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
use std::{fs::OpenOptions, io::Read};
use enums::Token;
pub mod lexer;
pub mod enums;
#[allow(unused_imports)]
#[warn(missing_docs)]
fn read_template(path: &str) -> Result<String, std::io::Error> {
let mut f = OpenOptions::new()
.read(true)
.write(false)
.open(path)
.unwrap();
let mut buffer: Vec<u8> = Vec::new();
let _ensual = match f.read_to_end(&mut buffer) {
Ok(_bit_count) => {}
Err(e) => {
panic!(
"let suc = match file_from.read_to_end(&mut buffer)^^^ERROR {:?}",
e
)
}
};
let page = std::str::from_utf8(&buffer).unwrap();
Ok(page.to_string())
}
pub fn lexer(path: &str) -> Vec<Token> {
let this = read_template(path);
if let Ok(page) = this {
let tmp = page.clone();
let mut token_container = vec![];
let tokenizer = lexer::lexer::lexer::Tokenizer::new(&tmp);
for token in tokenizer {
match Some(token) {
Some(t) => match t {
enums::Token::Undefined => break,
_ => {
token_container.push(t);
}
},
None => break,
}
}
return token_container;
}
vec![]
}
pub fn lexer_as_str(text: &str) -> Vec<Token> {
let mut token_container = vec![];
let tokenizer = lexer::lexer::lexer::Tokenizer::new(&text);
for token in tokenizer {
match Some(token) {
Some(t) => match t {
enums::Token::Undefined => break,
_ => {
token_container.push(t);
}
},
None => break,
}
}
return token_container;
}
#[cfg(test)]
mod unit_test {
use crate::{enums::Token, lexer::lexer::lexer::Tokenizer};
#[test]
fn test_basic_tokenizer() {
let mut tokenizer = Tokenizer::new("Water is healthy!");
assert_eq!(tokenizer.next().unwrap(), Token::Word("Water".to_string()));
assert_eq!(tokenizer.next().unwrap(), Token::WhiteSpace);
assert_eq!(tokenizer.next().unwrap(), Token::Word("is".to_string()));
assert_eq!(tokenizer.next().unwrap(), Token::WhiteSpace);
assert_eq!(
tokenizer.next().unwrap(),
Token::Word("healthy".to_string())
);
assert_eq!(tokenizer.next().unwrap(), Token::Not);
}
#[test]
fn test_punctuation_tokenizer() {
let mut tokenizer = Tokenizer::new("use super::*;");
assert_eq!(tokenizer.next().unwrap(), Token::KW_Use);
assert_eq!(tokenizer.next().unwrap(), Token::WhiteSpace);
assert_eq!(tokenizer.next().unwrap(), Token::KW_Super);
assert_eq!(tokenizer.next().unwrap(), Token::PathSep);
assert_eq!(tokenizer.next().unwrap(), Token::Star);
assert_eq!(tokenizer.next().unwrap(), Token::Semi);
}
#[test]
fn test_numeric_tokenizer() {
let mut tokenizer = Tokenizer::new("200 404.4 5_000");
assert_eq!(tokenizer.next().unwrap(), Token::Numeric("200".to_string()));
assert_eq!(tokenizer.next().unwrap(), Token::WhiteSpace);
assert_eq!(
tokenizer.next().unwrap(),
Token::Floating("404.4".to_string())
);
assert_eq!(tokenizer.next().unwrap(), Token::WhiteSpace);
assert_eq!(
tokenizer.next().unwrap(),
Token::Floating("5_000".to_string())
);
}
}