jorts/src/scanner.zig

const std = @import("std");

const token = @import("token.zig");
const main = @import("main.zig");

const TokenList = std.ArrayList(token.Token);

pub const Scanner = struct {
    source: []u8,
    tokens: TokenList,

    start: usize = 0,
    current: usize = 0,
    line: usize = 1,

    pub fn init(allocator: *std.mem.Allocator, data: []u8) Scanner {
        return Scanner{
            .source = data,
            .tokens = TokenList.init(allocator),
        };
    }

    fn isAtEnd(self: *Scanner) bool {
        return self.current >= self.source.len;
    }

    fn advance(self: *Scanner) u8 {
        self.current += 1;
        return self.source[self.current - 1];
    }

    fn currentLexeme(self: *Scanner) []u8 {
        return self.source[self.start..self.current];
    }

    fn addSimpleToken(self: *Scanner, ttype: token.TokenType) !void {
        try self.addToken(token.Token{
            .Simple = token.SimpleToken.init(
                ttype,
                self.currentLexeme(),
                self.line,
                {},
            ),
        });
    }

    fn addSliceToken(self: *Scanner, ttype: token.TokenType, slice: []u8) !void {
        try self.addToken(token.Token{
            .Slice = token.SliceToken.init(
                ttype,
                self.currentLexeme(),
                self.line,
                slice,
            ),
        });
    }

    fn addToken(
        self: *Scanner,
        tok: token.Token,
    ) !void {
        try self.tokens.append(tok);
    }

    /// Check if the next character matches what is expected.
    fn match(self: *Scanner, expected: u8) bool {
        if (self.isAtEnd()) return false;
        if (self.source[self.current] != expected) return false;

        self.current += 1;
        return true;
    }

    /// Add a SimpleToken of type_match if the next character is
    /// `expected`. Adds a SimpleToken of type_nomatch when it is not.
    fn addMatchToken(
        self: *Scanner,
        expected: u8,
        type_match: token.TokenType,
        type_nomatch: token.TokenType,
    ) !void {
        if (self.match(expected)) {
            try self.addSimpleToken(type_match);
        } else {
            try self.addSimpleToken(type_nomatch);
        }
    }

    fn peek(self: *Scanner) u8 {
        if (self.isAtEnd()) return 0;
        return self.source[self.current];
    }

    fn doString(self: *Scanner) !void {
        // consume entire string
        while (self.peek() != '"' and !self.isAtEnd()) {
            if (self.peek() == '\n') self.line += 1;
            _ = self.advance();
        }

        // unterminated string.
        if (self.isAtEnd()) {
            try main.doError(self.line, "Unterminated string.");
            return;
        }

        // the closing ".
        _ = self.advance();

        // trim the surrounding quotes.
        try self.addSliceToken(
            .STRING,
            self.source[self.start + 1 .. self.current - 1],
        );
    }

    /// Scan through our tokens and add them to the Scanner's token list.
    fn scanToken(self: *Scanner) !void {
        var c = self.advance();

        switch (c) {
            '(' => try self.addSimpleToken(.LEFT_PAREN),
            ')' => try self.addSimpleToken(.RIGHT_PAREN),
            '{' => try self.addSimpleToken(.LEFT_BRACE),
            '}' => try self.addSimpleToken(.RIGHT_BRACE),
            ',' => try self.addSimpleToken(.COMMA),
            '.' => try self.addSimpleToken(.DOT),
            '-' => try self.addSimpleToken(.MINUS),
            '+' => try self.addSimpleToken(.PLUS),
            ';' => try self.addSimpleToken(.SEMICOLON),
            '*' => try self.addSimpleToken(.STAR),

            '!' => try self.addMatchToken('=', .BANG_EQUAL, .BANG),
            '=' => try self.addMatchToken('=', .EQUAL_EQUAL, .EQUAL),
            '<' => try self.addMatchToken('=', .LESS_EQUAL, .LESS),
            '>' => try self.addMatchToken('=', .GREATER_EQUAL, .GREATER),

            '/' => blk: {
                // consume comments
                if (self.match('/')) {
                    while (self.peek() != '\n' and !self.isAtEnd()) {
                        _ = self.advance();
                    }
                } else {
                    try self.addSimpleToken(.SLASH);
                }
            },

            ' ', '\r', '\t' => blk: {},
            '\n' => blk: {
                self.line += 1;
            },

            '"' => try self.doString(),

            else => {
                try main.doError(self.line, "Unexpected character");
            },
        }
    }

    pub fn scanTokens(self: *Scanner) !TokenList {
        // while we aren't at the end, we're still consuming
        // tokens.
        while (!self.isAtEnd()) {
            self.start = self.current;
            try self.scanToken();
        }

        try self.addToken(token.Token{
            .Simple = token.SimpleToken.init(
                .EOF,
                "",
                self.line,
                {},
            ),
        });

        return self.tokens;
    }
};