1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
|
const std = @import("std");
const root = @import("root.zig");
const Lexer = root.Lexer;
const Token = root.Token;
pub const Literal = union(enum) {
// NOTE: currently only decimal literals are tokenized
numeric: void,
bigint: void,
string: void,
template: enum {
whole,
start,
middle,
end,
},
const digits = "_0123456789abcdef";
pub inline fn tokenize(comptime lexer: *Lexer) Lexer.Error!void {
comptime {
errdefer lexer.revert();
var token = lexer.start(.{ .literal = undefined });
const regex_possible = lexer.context.regex_possible;
lexer.context.regex_possible = false;
switch (try lexer.consume()) {
'0'...'9', '.' => |c| {
const base = if (c != '0') 10 else switch (lexer.peekChar() orelse 0) {
'x' => 16,
'o' => 8,
'b' => 2,
else => 10,
};
if (base != 10) lexer.skip() catch unreachable;
{
const index = std.mem.findNone(
u8,
lexer.buffer,
digits[0 .. base + 1],
) orelse lexer.buffer.len;
try lexer.skipTo(index);
if (index == 0 and base != 10) return Lexer.Error.UnexpectedToken;
}
if (base == 10 and lexer.peekChar() == '.') {
try lexer.skip();
const index = std.mem.findNone(
u8,
lexer.buffer,
digits[0 .. base + 1],
) orelse lexer.buffer.len;
try lexer.skipTo(index);
}
if (lexer.peekChar() == 'n') {
lexer.skip() catch unreachable;
token.kind.literal = .bigint;
} else {
token.kind.literal = .numeric;
}
},
'\'', '"' => |quote| {
token.kind.literal = .string;
while (true) {
switch (try lexer.consume()) {
quote => break,
'\\' => try lexer.skip(),
else => {},
}
}
},
'`' => {
token.kind.literal = .{ .template = undefined };
while (true) {
switch (try lexer.consume()) {
'`' => {
token.kind.literal.template = .whole;
break;
},
'\\' => try lexer.skip(),
'$' => if (lexer.peekChar() == '{') {
lexer.skip() catch unreachable;
lexer.context.template_nesting += 1;
token.kind.literal.template = .start;
lexer.context.regex_possible = true;
break;
},
else => {},
}
}
},
'}' => if (lexer.context.template_nesting > 0) {
lexer.context.template_nesting -= 1;
token.kind.literal = .{ .template = undefined };
while (true) {
switch (try lexer.consume()) {
'`' => {
token.kind.literal.template = .end;
break;
},
'\\' => try lexer.skip(),
'$' => if (lexer.peekChar() == '{') {
lexer.skip() catch unreachable;
lexer.context.template_nesting += 1;
token.kind.literal.template = .middle;
lexer.context.regex_possible = true;
break;
},
else => {},
}
}
} else return Lexer.Error.UnexpectedToken,
'/' => if (regex_possible) {
while (true) {
switch (try lexer.consume()) {
'/' => break,
'\\' => try lexer.skip(),
'\n' => return Lexer.Error.UnexpectedToken,
else => {},
}
}
} else return Lexer.Error.UnexpectedToken,
else => return Lexer.Error.UnexpectedToken,
}
lexer.commit(token);
}
}
};
test "numeric" {
const Simple = struct {
pub fn run(comptime buffer: []const u8, n: usize) !void {
comptime var lexer: Lexer = .init(buffer);
try Literal.tokenize(&lexer);
try std.testing.expectEqual(1, lexer.tokens.len);
try std.testing.expectEqual(n, lexer.tokens[0].slice.len);
}
};
try Simple.run("1234", 4);
try Simple.run("1.234", 5);
try Simple.run("1_2_3_4", 7);
try Simple.run("0b101011", 8);
try Simple.run("0xabcf01", 8);
try Simple.run("0o731734", 8);
try Simple.run("0o731734n", 9);
}
test "string" {
const Simple = struct {
pub fn run(comptime buffer: []const u8, n: usize) !void {
comptime var lexer: Lexer = .init(buffer);
try Literal.tokenize(&lexer);
try std.testing.expectEqual(1, lexer.tokens.len);
try std.testing.expectEqual(n, lexer.tokens[0].slice.len);
}
};
try Simple.run("'hello'", 7);
try Simple.run("\"hello\"", 7);
try std.testing.expectError(
Lexer.Error.EndOfBuffer,
Simple.run("'hello", 0),
);
}
test "regex" {
const Simple = struct {
pub fn run(comptime buffer: []const u8, n: usize) !void {
comptime var lexer: Lexer = .init(buffer);
try Literal.tokenize(&lexer);
try std.testing.expectEqual(1, lexer.tokens.len);
try std.testing.expectEqual(n, lexer.tokens[0].slice.len);
}
};
try Simple.run("/hello/", 7);
try Simple.run("/some string\\/ here/", 20);
}
|
