Implement scanner

diff --git a/Lox.zig b/Lox.zig
new file mode 100644 (file)
index 0000000..56a1572
--- /dev/null
+++ b/Lox.zig
@@ -0,0 +1,76 @@
+const std = @import("std");
+const Allocator = std.mem.Allocator;
+const Scanner = @import("Scanner.zig");
+
+var hadError = false;
+
+pub fn main() !u8 {
+    var gpa: std.heap.DebugAllocator(.{}) = .init;
+    defer _ = gpa.deinit();
+    const allocator = gpa.allocator();
+    const args = try std.process.argsAlloc(allocator);
+    defer std.process.argsFree(allocator, args);
+
+    if (args.len > 2) {
+        var stdout_writer = std.fs.File.stdout().writer(&.{});
+        const stdout = &stdout_writer.interface;
+        try stdout.writeAll("Usage: zlox [script]\n");
+        return 64;
+    } else if (args.len == 2) {
+        return runFile(allocator, args[1]);
+    } else {
+        try runPrompt(allocator);
+    }
+
+    return 0;
+}
+
+fn runFile(allocator: Allocator, path: []const u8) !u8 {
+    const bytes = try std.fs.cwd().readFileAlloc(allocator, path, std.math.maxInt(usize));
+    defer allocator.free(bytes);
+    try run(allocator, bytes);
+    // Indicate an error in the exit code.
+    if (hadError) return 65;
+    return 0;
+}
+
+fn runPrompt(allocator: Allocator) !void {
+    var stdin_buffer: [1024]u8 = undefined;
+    var stdin_reader = std.fs.File.stdin().reader(&stdin_buffer);
+    const stdin = &stdin_reader.interface;
+    var stdout_writer = std.fs.File.stdout().writer(&.{});
+    const stdout = &stdout_writer.interface;
+
+    while (true) {
+        try stdout.writeAll("> ");
+        const line = try stdin.takeDelimiter('\n');
+        if (line == null) break;
+        try run(allocator, line.?);
+        hadError = false;
+    }
+}
+
+fn run(allocator: Allocator, source: []const u8) !void {
+    var scanner = Scanner.init(source);
+    const tokens = try scanner.scanTokens(allocator);
+    defer allocator.free(tokens);
+
+    // For now, just print the tokens.
+    for (tokens) |token| {
+        std.debug.print("{f}\n", .{token});
+    }
+}
+
+pub fn @"error"(line: u32, message: []const u8) !void {
+    try report(line, "", message);
+}
+
+var stderr_buffer: [1024]u8 = undefined;
+var stderr_writer = std.fs.File.stderr().writer(&stderr_buffer);
+const stderr = &stderr_writer.interface;
+
+fn report(line: u32, where: []const u8, message: []const u8) !void {
+    try stderr.print("[line {}] Error{s}: {s}\n", .{ line, where, message });
+    try stderr.flush();
+    hadError = true;
+}

diff --git a/README.md b/README.md
index 84b40e2ce2a0f9b2643efc420f46b71f20be2001..c2b0cfa5ddf2ddfd98d9e58b9b0fd9e047d29fe1 100644 (file)
--- a/README.md
+++ b/README.md
@@ -1,3 +1,7 @@
 # Zlox
 
 An implementation of the [Lox language](https://craftinginterpreters.com/the-lox-language.html) in Zig.
 # Zlox
 
 An implementation of the [Lox language](https://craftinginterpreters.com/the-lox-language.html) in Zig.

+
+```shell
+zig run Lox.zig
+```

diff --git a/Scanner.zig b/Scanner.zig
new file mode 100644 (file)
index 0000000..d971ec5
--- /dev/null
+++ b/Scanner.zig
@@ -0,0 +1,173 @@
+const std = @import("std");
+const Allocator = std.mem.Allocator;
+const Token = @import("Token.zig");
+const Literal = Token.Literal;
+const Scanner = @This();
+const TokenType = @import("token-type.zig").TokenType;
+const Lox = @import("Lox.zig");
+
+source: []const u8,
+tokens: std.ArrayList(Token) = .empty,
+start: u32 = 0,
+current: u32 = 0,
+line: u32 = 1,
+
+const keyword: std.StaticStringMap(TokenType) = .initComptime(.{
+    .{ "and", .@"and" },
+    .{ "class", .class },
+    .{ "else", .@"else" },
+    .{ "false", .false },
+    .{ "for", .@"for" },
+    .{ "fun", .fun },
+    .{ "if", .@"if" },
+    .{ "nil", .nil },
+    .{ "or", .@"or" },
+    .{ "print", .print },
+    .{ "return", .@"return" },
+    .{ "super", .super },
+    .{ "this", .this },
+    .{ "true", .true },
+    .{ "var", .@"var" },
+    .{ "while", .@"while" },
+});
+
+pub fn init(source: []const u8) Scanner {
+    return .{
+        .source = source,
+    };
+}
+
+pub fn scanTokens(self: *Scanner, allocator: Allocator) ![]Token {
+    while (!isAtEnd(self)) {
+        // We are at the beginning of the next lexeme.
+        self.start = self.current;
+        try self.scanToken(allocator);
+    }
+
+    try self.tokens.append(allocator, .init(.eof, "", null, self.line));
+    return try self.tokens.toOwnedSlice(allocator);
+}
+
+fn scanToken(self: *Scanner, allocator: Allocator) !void {
+    const c = self.advance();
+
+    switch (c) {
+        '(' => try self.addToken(allocator, .left_paren, null),
+        ')' => try self.addToken(allocator, .right_paren, null),
+        '{' => try self.addToken(allocator, .left_brace, null),
+        '}' => try self.addToken(allocator, .right_brace, null),
+        ',' => try self.addToken(allocator, .comma, null),
+        '.' => try self.addToken(allocator, .dot, null),
+        '-' => try self.addToken(allocator, .minus, null),
+        '+' => try self.addToken(allocator, .plus, null),
+        ';' => try self.addToken(allocator, .semicolon, null),
+        '*' => try self.addToken(allocator, .star, null),
+        '!' => try self.addToken(allocator, if (self.match('=')) .bang_equal else .bang, null),
+        '=' => try self.addToken(allocator, if (self.match('=')) .equal_equal else .equal, null),
+        '<' => try self.addToken(allocator, if (self.match('=')) .less_equal else .less, null),
+        '>' => try self.addToken(allocator, if (self.match('=')) .greater_equal else .greater, null),
+
+        '/' => if (self.match('/')) {
+            while (self.peek() != '\n' and !self.isAtEnd()) _ = self.advance();
+        } else {
+            try self.addToken(allocator, .slash, null);
+        },
+
+        ' ', '\r', '\t' => {},
+        '\n' => self.line += 1,
+        '"' => try self.string(allocator),
+
+        else => if (isDigit(c)) {
+            try self.number(allocator);
+        } else if (isAlpha(c)) {
+            try self.identifier(allocator);
+        } else {
+            try Lox.@"error"(self.line, "Unexpected character.");
+        },
+    }
+}
+
+fn identifier(self: *Scanner, allocator: Allocator) !void {
+    while (isAlphanumeric(self.peek())) _ = self.advance();
+    const text = self.source[self.start..self.current];
+    var @"type" = keyword.get(text);
+    if (@"type" == null) @"type" = .identifier;
+    try self.addToken(allocator, @"type".?, null);
+}
+
+fn number(self: *Scanner, allocator: Allocator) !void {
+    while (isDigit(self.peek())) _ = self.advance();
+
+    // Look for a fractional part.
+    if (self.peek() == '.' and isDigit(self.peekNext())) {
+        // Consume the "."
+        _ = self.advance();
+
+        while (isDigit(self.peek())) _ = self.advance();
+    }
+
+    try self.addToken(allocator, .number, .{ .number = std.fmt.parseFloat(f64, self.source[self.start..self.current]) catch unreachable });
+}
+
+fn string(self: *Scanner, allocator: Allocator) !void {
+    while (self.peek() != '"' and !self.isAtEnd()) {
+        if (self.peek() == '\n') self.line += 1;
+        _ = self.advance();
+    }
+
+    if (self.isAtEnd()) {
+        try Lox.@"error"(self.line, "Unterminated string.");
+        return;
+    }
+
+    // The closing ".
+    _ = self.advance();
+
+    const value = self.source[self.start + 1 .. self.current - 1];
+    try self.addToken(allocator, .string, .{ .string = value });
+}
+
+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;
+}
+
+fn peek(self: *Scanner) u8 {
+    if (self.isAtEnd()) return 0;
+    return self.source[self.current];
+}
+
+fn peekNext(self: *Scanner) u8 {
+    if (self.current + 1 >= self.source.len) return 0;
+    return self.source[self.current + 1];
+}
+
+fn isAlpha(c: u8) bool {
+    return (c >= 'a' and c <= 'z') or
+        (c >= 'A' and c <= 'Z') or
+        c == '_';
+}
+
+fn isAlphanumeric(c: u8) bool {
+    return isAlpha(c) or isDigit(c);
+}
+
+fn isDigit(c: u8) bool {
+    return c >= '0' and c <= '9';
+}
+
+fn isAtEnd(self: *Scanner) bool {
+    return self.current >= self.source.len;
+}
+
+fn advance(self: *Scanner) u8 {
+    defer self.current += 1;
+    return self.source[self.current];
+}
+
+fn addToken(self: *Scanner, allocator: Allocator, @"type": TokenType, literal: ?Literal) !void {
+    const text = self.source[self.start..self.current];
+    try self.tokens.append(allocator, .init(@"type", text, literal, self.line));
+}

diff --git a/Token.zig b/Token.zig
new file mode 100644 (file)
index 0000000..bf988d8
--- /dev/null
+++ b/Token.zig
@@ -0,0 +1,26 @@
+const std = @import("std");
+const TokenType = @import("token-type.zig").TokenType;
+const Token = @This();
+
+type: TokenType,
+lexeme: []const u8,
+literal: ?Literal,
+line: u32,
+
+pub const Literal = union {
+    string: []const u8,
+    number: f64,
+};
+
+pub fn init(@"type": TokenType, lexeme: []const u8, literal: ?Literal, line: u32) Token {
+    return .{
+        .type = @"type",
+        .lexeme = lexeme,
+        .literal = literal,
+        .line = line,
+    };
+}
+
+pub fn format(self: Token, writer: *std.io.Writer) !void {
+    try writer.print("{} {s} {any}", .{ self.type, self.lexeme, self.literal });
+}

diff --git a/main.zig b/main.zig
deleted file mode 100644 (file)
index f0966fc..0000000
--- a/main.zig
+++ /dev/null
@@ -1,7 +0,0 @@
-const std = @import("std");
-
-pub fn main() !void {
-    var stdout_writer = std.fs.File.stdout().writer(&.{});
-    const stdout = &stdout_writer.interface;
-    try stdout.writeAll("Hello, Zlox!\n");
-}

diff --git a/token-type.zig b/token-type.zig
new file mode 100644 (file)
index 0000000..8972dfd
--- /dev/null
+++ b/token-type.zig
@@ -0,0 +1,49 @@
+pub const TokenType = enum {
+    // Single-character tokens.
+    left_paren,
+    right_paren,
+    left_brace,
+    right_brace,
+    comma,
+    dot,
+    minus,
+    plus,
+    semicolon,
+    slash,
+    star,
+
+    // One or two character tokens.
+    bang,
+    bang_equal,
+    equal,
+    equal_equal,
+    greater,
+    greater_equal,
+    less,
+    less_equal,
+
+    // Literals.
+    identifier,
+    string,
+    number,
+
+    // Keywords.
+    @"and",
+    class,
+    @"else",
+    false,
+    fun,
+    @"for",
+    @"if",
+    nil,
+    @"or",
+    print,
+    @"return",
+    super,
+    this,
+    true,
+    @"var",
+    @"while",
+
+    eof,
+};