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

use schala_repl::{
    ComputationRequest, ComputationResponse, GlobalOutputStats, LangMetaRequest, LangMetaResponse,
    ProgrammingLanguageInterface,
};
use stopwatch::Stopwatch;

use crate::{
    error::SchalaError, parsing, reduced_ir, symbol_table, tokenizing, tree_walk_eval, type_inference,
};

/// All the state necessary to parse and execute a Schala program are stored in this struct.
pub struct Schala<'a> {
    /// Holds a reference to the original source code, parsed into line and character
    source_reference: SourceReference,

    //state: eval::State<'static>,
    /// Keeps track of symbols and scopes
    symbol_table: symbol_table::SymbolTable,
    /// Contains information for type-checking
    type_context: type_inference::TypeContext,
    /// Schala Parser
    active_parser: parsing::Parser,

    /// Execution state for AST-walking interpreter
    eval_state: tree_walk_eval::State<'a>,

    timings: Vec<(&'static str, std::time::Duration)>,
}

/*
impl Schala {
    //TODO implement documentation for language items
    /*
    fn handle_docs(&self, source: String) -> LangMetaResponse {
      LangMetaResponse::Docs {
        doc_string: format!("Schala item `{}` : <<Schala-lang documentation not yet implemented>>", source)
      }
    }
    */
}
*/

impl<'a> Schala<'a> {
    /// Creates a new Schala environment *without* any prelude.
    fn new_blank_env() -> Schala<'a> {
        Schala {
            source_reference: SourceReference::new(),
            symbol_table: symbol_table::SymbolTable::new(),
            type_context: type_inference::TypeContext::new(),
            active_parser: parsing::Parser::new(),
            eval_state: tree_walk_eval::State::new(),
            timings: Vec::new(),
        }
    }

    /// Creates a new Schala environment with the standard prelude, which is defined as ordinary
    /// Schala code in the file `prelude.schala`
    #[allow(clippy::new_without_default)]
    pub fn new() -> Schala<'a> {
        let prelude = include_str!("../source-files/prelude.schala");
        let mut env = Schala::new_blank_env();

        let response = env.run_pipeline(prelude, SchalaConfig::default());
        if let Err(err) = response {
            panic!("Error in prelude, panicking: {}", err.display());
        }
        env
    }

    /// This is where the actual action of interpreting/compilation happens.
    /// Note: this should eventually use a query-based system for parallelization, cf.
    /// https://rustc-dev-guide.rust-lang.org/overview.html
    fn run_pipeline(&mut self, source: &str, config: SchalaConfig) -> Result<String, SchalaError> {
        self.timings = vec![];
        let sw = Stopwatch::start_new();

        // 1st stage - tokenization
        // TODO tokenize should return its own error type
        let tokens = tokenizing::tokenize(source);
        if let Some(err) = SchalaError::from_tokens(&tokens) {
            return Err(err);
        }

        //2nd stage - parsing
        self.active_parser.add_new_tokens(tokens);
        let ast = self
            .active_parser
            .parse()
            .map_err(|err| SchalaError::from_parse_error(err, &self.source_reference))?;
        self.timings.push(("parsing", sw.elapsed()));

        let sw = Stopwatch::start_new();
        //Perform all symbol table work
        self.symbol_table
            .process_ast(&ast, &mut self.type_context)
            .map_err(SchalaError::from_symbol_table)?;

        self.timings.push(("symbol_table", sw.elapsed()));

        // Typechecking
        // TODO typechecking not working
        //let _overall_type = self.type_context.typecheck(&ast).map_err(SchalaError::from_type_error);

        let sw = Stopwatch::start_new();
        let reduced_ir = reduced_ir::reduce(&ast, &self.symbol_table, &self.type_context);
        self.timings.push(("reduced_ir", sw.elapsed()));

        let sw = Stopwatch::start_new();
        let evaluation_outputs = self.eval_state.evaluate(reduced_ir, &self.type_context, config.repl);
        self.timings.push(("tree-walking-evaluation", sw.elapsed()));
        let text_output: Result<Vec<String>, String> = evaluation_outputs.into_iter().collect();

        let text_output: Result<Vec<String>, SchalaError> =
            text_output.map_err(|err| SchalaError::from_string(err, Stage::Evaluation));

        let eval_output: String =
            text_output.map(|v| Iterator::intersperse(v.into_iter(), "\n".to_owned()).collect())?;

        Ok(eval_output)
    }
}

/// Represents lines of source code
pub(crate) struct SourceReference {
    last_source: Option<String>,
    /// Offsets in *bytes* (not chars) representing a newline character
    newline_offsets: Vec<usize>,
}

impl SourceReference {
    fn new() -> SourceReference {
        SourceReference { last_source: None, newline_offsets: vec![]}
    }

    fn load_new_source(&mut self, source: &str) {

        for (offset, ch) in source.as_bytes().iter().enumerate() {
            if *ch == ('\n' as u8) {
                self.newline_offsets.push(offset);
            }
        }
        self.last_source = Some(source.to_string());
    }

    pub fn get_line(&self, line: usize) -> String {
        //TODO make sure this is utf8-safe
        let start_idx = match self.newline_offsets.binary_search(&line) {
            Ok(index) | Err(index) => index,
        };

        let last_source = self.last_source.as_ref().unwrap();

        let start = self.newline_offsets[start_idx];
        let end = self.newline_offsets.get(start_idx + 1).cloned().unwrap_or_else(|| last_source.len());

        let slice = &last_source.as_bytes()[start..end];
        std::str::from_utf8(slice).unwrap().to_string()
    }
}

#[allow(dead_code)]
#[derive(Clone, Copy, Debug)]
pub(crate) enum Stage {
    Tokenizing,
    Parsing,
    Symbols,
    ScopeResolution,
    Typechecking,
    AstReduction,
    Evaluation,
}

fn stage_names() -> Vec<&'static str> {
    vec!["tokenizing", "parsing", "symbol-table", "typechecking", "ast-reduction", "ast-walking-evaluation"]
}

#[derive(Default, Clone)]
pub struct SchalaConfig {
    pub repl: bool,
}

impl<'a> ProgrammingLanguageInterface for Schala<'a> {
    //TODO flesh out Config
    type Config = SchalaConfig;
    fn language_name() -> String {
        "Schala".to_owned()
    }

    fn source_file_suffix() -> String {
        "schala".to_owned()
    }

    fn run_computation(&mut self, request: ComputationRequest<Self::Config>) -> ComputationResponse {
        let ComputationRequest { source, debug_requests: _, config: _ } = request;
        self.source_reference.load_new_source(source);
        let sw = Stopwatch::start_new();

        let main_output =
            self.run_pipeline(source, request.config).map_err(|schala_err| schala_err.display());
        let total_duration = sw.elapsed();

        let stage_durations: Vec<_> = std::mem::replace(&mut self.timings, vec![])
            .into_iter()
            .map(|(label, duration)| (label.to_string(), duration))
            .collect();
        let global_output_stats = GlobalOutputStats { total_duration, stage_durations };

        ComputationResponse { main_output, global_output_stats, debug_responses: vec![] }
    }

    fn request_meta(&mut self, request: LangMetaRequest) -> LangMetaResponse {
        match request {
            LangMetaRequest::StageNames =>
                LangMetaResponse::StageNames(stage_names().iter().map(|s| s.to_string()).collect()),
            _ => LangMetaResponse::Custom { kind: "not-implemented".to_string(), value: "".to_string() },
        }
    }
}