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
|
const std = @import("std");
const estd = @import("estd");
const Cursor = estd.cursor.Cursor;
const Parser = estd.parser.Parser;
const Context = estd.parser.Context;
const Literal = estd.parser.common.Literal;
const ParseFn = estd.parser.ParseFn;
const Keyword = enum {
if_statement,
other
};
const String = struct {
};
const Token = union(enum) {
openparenthesis: void,
closeparenthesis: void,
openscope: void,
closescope: void,
backslash: void,
pipe: void,
semicolon: void,
logical_and: void,
logical_or: void,
assign: void,
keyword: Keyword,
string: String,
};
pub fn parse_string(ctx: *Context(u8)) !Token {
const snapshot = ctx.cursor.snapshot();
errdefer ctx.cursor.rollback(snapshot);
const first_char = (try ctx.cursor.consume(1))[0];
if (first_char == ' ') {
return error.NotAString;
}
if (first_char == '"') {
while (ctx.cursor.consume(1) catch null) |c| {
if (c[0] == '\"') {
return Token.string;
} else if (c[0] == '{') {
while (ctx.cursor.consume(1) catch null) |inner| {
if (inner[0] == '}') {
break;
}
} else {
return error.UnterminatedString;
}
}
} else {
return error.UnterminatedString;
}
} else if (first_char == '\'') {
while (ctx.cursor.consume(1) catch null) |c| {
if (c[0] == '\'') {
return Token.string;
}
} else {
return error.UnterminatedString;
}
}
while (ctx.cursor.consume(1) catch null) |c| {
if (c[0] == ' ') {
return Token.string;
} else if (c[0] == '{') {
while (ctx.cursor.consume(1) catch null) |inner| {
if (inner[0] == '}') {
break;
}
} else {
return error.UnterminatedString;
}
}
} else {
return error.UnterminatedString;
}
}
const unterminated_keyword = Parser(u8, Keyword, keyword_literal("if", Keyword.if_statement));
fn keyword(ctx: *Context(u8)) !Token {
const snapshot = ctx.cursor.snapshot();
errdefer ctx.cursor.rollback(snapshot);
const token = try unterminated_keyword.parse(ctx);
const next_char = (try ctx.cursor.peek(1))[0];
switch (next_char) {
'(', ')', '{', '}', '\\', '&', '|', ';', '=', ' ' => return .{ .keyword = token },
else => return error.UnterminatedKeyword,
}
}
const literal = Literal(u8, Token);
const keyword_literal = Literal(u8, Keyword);
const skip_literal = Literal(u8, void);
const Tokenizer = Parser(u8, Token, literal("(", Token.openparenthesis))
.or_else(literal(")", Token.closeparenthesis))
.or_else(literal("{", Token.openscope))
.or_else(literal("}", Token.closescope))
.or_else(literal("\\", Token.backslash))
.or_else(literal("&&", Token.logical_and))
.or_else(literal("||", Token.logical_or))
.or_else(literal("|", Token.pipe))
.or_else(literal(";", Token.semicolon))
.or_else(literal("=", Token.assign))
.or_else(keyword)
.or_else(parse_string)
.and_skip(Parser(u8, void, skip_literal(" ", {})).zero_or_more().parse)
.zero_or_more()
.then_skip(Parser(u8, void, skip_literal(" ", {})).zero_or_more().parse)
.end();
pub fn main() void {
std.debug.print("Hello, World!\n", .{});
}
test "tokenizer" {
const example = " | 'asdf' ( || \"hello\" ) or_something &&{ =}\\ ; if ";
var ctx = Context(u8) {
.cursor = Cursor(u8).init(example),
.allocator = std.testing.allocator,
};
const tokens = try Tokenizer.parse(&ctx);
defer tokens.deinit();
try std.testing.expectEqualSlices(
Token,
&[_]Token {
.pipe,
.string,
.openparenthesis,
.logical_or,
.string,
.closeparenthesis,
.string,
.logical_and,
.openscope,
.assign,
.closescope,
.backslash,
.semicolon,
.{ .keyword = Keyword.if_statement }
},
tokens.items
);
}
|
