Compare commits
No commits in common. "1bd463998cc9acdb60870cd2c274477f1fb8c712" and "882d123fe0c226f3040d510c96fb0e8832443fc1" have entirely different histories.
1bd463998c
...
882d123fe0
@ -24,13 +24,7 @@ Now in Zig!
|
|||||||
|
|
||||||
## v0.0.1
|
## v0.0.1
|
||||||
|
|
||||||
- [x] Lex numbers
|
- [x] Lex integers & floating point numbers
|
||||||
- [x] Lex identifier
|
|
||||||
- [x] Lex datatypes
|
|
||||||
- [x] Lex operators
|
|
||||||
- [x] Lex single line comments
|
|
||||||
- [x] Lex strings
|
|
||||||
- [x] Lex grouping signs
|
|
||||||
- [ ]
|
- [ ]
|
||||||
|
|
||||||
|
|
||||||
|
@ -101,7 +101,6 @@ pub fn build(b: *std.Build) void {
|
|||||||
"src/01_lexic/token.zig",
|
"src/01_lexic/token.zig",
|
||||||
"src/01_lexic/utils.zig",
|
"src/01_lexic/utils.zig",
|
||||||
"src/01_lexic/grouping.zig",
|
"src/01_lexic/grouping.zig",
|
||||||
"src/01_lexic/punctiation.zig",
|
|
||||||
};
|
};
|
||||||
for (files) |file| {
|
for (files) |file| {
|
||||||
const file_unit_test = b.addTest(.{
|
const file_unit_test = b.addTest(.{
|
||||||
|
@ -1,60 +0,0 @@
|
|||||||
const std = @import("std");
|
|
||||||
const assert = std.debug.assert;
|
|
||||||
const token = @import("./token.zig");
|
|
||||||
const utils = @import("./utils.zig");
|
|
||||||
|
|
||||||
const Token = token.Token;
|
|
||||||
const TokenType = token.TokenType;
|
|
||||||
const LexError = token.LexError;
|
|
||||||
const LexReturn = token.LexReturn;
|
|
||||||
|
|
||||||
pub fn lex(input: []const u8, start: usize) LexError!?LexReturn {
|
|
||||||
// there should be at least 1 char
|
|
||||||
assert(start < input.len);
|
|
||||||
|
|
||||||
const c = input[start];
|
|
||||||
const token_type = switch (c) {
|
|
||||||
',' => TokenType.Comma,
|
|
||||||
'\n' => TokenType.Newline,
|
|
||||||
else => {
|
|
||||||
return null;
|
|
||||||
},
|
|
||||||
};
|
|
||||||
|
|
||||||
return .{ Token.init(input[start .. start + 1], token_type, start), start + 1 };
|
|
||||||
}
|
|
||||||
|
|
||||||
test "shouldnt lex other things" {
|
|
||||||
const input = "322";
|
|
||||||
const output = try lex(input, 0);
|
|
||||||
|
|
||||||
try std.testing.expect(output == null);
|
|
||||||
}
|
|
||||||
|
|
||||||
test "should lex comma" {
|
|
||||||
const input = ",";
|
|
||||||
const output = try lex(input, 0);
|
|
||||||
|
|
||||||
if (output) |tuple| {
|
|
||||||
const t = tuple[0];
|
|
||||||
try std.testing.expectEqualDeep(",", t.value);
|
|
||||||
try std.testing.expectEqual(TokenType.Comma, t.token_type);
|
|
||||||
try std.testing.expectEqual(1, tuple[1]);
|
|
||||||
} else {
|
|
||||||
try std.testing.expect(false);
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
test "should lex new line" {
|
|
||||||
const input = "\n";
|
|
||||||
const output = try lex(input, 0);
|
|
||||||
|
|
||||||
if (output) |tuple| {
|
|
||||||
const t = tuple[0];
|
|
||||||
try std.testing.expectEqualDeep("\n", t.value);
|
|
||||||
try std.testing.expectEqual(TokenType.Newline, t.token_type);
|
|
||||||
try std.testing.expectEqual(1, tuple[1]);
|
|
||||||
} else {
|
|
||||||
try std.testing.expect(false);
|
|
||||||
}
|
|
||||||
}
|
|
@ -8,18 +8,16 @@ const operator = @import("./operator.zig");
|
|||||||
const comment = @import("./comment.zig");
|
const comment = @import("./comment.zig");
|
||||||
const string = @import("./string.zig");
|
const string = @import("./string.zig");
|
||||||
const grouping = @import("./grouping.zig");
|
const grouping = @import("./grouping.zig");
|
||||||
const punctuation = @import("./punctiation.zig");
|
|
||||||
|
|
||||||
const TokenType = token.TokenType;
|
const TokenType = token.TokenType;
|
||||||
const Token = token.Token;
|
const Token = token.Token;
|
||||||
|
|
||||||
// Creates an array list of tokens. The caller is responsible of
|
pub fn tokenize(input: []const u8, alloc: std.mem.Allocator) !void {
|
||||||
// calling `deinit` to free the array list
|
|
||||||
pub fn tokenize(input: []const u8, alloc: std.mem.Allocator) !std.ArrayList(Token) {
|
|
||||||
const input_len = input.len;
|
const input_len = input.len;
|
||||||
var current_pos: usize = 0;
|
var current_pos: usize = 0;
|
||||||
|
|
||||||
var tokens = std.ArrayList(Token).init(alloc);
|
var tokens = std.ArrayList(Token).init(alloc);
|
||||||
|
defer tokens.deinit();
|
||||||
|
|
||||||
while (current_pos < input_len) {
|
while (current_pos < input_len) {
|
||||||
const actual_next_pos = ignore_whitespace(input, current_pos);
|
const actual_next_pos = ignore_whitespace(input, current_pos);
|
||||||
@ -81,14 +79,6 @@ pub fn tokenize(input: []const u8, alloc: std.mem.Allocator) !std.ArrayList(Toke
|
|||||||
|
|
||||||
try tokens.append(t);
|
try tokens.append(t);
|
||||||
}
|
}
|
||||||
// lex punctuation
|
|
||||||
else if (try punctuation.lex(input, actual_next_pos)) |tuple| {
|
|
||||||
assert(tuple[1] > current_pos);
|
|
||||||
const t = tuple[0];
|
|
||||||
current_pos = tuple[1];
|
|
||||||
|
|
||||||
try tokens.append(t);
|
|
||||||
}
|
|
||||||
// nothing was matched. fail
|
// nothing was matched. fail
|
||||||
// TODO: instead of failing add an error, ignore all chars
|
// TODO: instead of failing add an error, ignore all chars
|
||||||
// until next whitespace, and continue lexing
|
// until next whitespace, and continue lexing
|
||||||
@ -99,8 +89,6 @@ pub fn tokenize(input: []const u8, alloc: std.mem.Allocator) !std.ArrayList(Toke
|
|||||||
break;
|
break;
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
return tokens;
|
|
||||||
}
|
}
|
||||||
|
|
||||||
/// Ignores all whitespace on `input` since `start`
|
/// Ignores all whitespace on `input` since `start`
|
||||||
@ -120,12 +108,10 @@ pub fn ignore_whitespace(input: []const u8, start: usize) usize {
|
|||||||
|
|
||||||
test "should insert 1 item" {
|
test "should insert 1 item" {
|
||||||
const input = "322";
|
const input = "322";
|
||||||
const arrl = try tokenize(input, std.testing.allocator);
|
try tokenize(input, std.testing.allocator);
|
||||||
arrl.deinit();
|
|
||||||
}
|
}
|
||||||
|
|
||||||
test "should insert 2 item" {
|
test "should insert 2 item" {
|
||||||
const input = "322 644";
|
const input = "322 644";
|
||||||
const arrl = try tokenize(input, std.testing.allocator);
|
try tokenize(input, std.testing.allocator);
|
||||||
arrl.deinit();
|
|
||||||
}
|
}
|
||||||
|
@ -16,7 +16,8 @@ pub const TokenType = enum {
|
|||||||
// punctiation that carries special meaning
|
// punctiation that carries special meaning
|
||||||
Comma,
|
Comma,
|
||||||
Newline,
|
Newline,
|
||||||
// Each keyword will have its own token
|
// Others
|
||||||
|
Keyword,
|
||||||
};
|
};
|
||||||
|
|
||||||
pub const Token = struct {
|
pub const Token = struct {
|
||||||
|
10
src/main.zig
10
src/main.zig
@ -27,8 +27,14 @@ fn repl() !void {
|
|||||||
var gpa = std.heap.GeneralPurposeAllocator(.{}){};
|
var gpa = std.heap.GeneralPurposeAllocator(.{}){};
|
||||||
const alloc = gpa.allocator();
|
const alloc = gpa.allocator();
|
||||||
|
|
||||||
const tokens = try lexic.tokenize(line, alloc);
|
try lexic.tokenize(line, alloc);
|
||||||
defer tokens.deinit();
|
|
||||||
|
|
||||||
try bw.flush();
|
try bw.flush();
|
||||||
}
|
}
|
||||||
|
|
||||||
|
test "simple test" {
|
||||||
|
var list = std.ArrayList(i32).init(std.testing.allocator);
|
||||||
|
defer list.deinit(); // try commenting this out and see if zig detects the memory leak!
|
||||||
|
try list.append(42);
|
||||||
|
try std.testing.expectEqual(@as(i32, 42), list.pop());
|
||||||
|
}
|
||||||
|
Loading…
Reference in New Issue
Block a user