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
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
use std::cmp::PartialOrd;
use std::io::Read;
use lazy_static::lazy_static;
use regex::Regex;
lazy_static! {
static ref BASIC_TOKEN_RE: Regex = Regex::new(
&r#"(?mx)
(?P<comment>
//.*?$ |
/\*.*?\*/) |
(?P<whitespace>
\s+) |
(?P<string>
'([^'\\]*(?:\\.[^'\\]*)*)' |
"([^"\\]*(?:\\.[^"\\]*)*)" |
`([^`\\]*(?:\\.[^`\\]*)*)`) |
(?P<regex_op>
\\/|/) |
(?P<keyword>(?:\b
async|
await|
break|
case|
catch|
class|
continue|
debugger|
default|
delete|
do|
else|
export|
extends|
finally|
for|
function|
if|
import|
instanceof|
in|
let|
new|
null|
return|
static|
super|
switch|
this|
throw|
true|
try|
typeof|
var|
void|
while|
with)\b) |
(?P<ident>
[\p{Lu}\p{Ll}\p{Lt}\p{Lm}\p{Lo}\p{Nl}$_]
[\p{Lu}\p{Ll}\p{Lt}\p{Lm}\p{Lo}\p{Nl}\p{Mn}\p{Mc}\p{Nd}\p{Pc}$_]*
)
"#
)
.unwrap();
}
lazy_static! {
static ref IDENT_RE: Regex = Regex::new(
&r#"(?mx)
[\p{Lu}\p{Ll}\p{Lt}\p{Lm}\p{Lo}\p{Nl}$_]
[\p{Lu}\p{Ll}\p{Lt}\p{Lm}\p{Lo}\p{Nl}\p{Mn}\p{Mc}\p{Nd}\p{Pc}$_]*
"#
)
.unwrap();
}
fn partial_clamp<T: PartialOrd>(l: T, u: T, v: T) -> T {
if v < l {
l
} else if v > u {
u
} else {
v
}
}
pub struct Analysis {
line_lengths: Vec<usize>,
ident_lengths: Vec<usize>,
space_count: usize,
non_space_count: usize,
}
pub fn analyze_str(code: &str) -> Analysis {
let mut line_lengths = vec![];
let mut ident_lengths = vec![];
let mut space = 0;
let mut not_space = 1;
let mut line_width = 0;
for c in code.chars() {
if c == '\t' {
space += 4;
} else if c.is_whitespace() {
space += 1;
} else {
not_space += 1;
}
if c == '\r' {
continue;
} else if c == '\n' {
if line_width > 0 {
line_lengths.push(line_width);
}
line_width = 0;
} else {
line_width += if c == '\t' { 4 } else { 1 };
}
}
if line_width > 0 {
line_lengths.push(line_width);
}
for m in BASIC_TOKEN_RE.find_iter(code) {
if IDENT_RE.is_match(m.as_str()) {
ident_lengths.push(m.end() - m.start());
}
}
line_lengths.sort();
ident_lengths.sort();
Analysis {
line_lengths: line_lengths,
ident_lengths: ident_lengths,
space_count: space,
non_space_count: not_space,
}
}
pub fn analyze<R: Read>(mut rdr: R) -> Analysis {
let mut rv = String::new();
rdr.read_to_string(&mut rv).unwrap();
analyze_str(&rv)
}
impl Analysis {
pub fn space_to_code_ratio(&self) -> f32 {
self.space_count as f32 / self.non_space_count as f32
}
pub fn median_ident_length(&self) -> usize {
if self.line_lengths.is_empty() {
0
} else {
*self
.ident_lengths
.get(self.ident_lengths.len() / 2)
.unwrap_or(&0)
}
}
pub fn longest_line(&self) -> usize {
if self.line_lengths.is_empty() {
0
} else {
*self
.line_lengths
.get(self.line_lengths.len() - 1)
.unwrap_or(&0)
}
}
pub fn shape(&self) -> f32 {
if self.line_lengths.is_empty() {
return 0.0;
}
let width = self.line_lengths[self.line_lengths.len() / 4 * 3];
let height = self.line_lengths.len();
height as f32 / width as f32
}
pub fn minified_probability(&self) -> f32 {
let p_space = (0.5 - partial_clamp(0.0, 0.5, self.space_to_code_ratio())) * 2.0;
let p_name = (5 - (partial_clamp(1, 6, self.median_ident_length()) - 1)) as f32 / 5.0;
let p_shape = (20.0 - partial_clamp(0.0, 20.0, self.shape())) / 20.0;
let p_line = partial_clamp(0, 1000, self.longest_line()) as f32 / 1000.0;
(p_space * 0.1 + p_name * 0.4 + p_shape * 0.2 + p_line * 0.3)
}
pub fn is_likely_minified(&self) -> bool {
self.minified_probability() > 0.5
}
}