .for_expression_by_source(
 
            "b0 + b1", "+", 
 
            |e| { e.assert_concrete_type("s8"); }
 
        )
 
        .for_expression_by_source(
 
            "s0 + s1", "+", 
 
            |e| { e.assert_concrete_type("s16"); }
 
        )
 
        .for_expression_by_source(
 
            "i0 + i1", "+", 
 
            |e| { e.assert_concrete_type("s32"); }
 
        )
 
        .for_expression_by_source(
 
            "l0 + l1", "+", 
 
            |e| { e.assert_concrete_type("s64"); }
 
        );
 
    });
 

	
 
    Tester::new_single_source_expect_err(
 
        "incompatible types", 
 
        "func call() -> s32 {
 
            s8 b = 0;
 
            s64 l = 1;
 
            auto r = b + l;
 
            return 0;
 
        }"
 
    ).error(|e| { e
 
        .assert_ctx_has(0, "b + l")
 
        .assert_msg_has(0, "cannot apply")
 
        .assert_occurs_at(0, "+")
 
        .assert_msg_has(1, "has type 's8'")
 
        .assert_msg_has(2, "has type 's64'");
 
    });
 
}
 

	
 

	
 

	
 
#[test]
 
fn test_struct_inference() {
 
    Tester::new_single_source_expect_ok(
 
        "by function calls",
 
        "
 
        struct Pair<T1, T2>{ T1 first, T2 second }
 
        func construct<T1, T2>(T1 first, T2 second) -> Pair<T1, T2> {
 
            return Pair{ first: first, second: second };
 
        }
 
        func fix_t1<T2>(Pair<s8, T2> arg) -> s32 { return 0; }
 
        func fix_t2<T1>(Pair<T1, s32> arg) -> s32 { return 0; }
 
        func test() -> s32 {
 
            auto first = 0;
 
            auto second = 1;
 
            auto pair = construct(first, second);
 
            fix_t1(pair);
 
            fix_t2(pair);
 
            return 0;
 
        }
 
        "
 
    ).for_function("test", |f| { f
 
        .for_variable("first", |v| { v
 
            .assert_parser_type("auto")
 
            .assert_concrete_type("s8");
 
        })
 
        .for_variable("second", |v| { v
 
            .assert_parser_type("auto")
 
            .assert_concrete_type("s32");
 
        })
 
        .for_variable("pair", |v| { v
 
            .assert_parser_type("auto")
 
            .assert_concrete_type("Pair<s8,s32>");
 
        });
 
    });
 

	
 
    // Tester::new_single_source_expect_ok(
 
    //     "by field access",
 
    //     "
 
    //     struct Pair<T1, T2>{ T1 first, T2 second }
 
    //     func construct<T1, T2>(T1 first, T2 second) -> Pair<T1, T2> {
 
    //         return Pair{ first: first, second: second };
 
    //     }
 
    //     test() -> s32 {
 
    //         auto first = 0;
 
    //         auto second = 1;
 
    //         auto pair = construct(first, second);
 
    //         s8 assign_first = 0;
 
    //         s64 assign_second = 1;
 
    //         pair.first = assign_first;
 
    //         pair.second = assign_second;
 
    //         return 0;
 
    //     }
 
    //     "
 
    // ).for_function("test", |f| { f
 
    //     .for_variable("first", |v| { v
 
    //         .assert_parser_type("auto")
 
    //         .assert_concrete_type("s8");
 
    //     })
 
    //     .for_variable("second", |v| { v
 
    //         .assert_parser_type("auto")
 
    //         .assert_concrete_type("s64");
 
    //     })
 
    //     .for_variable("pair", |v| { v
 
    //         .assert_parser_type("auto")
 
    //         .assert_concrete_type("Pair<s8,s64>");
 
    //     });
 
    // });
 
    //
 
    // Tester::new_single_source_expect_ok(
 
    //     "by nested field access",
 
    //     "
 
    //     struct Node<T1, T2>{ T1 l, T2 r }
 
    //     func construct<T1, T2>(T1 l, T2 r) -> Node<T1, T2> {
 
    //         return Node{ l: l, r: r };
 
    //     }
 
    //     func fix_poly<T>(Node<T, T> a) -> s32 { return 0; }
 
    //     func test() -> s32 {
 
    //         s8 assigned = 0;
 
    //         auto thing = construct(assigned, construct(0, 1));
 
    //         fix_poly(thing.r);
 
    //         thing.r.r = assigned;
 
    //         return 0;
 
    //     }
 
    //     ",
 
    // ).for_function("test", |f| { f
 
    //     .for_variable("thing", |v| { v
 
    //         .assert_parser_type("auto")
 
    //         .assert_concrete_type("Node<s8,Node<s8,s8>>");
 
    //     });
 
    // });
 
    Tester::new_single_source_expect_ok(
 
        "by field access",
 
        "
 
        struct Pair<T1, T2>{ T1 first, T2 second }
 
        func construct<T1, T2>(T1 first, T2 second) -> Pair<T1, T2> {
 
            return Pair{ first: first, second: second };
 
        }
 
        func test() -> s32 {
 
            auto first = 0;
 
            auto second = 1;
 
            auto pair = construct(first, second);
 
            s8 assign_first = 0;
 
            s64 assign_second = 1;
 
            pair.first = assign_first;
 
            pair.second = assign_second;
 
            return 0;
 
        }
 
        "
 
    ).for_function("test", |f| { f
 
        .for_variable("first", |v| { v
 
            .assert_parser_type("auto")
 
            .assert_concrete_type("s8");
 
        })
 
        .for_variable("second", |v| { v
 
            .assert_parser_type("auto")
 
            .assert_concrete_type("s64");
 
        })
 
        .for_variable("pair", |v| { v
 
            .assert_parser_type("auto")
 
            .assert_concrete_type("Pair<s8,s64>");
 
        });
 
    });
 

	
 
    Tester::new_single_source_expect_ok(
 
        "by nested field access",
 
        "
 
        struct Node<T1, T2>{ T1 l, T2 r }
 
        func construct<T1, T2>(T1 l, T2 r) -> Node<T1, T2> {
 
            return Node{ l: l, r: r };
 
        }
 
        func fix_poly<T>(Node<T, T> a) -> s32 { return 0; }
 
        func test() -> s32 {
 
            s8 assigned = 0;
 
            auto thing = construct(assigned, construct(0, 1));
 
            fix_poly(thing.r);
 
            thing.r.r = assigned;
 
            return 0;
 
        }
 
        ",
 
    ).for_function("test", |f| { f
 
        .for_variable("thing", |v| { v
 
            .assert_parser_type("auto")
 
            .assert_concrete_type("Node<s8,Node<s8,s8>>");
 
        });
 
    });
 
}
 

	
 
#[test]
 
fn test_enum_inference() {
 
    Tester::new_single_source_expect_ok(
 
        "no polymorphic vars",
 
        "
 
        enum Choice { A, B }
 
        test_instances() -> s32 {
 
        func test_instances() -> s32 {
 
            auto foo = Choice::A;
 
            auto bar = Choice::B;
 
            return 0;
 
        }
 
        "
 
    ).for_function("test_instances", |f| { f
 
        .for_variable("foo", |v| { v
 
            .assert_parser_type("auto")
 
            .assert_concrete_type("Choice");
 
        })
 
        .for_variable("bar", |v| { v
 
            .assert_parser_type("auto")
 
            .assert_concrete_type("Choice");
 
        });
 
    });
 

	
 
    Tester::new_single_source_expect_ok(
 
        "one polymorphic var",
 
        "
 
        enum Choice<T>{
 
            A,
 
            B,
 
        }
 
        func fix_as_s8(Choice<s8> arg) -> s32 { return 0; }
 
        fix_as_s32(Choice<s32> arg) -> s32 { return 0; }
 
        test_instances() -> s32 {
 
        func fix_as_s32(Choice<s32> arg) -> s32 { return 0; }
 
        func test_instances() -> s32 {
 
            auto choice_s8 = Choice::A;
 
            auto choice_s32_1 = Choice::B;
 
            Choice<auto> choice_s32_2 = Choice::B;
 
            fix_as_s8(choice_s8);
 
            fix_as_s32(choice_s32_1);
 
            return fix_as_int(choice_s32_2);
 
            return fix_as_s32(choice_s32_2);
 
        }
 
        "
 
    ).for_function("test_instances", |f| { f
 
        .for_variable("choice_s8", |v| { v
 
            .assert_parser_type("auto")
 
            .assert_concrete_type("Choice<s8>");
 
        })
 
        .for_variable("choice_int1", |v| { v
 
        .for_variable("choice_s32_1", |v| { v
 
            .assert_parser_type("auto")
 
            .assert_concrete_type("Choice<int>");
 
            .assert_concrete_type("Choice<s32>");
 
        })
 
        .for_variable("choice_int2", |v| { v
 
        .for_variable("choice_s32_2", |v| { v
 
            .assert_parser_type("Choice<auto>")
 
            .assert_concrete_type("Choice<int>");
 
            .assert_concrete_type("Choice<s32>");
 
        });
 
    });
 

	
 
    Tester::new_single_source_expect_ok(
 
        "two polymorphic vars",
 
        "
 
        enum Choice<T1, T2>{ A, B, }
 
        fix_t1<T>(Choice<s8, T> arg) -> s32 { return 0; }
 
        fix_t2<T>(Choice<T, int> arg) -> s32 { return 0; }
 
        test_instances() -> int {
 
        func fix_t1<T>(Choice<s8, T> arg) -> s32 { return 0; }
 
        func fix_t2<T>(Choice<T, s32> arg) -> s32 { return 0; }
 
        func test_instances() -> s32 {
 
            Choice<s8, auto> choice1 = Choice::A;
 
            Choice<auto, int> choice2 = Choice::A;
 
            Choice<auto, s32> choice2 = Choice::A;
 
            Choice<auto, auto> choice3 = Choice::B;
 
            auto choice4 = Choice::B;
 
            fix_t1(choice1); fix_t1(choice2); fix_t1(choice3); fix_t1(choice4);
 
            fix_t2(choice1); fix_t2(choice2); fix_t2(choice3); fix_t2(choice4);
 
            return 0;
 
        }
 
        "
 
    ).for_function("test_instances", |f| { f
 
        .for_variable("choice1", |v| { v
 
            .assert_parser_type("Choice<s8,auto>")
 
            .assert_concrete_type("Choice<s8,int>");
 
            .assert_concrete_type("Choice<s8,s32>");
 
        })
 
        .for_variable("choice2", |v| { v
 
            .assert_parser_type("Choice<auto,int>")
 
            .assert_concrete_type("Choice<s8,int>");
 
            .assert_parser_type("Choice<auto,s32>")
 
            .assert_concrete_type("Choice<s8,s32>");
 
        })
 
        .for_variable("choice3", |v| { v
 
            .assert_parser_type("Choice<auto,auto>")
 
            .assert_concrete_type("Choice<s8,int>");
 
            .assert_concrete_type("Choice<s8,s32>");
 
        })
 
        .for_variable("choice4", |v| { v
 
            .assert_parser_type("auto")
 
            .assert_concrete_type("Choice<s8,int>");
 
            .assert_concrete_type("Choice<s8,s32>");
 
        });
 
    });
 
}
 

	
 
#[test]
 
fn test_failed_polymorph_inference() {
 
    Tester::new_single_source_expect_err(
 
        "function call inference mismatch",
 
        "
 
        func poly<T>(T a, T b) -> s32 { return 0; }
 
        func call() -> s32 {
 
            s8 first_arg = 5;
 
            s64 second_arg = 2;
 
            return poly(first_arg, second_arg);
 
        }
 
        "
 
    ).error(|e| { e
 
        .assert_num(3)
 
        .assert_ctx_has(0, "poly(first_arg, second_arg)")
 
        .assert_occurs_at(0, "poly")
 
        .assert_msg_has(0, "Conflicting type for polymorphic variable 'T'")
 
        .assert_occurs_at(1, "second_arg")
 
        .assert_msg_has(1, "inferred it to 's64'")
 
        .assert_occurs_at(2, "first_arg")
 
        .assert_msg_has(2, "inferred it to 's8'");
 
    });
 

	
 
    Tester::new_single_source_expect_err(
 
        "struct literal inference mismatch",
 
        "
 
        struct Pair<T>{ T first, T second }
 
        call() -> s32 {
 
        func call() -> s32 {
 
            s8 first_arg = 5;
 
            s64 second_arg = 2;
 
            auto pair = Pair{ first: first_arg, second: second_arg };
 
            return 3;
 
        }
 
        "
 
    ).error(|e| { e
 
        .assert_num(3)
 
        .assert_ctx_has(0, "Pair{ first: first_arg, second: second_arg }")
 
        .assert_occurs_at(0, "Pair{")
 
        .assert_msg_has(0, "Conflicting type for polymorphic variable 'T'")
 
        .assert_occurs_at(1, "second_arg")
 
        .assert_msg_has(1, "inferred it to 's64'")
 
        .assert_occurs_at(2, "first_arg")
 
        .assert_msg_has(2, "inferred it to 's8'");
 
    });
 

	
 
    // Cannot really test literal inference error, but this comes close
 
    Tester::new_single_source_expect_err(
 
        "enum literal inference mismatch",
 
        "
 
        enum Uninteresting<T>{ Variant }
 
        func fix_t<T>(Uninteresting<T> arg) -> s32 { return 0; }
 
        func call() -> s32 {
 
            auto a = Uninteresting::Variant;
 
            fix_t<s8>(a);
 
            fix_t<int>(a);
 
            fix_t<s32>(a);
 
            return 4;
 
        }
 
        "
 
    ).error(|e| { e
 
        .assert_num(2)
 
        .assert_any_msg_has("type 'Uninteresting<s8>'")
 
        .assert_any_msg_has("type 'Uninteresting<int>'");
 
        .assert_any_msg_has("type 'Uninteresting<s32>'");
 
    });
 

	
 
    Tester::new_single_source_expect_err(
 
        "field access inference mismatch",
 
        "
 
        struct Holder<Shazam>{ Shazam a }
 
        func call() -> s32 {
 
            s8 to_hold = 0;
 
            auto holder = Holder{ a: to_hold };
 
            return holder.a;
 
        }
 
        "
 
    ).error(|e| { e
 
        .assert_num(3)
 
        .assert_ctx_has(0, "holder.a")
 
        .assert_occurs_at(0, ".")
 
        .assert_msg_has(0, "Conflicting type for polymorphic variable 'Shazam'")
 
        .assert_msg_has(1, "inferred it to 's8'")
 
        .assert_msg_has(2, "inferred it to 'int'");
 
        .assert_msg_has(2, "inferred it to 's32'");
 
    });
 

	
 
    // TODO: Needs better error messages anyway, but this failed before
 
    Tester::new_single_source_expect_err(
 
        "nested field access inference mismatch",
 
        "
 
        struct Node<T1, T2>{ T1 l, T2 r }
 
        func construct<T1, T2>(T1 l, T2 r) -> Node<T1, T2> { return Node{ l: l, r: r }; }
 
        func fix_poly<T>(Node<T, T> a) -> s32 { return 0; }
 
        func test() -> s32 {
 
            s8 assigned = 0;
 
            s64 another = 1;
 
            auto thing = construct(assigned, construct(another, 1));
 
            fix_poly(thing.r);
 
            thing.r.r = assigned;
 
            return 0;
 
        }
 
        ",
 
    );
 
}
 
\ No newline at end of file
src/protocol/tests/parser_monomorphs.rs
Show inline comments
 
/// parser_monomorphs.rs
 
///
 
/// Simple tests to make sure that all of the appropriate monomorphs are 
 
/// instantiated
 

	
 
use super::*;
 

	
 
#[test]
 
fn test_struct_monomorphs() {
 
    Tester::new_single_source_expect_ok(
 
        "no polymorph",
 
        "struct Integer{ s32 field }"
 
    ).for_struct("Integer", |s| { s
 
        .assert_num_monomorphs(0);
 
    });
 

	
 
    Tester::new_single_source_expect_ok(
 
        "single polymorph",
 
        "
 
        struct Number<T>{ T number }
 
        s32 instantiator() {
 
        func instantiator() -> s32 {
 
            auto a = Number<s8>{ number: 0 };
 
            auto b = Number<s8>{ number: 1 };
 
            auto c = Number<s32>{ number: 2 };
 
            auto d = Number<s64>{ number: 3 };
 
            auto e = Number<Number<s16>>{ number: Number{ number: 4 }};
 
            return 0;
 
        }
 
        "
 
    ).for_struct("Number", |s| { s
 
        .assert_has_monomorph("s8")
 
        .assert_has_monomorph("s16")
 
        .assert_has_monomorph("s32")
 
        .assert_has_monomorph("s64")
 
        .assert_has_monomorph("Number<s16>")
 
        .assert_num_monomorphs(5);
 
    }).for_function("instantiator", |f| { f
 
        .for_variable("a", |v| {v.assert_concrete_type("Number<s8>");} )
 
        .for_variable("e", |v| {v.assert_concrete_type("Number<Number<s16>>");} );
 
    });
 
}
 

	
 
#[test]
 
fn test_enum_monomorphs() {
 
    Tester::new_single_source_expect_ok(
 
        "no polymorph",
 
        "
 
        enum Answer{ Yes, No }
 
        s32 do_it() { auto a = Answer::Yes; return 0; }
 
        func do_it() -> s32 { auto a = Answer::Yes; return 0; }
 
        "
 
    ).for_enum("Answer", |e| { e
 
        .assert_num_monomorphs(0);
 
    });
 

	
 
    Tester::new_single_source_expect_ok(
 
        "single polymorph",
 
        "
 
        enum Answer<T> { Yes, No }
 
        s32 instantiator() {
 
        func instantiator() -> s32 {
 
            auto a = Answer<s8>::Yes;
 
            auto b = Answer<s8>::No;
 
            auto c = Answer<s32>::Yes;
 
            auto d = Answer<Answer<Answer<s64>>>::No;
 
            return 0;
 
        }
 
        "
 
    ).for_enum("Answer", |e| { e
 
        .assert_num_monomorphs(3)
 
        .assert_has_monomorph("s8")
 
        .assert_has_monomorph("s32")
 
        .assert_has_monomorph("Answer<Answer<s64>>");
 
    });
 
}
 

	
 
#[test]
 
fn test_union_monomorphs() {
 
    Tester::new_single_source_expect_ok(
 
        "no polymorph",
 
        "
 
        union Trinary { Undefined, Value(boolean) }
 
        s32 do_it() { auto a = Trinary::Value(true); return 0; }
 
        union Trinary { Undefined, Value(bool) }
 
        func do_it() -> s32 { auto a = Trinary::Value(true); return 0; }
 
        "
 
    ).for_union("Trinary", |e| { e
 
        .assert_num_monomorphs(0);
 
    });
 

	
 
    // TODO: Does this do what we want? Or do we expect the embedded monomorph
 
    //  Result<s8,s32> to be instantiated as well? I don't think so.
 
    Tester::new_single_source_expect_ok(
 
        "polymorphs",
 
        "
 
        union Result<T, E>{ Ok(T), Err(E) }
 
        s32 instantiator() {
 
        func instantiator() -> s32 {
 
            s16 a_s16 = 5;
 
            auto a = Result<s8, boolean>::Ok(0);
 
            auto b = Result<boolean, s8>::Ok(true);
 
            auto a = Result<s8, bool>::Ok(0);
 
            auto b = Result<bool, s8>::Ok(true);
 
            auto c = Result<Result<s8, s32>, Result<s16, s64>>::Err(Result::Ok(5));
 
            auto d = Result<Result<s8, s32>, auto>::Err(Result<auto, s64>::Ok(a_s16));
 
            return 0;
 
        }
 
        "
 
    ).for_union("Result", |e| { e
 
        .assert_num_monomorphs(4)
 
        .assert_has_monomorph("s8;bool")
 
        .assert_has_monomorph("bool;s8")
 
        .assert_has_monomorph("Result<s8,s32>;Result<s16,s64>")
 
        .assert_has_monomorph("s16;s64");
 
    }).for_function("instantiator", |f| { f
 
        .for_variable("d", |v| { v
 
            .assert_parser_type("auto")
 
            .assert_concrete_type("Result<Result<s8,s32>,Result<s16,s64>>");
 
        });
 
    });
 
}
 
\ No newline at end of file
src/protocol/tests/parser_validation.rs
Show inline comments
 
/// parser_validation.rs
 
///
 
/// Simple tests for the validation phase
 
/// TODO: If semicolon behind struct definition: should be fine...
 

	
 
use super::*;
 

	
 
#[test]
 
fn test_correct_struct_instance() {
 
    Tester::new_single_source_expect_ok(
 
        "single field",
 
        "
 
        struct Foo { s32 a }
 
        Foo bar(s32 arg) { return Foo{ a: arg }; }
 
        func bar(s32 arg) -> Foo { return Foo{ a: arg }; }
 
        "
 
    );
 

	
 
    Tester::new_single_source_expect_ok(
 
        "multiple fields",
 
        "
 
        struct Foo { s32 a, s32 b }
 
        Foo bar(s32 arg) { return Foo{ a: arg, b: arg }; }
 
        func bar(s32 arg) -> Foo { return Foo{ a: arg, b: arg }; }
 
        "
 
    );
 

	
 
    Tester::new_single_source_expect_ok(
 
        "single field, explicit polymorph",
 
        "
 
        struct Foo<T>{ T field }
 
        Foo<s32> bar(s32 arg) { return Foo<s32>{ field: arg }; }
 
        func bar(s32 arg) -> Foo<s32> { return Foo<s32>{ field: arg }; }
 
        "
 
    );
 

	
 
    Tester::new_single_source_expect_ok(
 
        "single field, implicit polymorph",
 
        "
 
        struct Foo<T>{ T field }
 
        s32 bar(s32 arg) {
 
        func bar(s32 arg) -> s32 {
 
            auto thingo = Foo{ field: arg };
 
            return arg;
 
        }
 
        "
 
    );
 

	
 
    Tester::new_single_source_expect_ok(
 
        "multiple fields, same explicit polymorph",
 
        "
 
        struct Pair<T1, T2>{ T1 first, T2 second }
 
        s32 bar(s32 arg) {
 
        func bar(s32 arg) -> s32 {
 
            auto qux = Pair<s32, s32>{ first: arg, second: arg };
 
            return arg;
 
        }
 
        "
 
    );
 

	
 
    Tester::new_single_source_expect_ok(
 
        "multiple fields, same implicit polymorph", 
 
        "
 
        struct Pair<T1, T2>{ T1 first, T2 second }
 
        s32 bar(s32 arg) {
 
        func bar(s32 arg) -> s32 {
 
            auto wup = Pair{ first: arg, second: arg };
 
            return arg;
 
        }
 
        "
 
    );
 

	
 
    Tester::new_single_source_expect_ok(
 
        "multiple fields, different explicit polymorph",
 
        "
 
        struct Pair<T1, T2>{ T1 first, T2 second }
 
        s32 bar(s32 arg1, s8 arg2) {
 
        func bar(s32 arg1, s8 arg2) -> s32 {
 
            auto shoo = Pair<s32, s8>{ first: arg1, second: arg2 };
 
            return arg1;
 
        }
 
        "
 
    );
 

	
 
    Tester::new_single_source_expect_ok(
 
        "multiple fields, different implicit polymorph",
 
        "
 
        struct Pair<T1, T2>{ T1 first, T2 second }
 
        s32 bar(s32 arg1, s8 arg2) {
 
        func bar(s32 arg1, s8 arg2) -> s32 {
 
            auto shrubbery = Pair{ first: arg1, second: arg2 };
 
            return arg1;
 
        }
 
        "
 
    );
 
}
 

	
 
#[test]
 
fn test_incorrect_struct_instance() {
 
    Tester::new_single_source_expect_err(
 
        "reused field in definition",
 
        "struct Foo{ s32 a, s8 a }"
 
    ).error(|e| { e
 
        .assert_num(2)
 
        .assert_occurs_at(0, "a }")
 
        .assert_msg_has(0, "defined more than once")
 
        .assert_occurs_at(1, "a, ")
 
        .assert_msg_has(1, "other struct field");
 
    });
 

	
 
    Tester::new_single_source_expect_err(
 
        "reused field in instance",
 
        "
 
        struct Foo{ int a, int b }
 
        int bar() {
 
        struct Foo{ s32 a, s32 b }
 
        func bar() -> s32 {
 
            auto foo = Foo{ a: 5, a: 3 };
 
            return 0;
 
        }
 
        "
 
    ).error(|e| { e
 
        .assert_occurs_at(0, "a: 3")
 
        .assert_msg_has(0, "field is specified more than once");
 
    });
 

	
 
    Tester::new_single_source_expect_err(
 
        "missing field",
 
        "
 
        struct Foo { int a, int b }
 
        int bar() {
 
        struct Foo { s32 a, s32 b }
 
        func bar() -> s32 {
 
            auto foo = Foo{ a: 2 };
 
            return 0;
 
        }
 
        "
 
    ).error(|e| { e
 
        .assert_occurs_at(0, "Foo{")
 
        .assert_msg_has(0, "'b' is missing");
 
    });
 

	
 
    Tester::new_single_source_expect_err(
 
        "missing fields",
 
        "
 
        struct Foo { int a, int b, int c }
 
        int bar() {
 
        struct Foo { s32 a, s32 b, s32 c }
 
        func bar() -> s32 {
 
            auto foo = Foo{ a: 2 };
 
            return 0;
 
        }
 
        "
 
    ).error(|e| { e
 
        .assert_occurs_at(0, "Foo{")
 
        .assert_msg_has(0, "[b, c] are missing");
 
    });
 
}
 

	
 
#[test]
 
fn test_correct_enum_instance() {
 
    Tester::new_single_source_expect_ok(
 
        "single variant",
 
        "
 
        enum Foo { A }
 
        Foo bar() { return Foo::A; }
 
        func bar() -> Foo { return Foo::A; }
 
        "
 
    );
 

	
 
    Tester::new_single_source_expect_ok(
 
        "multiple variants",
 
        "
 
        enum Foo { A=15, B = 0xF }
 
        Foo bar() { auto a = Foo::A; return Foo::B; }
 
        func bar() -> Foo { auto a = Foo::A; return Foo::B; }
 
        "
 
    );
 

	
 
    Tester::new_single_source_expect_ok(
 
        "explicit single polymorph",
 
        "
 
        enum Foo<T>{ A }
 
        Foo<int> bar() { return Foo::A; }
 
        func bar() -> Foo<s32> { return Foo::A; }
 
        "
 
    );
 

	
 
    Tester::new_single_source_expect_ok(
 
        "explicit multi-polymorph",
 
        "
 
        enum Foo<A, B>{ A, B }
 
        Foo<s8, int> bar() { return Foo::B; }
 
        func bar() -> Foo<s8, s32> { return Foo::B; }
 
        "
 
    );
 
}
 

	
 
#[test]
 
fn test_incorrect_enum_instance() {
 
    Tester::new_single_source_expect_err(
 
        "variant name reuse",
 
        "
 
        enum Foo { A, A }
 
        Foo bar() { return Foo::A; }
 
        func bar() -> Foo { return Foo::A; }
 
        "
 
    ).error(|e| { e
 
        .assert_num(2)
 
        .assert_occurs_at(0, "A }")
 
        .assert_msg_has(0, "defined more than once")
 
        .assert_occurs_at(1, "A, ")
 
        .assert_msg_has(1, "other enum variant is defined here");
 
    });
 

	
 
    Tester::new_single_source_expect_err(
 
        "undefined variant",
 
        "
 
        enum Foo { A }
 
        Foo bar() { return Foo::B; }
 
        func bar() -> Foo { return Foo::B; }
 
        "
 
    ).error(|e| { e
 
        .assert_num(1)
 
        .assert_msg_has(0, "variant 'B' does not exist on the enum 'Foo'");
 
    });
 
}
 

	
 
#[test]
 
fn test_correct_union_instance() {
 
    Tester::new_single_source_expect_ok(
 
        "single tag",
 
        "
 
        union Foo { A }
 
        Foo bar() { return Foo::A; }
 
        func bar() -> Foo { return Foo::A; }
 
        "
 
    );
 

	
 
    Tester::new_single_source_expect_ok(
 
        "multiple tags",
 
        "
 
        union Foo { A, B }
 
        Foo bar() { return Foo::B; }
 
        func bar() -> Foo { return Foo::B; }
 
        "
 
    );
 

	
 
    Tester::new_single_source_expect_ok(
 
        "single embedded",
 
        "
 
        union Foo { A(int) }
 
        Foo bar() { return Foo::A(5); }
 
        union Foo { A(s32) }
 
        func bar() -> Foo { return Foo::A(5); }
 
        "
 
    );
 

	
 
    Tester::new_single_source_expect_ok(
 
        "multiple embedded",
 
        "
 
        union Foo { A(int), B(s8) }
 
        Foo bar() { return Foo::B(2); }
 
        union Foo { A(s32), B(s8) }
 
        func bar() -> Foo { return Foo::B(2); }
 
        "
 
    );
 

	
 
    Tester::new_single_source_expect_ok(
 
        "multiple values in embedded",
 
        "
 
        union Foo { A(int, s8) }
 
        Foo bar() { return Foo::A(0, 2); }
 
        union Foo { A(s32, s8) }
 
        func bar() -> Foo { return Foo::A(0, 2); }
 
        "
 
    );
 

	
 
    Tester::new_single_source_expect_ok(
 
        "mixed tag/embedded",
 
        "
 
        union OptionInt { None, Some(int) }
 
        OptionInt bar() { return OptionInt::Some(3); } 
 
        union OptionInt { None, Some(s32) }
 
        func bar() -> OptionInt { return OptionInt::Some(3); }
 
        "
 
    );
 

	
 
    Tester::new_single_source_expect_ok(
 
        "single polymorphic var",
 
        "
 
        union Option<T> { None, Some(T) }
 
        Option<int> bar() { return Option::Some(3); }"
 
        func bar() -> Option<s32> { return Option::Some(3); }"
 
    );
 

	
 
    Tester::new_single_source_expect_ok(
 
        "multiple polymorphic vars",
 
        "
 
        union Result<T, E> { Ok(T), Err(E), }
 
        Result<int, s8> bar() { return Result::Ok(3); }
 
        func bar() -> Result<s32, s8> { return Result::Ok(3); }
 
        "
 
    );
 

	
 
    Tester::new_single_source_expect_ok(
 
        "multiple polymorphic in one variant",
 
        "
 
        union MaybePair<T1, T2>{ None, Some(T1, T2) }
 
        MaybePair<s8, int> bar() { return MaybePair::Some(1, 2); }
 
        func bar() -> MaybePair<s8, s32> { return MaybePair::Some(1, 2); }
 
        "
 
    );
 
}
 

	
 
#[test]
 
fn test_incorrect_union_instance() {
 
    Tester::new_single_source_expect_err(
 
        "tag-variant name reuse",
 
        "
 
        union Foo{ A, A }
 
        "
 
    ).error(|e| { e
 
        .assert_num(2)
 
        .assert_occurs_at(0, "A }")
 
        .assert_msg_has(0, "union variant is defined more than once")
 
        .assert_occurs_at(1, "A, ")
 
        .assert_msg_has(1, "other union variant");
 
    });
 

	
 
    Tester::new_single_source_expect_err(
 
        "embedded-variant name reuse",
 
        "
 
        union Foo{ A(int), A(s8) }
 
        union Foo{ A(s32), A(s8) }
 
        "
 
    ).error(|e| { e 
 
        .assert_num(2)
 
        .assert_occurs_at(0, "A(s8)")
 
        .assert_msg_has(0, "union variant is defined more than once")
 
        .assert_occurs_at(1, "A(int)")
 
        .assert_occurs_at(1, "A(s32)")
 
        .assert_msg_has(1, "other union variant");
 
    });
 

	
 
    Tester::new_single_source_expect_err(
 
        "undefined variant",
 
        "
 
        union Silly{ Thing(s8) }
 
        Silly bar() { return Silly::Undefined(5); }
 
        func bar() -> Silly { return Silly::Undefined(5); }
 
        "
 
    ).error(|e| { e
 
        .assert_msg_has(0, "variant 'Undefined' does not exist on the union 'Silly'");
 
    });
 

	
 
    Tester::new_single_source_expect_err(
 
        "using tag instead of embedded",
 
        "
 
        union Foo{ A(int) }
 
        Foo bar() { return Foo::A; }
 
        union Foo{ A(s32) }
 
        func bar() -> Foo { return Foo::A; }
 
        "
 
    ).error(|e| { e
 
        .assert_msg_has(0, "variant 'A' of union 'Foo' expects 1 embedded values, but 0 were");
 
    });
 

	
 
    Tester::new_single_source_expect_err(
 
        "using embedded instead of tag",
 
        "
 
        union Foo{ A }
 
        Foo bar() { return Foo::A(3); }
 
        func bar() -> Foo { return Foo::A(3); }
 
        "
 
    ).error(|e| { e 
 
        .assert_msg_has(0, "The variant 'A' of union 'Foo' expects 0");
 
    });
 

	
 
    Tester::new_single_source_expect_err(
 
        "wrong embedded value",
 
        "
 
        union Foo{ A(int) }
 
        Foo bar() { return Foo::A(false); }
 
        union Foo{ A(s32) }
 
        func bar() -> Foo { return Foo::A(false); }
 
        "
 
    ).error(|e| { e
 
        .assert_occurs_at(0, "Foo::A")
 
        .assert_msg_has(0, "Failed to fully resolve")
 
        .assert_msg_has(0, "failed to fully resolve")
 
        .assert_occurs_at(1, "false")
 
        .assert_msg_has(1, "has been resolved to 'int'")
 
        .assert_msg_has(1, "has been resolved to 's32'")
 
        .assert_msg_has(1, "has been resolved to 'bool'");
 
    });
 
}
 
\ No newline at end of file
src/protocol/tests/utils.rs
Show inline comments
 
use crate::collections::StringPool;
 
use crate::protocol::{
 
    ast::*,
 
    input_source::*,
 
    parser::{
 
        *,
 
        type_table::TypeTable,
 
        symbol_table::SymbolTable,
 
        token_parsing::*,
 
    },
 
};
 

	
 
// Carries information about the test into utility structures for builder-like
 
// assertions
 
#[derive(Clone, Copy)]
 
struct TestCtx<'a> {
 
    test_name: &'a str,
 
    heap: &'a Heap,
 
    modules: &'a Vec<Module>,
 
    types: &'a TypeTable,
 
    symbols: &'a SymbolTable,
 
}
 

	
 
//------------------------------------------------------------------------------
 
// Interface for parsing and compiling
 
//------------------------------------------------------------------------------
 

	
 
pub(crate) struct Tester {
 
    test_name: String,
 
    sources: Vec<String>
 
}
 

	
 
impl Tester {
 
    /// Constructs a new tester, allows adding multiple sources before compiling
 
    pub(crate) fn new<S: ToString>(test_name: S) -> Self {
 
        Self{
 
            test_name: test_name.to_string(),
 
            sources: Vec::new()
 
        }
 
    }
 

	
 
    /// Utility for quick tests that use a single source file and expect the
 
    /// compilation to succeed.
 
    pub(crate) fn new_single_source_expect_ok<T: ToString, S: ToString>(test_name: T, source: S) -> AstOkTester {
 
        Self::new(test_name)
 
            .with_source(source)
 
            .compile()
 
            .expect_ok()
 
    }
 

	
 
    /// Utility for quick tests that use a single source file and expect the
 
    /// compilation to fail.
 
    pub(crate) fn new_single_source_expect_err<T: ToString, S: ToString>(test_name: T, source: S) -> AstErrTester {
 
        Self::new(test_name)
 
            .with_source(source)
 
            .compile()
 
            .expect_err()
 
    }
 

	
 
    pub(crate) fn with_source<S: ToString>(mut self, source: S) -> Self {
 
        self.sources.push(source.to_string());
 
        self
 
    }
 

	
 
    pub(crate) fn compile(self) -> AstTesterResult {
 
        let mut parser = Parser::new();
 
        for source in self.sources.into_iter() {
 
            let source = source.into_bytes();
 
            let input_source = InputSource::new(String::from(""), source);
 

	
 
            if let Err(err) = parser.feed(input_source) {
 
                return AstTesterResult::Err(AstErrTester::new(self.test_name, err))
 
            }
 
        }
 

	
 
        if let Err(err) = parser.parse() {
 
            return AstTesterResult::Err(AstErrTester::new(self.test_name, err))
 
        }
 

	
 
        AstTesterResult::Ok(AstOkTester::new(self.test_name, parser))
 
    }
 
}
 

	
 
pub(crate) enum AstTesterResult {
 
    Ok(AstOkTester),
 
    Err(AstErrTester)
 
}
 

	
 
impl AstTesterResult {
 
    pub(crate) fn expect_ok(self) -> AstOkTester {
 
        match self {
 
            AstTesterResult::Ok(v) => v,
 
            AstTesterResult::Err(err) => {
 
                let wrapped = ErrorTester{ test_name: &err.test_name, error: &err.error };
 
                println!("DEBUG: Full error:\n{}", &err.error);
 
                assert!(
 
                    false,
 
                    "[{}] Expected compilation to succeed, but it failed with {}",
 
                    err.test_name, wrapped.assert_postfix()
 
                );
 
                unreachable!();
 
            }
 
        }
 
    }
 

	
 
    pub(crate) fn expect_err(self) -> AstErrTester {
 
        match self {
 
            AstTesterResult::Ok(ok) => {
 
                assert!(false, "[{}] Expected compilation to fail, but it succeeded", ok.test_name);
 
                unreachable!();
 
            },
 
            AstTesterResult::Err(err) => err,
 
        }
 
    }
 
}
 

	
 
//------------------------------------------------------------------------------
 
// Interface for successful compilation
 
//------------------------------------------------------------------------------
 

	
 
pub(crate) struct AstOkTester {
 
    test_name: String,
 
    modules: Vec<Module>,
 
    heap: Heap,
 
    symbols: SymbolTable,
 
    types: TypeTable,
 
    pool: StringPool,
 
    pool: StringPool, // This is stored because if we drop it on the floor, we lose all our `StringRef<'static>`s
 
}
 

	
 
impl AstOkTester {
 
    fn new(test_name: String, parser: Parser) -> Self {
 
        Self {
 
            test_name,
 
            modules: parser.modules,
 
            heap: parser.heap,
 
            symbols: parser.symbol_table,
 
            types: parser.type_table,
 
            pool: parser.string_pool,
 
        }
 
    }
 

	
 
    pub(crate) fn for_struct<F: Fn(StructTester)>(self, name: &str, f: F) -> Self {
 
        let mut found = false;
 
        for definition in self.heap.definitions.iter() {
 
            if let Definition::Struct(definition) = definition {
 
                if definition.identifier.value.as_str() != name {
 
                    continue;
 
                }
 

	
 
                // Found struct with the same name
 
                let tester = StructTester::new(self.ctx(), definition);
 
                f(tester);
 
                found = true;
 
                break
 
            }
 
        }
 

	
 
        assert!(
 
            found, "[{}] Failed to find definition for struct '{}'",
 
            self.test_name, name
 
        );
 
        self
 
    }
 

	
 
    pub(crate) fn for_enum<F: Fn(EnumTester)>(self, name: &str, f: F) -> Self {
 
        let mut found = false;
 
        for definition in self.heap.definitions.iter() {
 
            if let Definition::Enum(definition) = definition {
 
                if definition.identifier.value.as_str() != name {
 
                    continue;
 
                }
 

	
 
                // Found enum with the same name
 
                let tester = EnumTester::new(self.ctx(), definition);
 
                f(tester);
 
                found = true;
 
                break;
 
            }
 
        }
 

	
 
        assert!(
 
            found, "[{}] Failed to find definition for enum '{}'",
 
            self.test_name, name
 
        );
 
        self
 
    }
 

	
 
    pub(crate) fn for_union<F: Fn(UnionTester)>(self, name: &str, f: F) -> Self {
 
        let mut found = false;
 
        for definition in self.heap.definitions.iter() {
 
            if let Definition::Union(definition) = definition {
 
                if definition.identifier.value.as_str() != name {
 
                    continue;
 
                }
 

	
 
                // Found union with the same name
 
                let tester = UnionTester::new(self.ctx(), definition);
 
                f(tester);
 
                found = true;
 
                break;
 
            }
 
        }
 

	
 
        assert!(
 
            found, "[{}] Failed to find definition for union '{}'",
 
            self.test_name, name
 
        );
 
        self
 
    }
 

	
 
    pub(crate) fn for_function<F: Fn(FunctionTester)>(self, name: &str, f: F) -> Self {
 
        let mut found = false;
 
        for definition in self.heap.definitions.iter() {
 
            if let Definition::Function(definition) = definition {
 
                println!("DEBUG: Have {}", definition.identifier.value.as_str());
 
                if definition.identifier.value.as_str() != name {
 
                    continue;
 
                }
 

	
 
                // Found function
 
                let tester = FunctionTester::new(self.ctx(), definition);
 
                f(tester);
 
                found = true;
 
                break;
 
            } else {
 
                println!("DEBUG: Have (not a function, but) {}", definition.identifier().value.as_str());
 
            }
 
        }
 

	
 
        if found { return self }
 

	
 
        assert!(
 
            false, "[{}] failed to find definition for function '{}'",
 
            self.test_name, name
 
        );
 
        unreachable!();
 
    }
 

	
 
    fn ctx(&self) -> TestCtx {
 
        TestCtx{
 
            test_name: &self.test_name,
 
            modules: &self.modules,
 
            heap: &self.heap,
 
            types: &self.types,
 
            symbols: &self.symbols,
 
        }
 
    }
 
}
 

	
 
//------------------------------------------------------------------------------
 
// Utilities for successful compilation
 
//------------------------------------------------------------------------------
 

	
 
pub(crate) struct StructTester<'a> {
 
    ctx: TestCtx<'a>,
 
    def: &'a StructDefinition,
 
}
 

	
 
impl<'a> StructTester<'a> {
 
    fn new(ctx: TestCtx<'a>, def: &'a StructDefinition) -> Self {
 
        Self{ ctx, def }
 
    }
 

	
 
    pub(crate) fn assert_num_fields(self, num: usize) -> Self {
 
        assert_eq!(
 
            num, self.def.fields.len(),
 
            "[{}] Expected {} struct fields, but found {} for {}",
 
            self.ctx.test_name, num, self.def.fields.len(), self.assert_postfix()
 
        );
 
        self
 
    }
 

	
 
    pub(crate) fn assert_num_monomorphs(self, num: usize) -> Self {
 
        let (is_equal, num_encountered) = has_equal_num_monomorphs(self.ctx, num, self.def.this.upcast());
 
        assert!(
 
            is_equal, "[{}] Expected {} monomorphs, but got {} for {}",
 
            self.ctx.test_name, num, num_encountered, self.assert_postfix()
 
        );
 
        self
 
    }
 

	
 
    /// Asserts that a monomorph exist, separate polymorphic variable types by
 
    /// a semicolon.
 
    pub(crate) fn assert_has_monomorph(self, serialized_monomorph: &str) -> Self {
 
        let (has_monomorph, serialized) = has_monomorph(self.ctx, self.def.this.upcast(), serialized_monomorph);
 
        assert!(
 
            has_monomorph, "[{}] Expected to find monomorph {}, but got {} for {}",
 
            self.ctx.test_name, serialized_monomorph, &serialized, self.assert_postfix()
 
        );
 
        self
 
    }
 

	
 
    pub(crate) fn for_field<F: Fn(StructFieldTester)>(self, name: &str, f: F) -> Self {
 
        // Find field with specified name
 
        for field in &self.def.fields {
 
            if field.field.value.as_str() == name {
 
                let tester = StructFieldTester::new(self.ctx, field);
 
                f(tester);
 
                return self;
 
            }
 
        }
 

	
 
        assert!(
 
            false, "[{}] Could not find struct field '{}' for {}",
 
            self.ctx.test_name, name, self.assert_postfix()
 
        );
 
        unreachable!();
 
    }
 

	
 
    fn assert_postfix(&self) -> String {
 
        let mut v = String::new();
 
        v.push_str("Struct{ name: ");
 
        v.push_str(self.def.identifier.value.as_str());
 
        v.push_str(", fields: [");
 
        for (field_idx, field) in self.def.fields.iter().enumerate() {
 
            if field_idx != 0 { v.push_str(", "); }
 
            v.push_str(field.field.value.as_str());
 
        }
 
        v.push_str("] }");
 
        v
 
    }
 
}
 

	
 
pub(crate) struct StructFieldTester<'a> {
 
    ctx: TestCtx<'a>,
 
    def: &'a StructFieldDefinition,
 
}
 

	
 
impl<'a> StructFieldTester<'a> {
 
    fn new(ctx: TestCtx<'a>, def: &'a StructFieldDefinition) -> Self {
 
        Self{ ctx, def }
 
    }
 

	
 
    pub(crate) fn assert_parser_type(self, expected: &str) -> Self {
 
        let mut serialized_type = String::new();
 
        serialize_parser_type(&mut serialized_type, &self.ctx.heap, &self.def.parser_type);
 
        assert_eq!(
 
            expected, &serialized_type,
 
            "[{}] Expected type '{}', but got '{}' for {}",
 
            self.ctx.test_name, expected, &serialized_type, self.assert_postfix()
 
        );
 
        self
 
    }
 

	
 
    fn assert_postfix(&self) -> String {
 
        let mut serialized_type = String::new();
 
        serialize_parser_type(&mut serialized_type, &self.ctx.heap, &self.def.parser_type);
 
        format!("StructField{{ name: {}, parser_type: {} }}", self.def.field.value.as_str(), serialized_type)
 
    }
 
}
 

	
 
pub(crate) struct EnumTester<'a> {
 
    ctx: TestCtx<'a>,
 
    def: &'a EnumDefinition,
 
}
 

	
 
impl<'a> EnumTester<'a> {
 
    fn new(ctx: TestCtx<'a>, def: &'a EnumDefinition) -> Self {
 
        Self{ ctx, def }
 
    }
 

	
 
    pub(crate) fn assert_num_variants(self, num: usize) -> Self {
 
        assert_eq!(
 
            num, self.def.variants.len(),
 
            "[{}] Expected {} enum variants, but found {} for {}",
 
            self.ctx.test_name, num, self.def.variants.len(), self.assert_postfix()
 
        );
 
        self
 
    }
 

	
 
    pub(crate) fn assert_num_monomorphs(self, num: usize) -> Self {
 
        let (is_equal, num_encountered) = has_equal_num_monomorphs(self.ctx, num, self.def.this.upcast());
 
        assert!(
 
            is_equal, "[{}] Expected {} monomorphs, but got {} for {}",
 
            self.ctx.test_name, num, num_encountered, self.assert_postfix()
 
        );
 
        self
 
    }
 

	
 
    pub(crate) fn assert_has_monomorph(self, serialized_monomorph: &str) -> Self {
 
        let (has_monomorph, serialized) = has_monomorph(self.ctx, self.def.this.upcast(), serialized_monomorph);
 
        assert!(
 
            has_monomorph, "[{}] Expected to find monomorph {}, but got {} for {}",
 
            self.ctx.test_name, serialized_monomorph, serialized, self.assert_postfix()
 
        );
 
        self
 
    }
 

	
 
    pub(crate) fn assert_postfix(&self) -> String {
 
        let mut v = String::new();
 
        v.push_str("Enum{ name: ");
 
        v.push_str(self.def.identifier.value.as_str());
 
        v.push_str(", variants: [");
 
        for (variant_idx, variant) in self.def.variants.iter().enumerate() {
 
            if variant_idx != 0 { v.push_str(", "); }
 
            v.push_str(variant.identifier.value.as_str());
 
        }
 
        v.push_str("] }");
 
        v
 
    }
 
}
 

	
 
pub(crate) struct UnionTester<'a> {
 
    ctx: TestCtx<'a>,
 
    def: &'a UnionDefinition,
 
}
 

	
 
impl<'a> UnionTester<'a> {
 
    fn new(ctx: TestCtx<'a>, def: &'a UnionDefinition) -> Self {
 
        Self{ ctx, def }
 
    }
 

	
 
    pub(crate) fn assert_num_variants(self, num: usize) -> Self {
 
        assert_eq!(
 
            num, self.def.variants.len(),
 
            "[{}] Expected {} union variants, but found {} for {}",
 
            self.ctx.test_name, num, self.def.variants.len(), self.assert_postfix()
 
        );
0 comments (0 inline, 0 general)