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
use regex::{Captures, Regex};
fn condense_whitespace(source: &str) -> String {
let lower_source = source.to_lowercase();
if lower_source.find("<textarea").is_none() && lower_source.find("<pre").is_none() {
let re = Regex::new(r">\s+<").unwrap();
let source = re.replace_all(source, "> <").into_owned();
let re = Regex::new(r"\s{2,}|[\r\n]").unwrap();
re.replace_all(&source, " ").into_owned()
} else {
source.trim().to_owned()
}
}
fn condense(source: &str) -> String {
let re = Regex::new(r"<(style|script)[\w|\s].*?>").unwrap();
re.replace_all(source, |caps: &Captures| {
format!("<{}>", &caps[1])
}).into_owned()
}
fn clean_unneeded_tags(source: &str) -> String {
let useless_tags = ["</area>", "</base>", "<body>", "</body>", "</br>",
"</col>", "</colgroup>", "</dd>", "</dt>", "<head>",
"</head>", "</hr>", "<html>", "</html>", "</img>",
"</input>", "</li>", "</link>", "</meta>", "</option>",
"</param>", "<tbody>", "</tbody>", "</td>", "</tfoot>",
"</th>", "</thead>", "</tr>", "</basefont>",
"</isindex>", "</param>"];
let mut res = source.to_owned();
for useless_tag in &useless_tags {
res = res.replace(useless_tag, "");
}
res
}
fn remove_comments(source: &str) -> String {
let re = Regex::new("<!--(.|\n)*?-->").unwrap();
re.replace_all(source, " ").into_owned()
}
fn unquote_attributes(source: &str) -> String {
let any_tag = Regex::new(r"<\w.*?>").unwrap();
let extra_spaces = Regex::new(r" \s+|\s +").unwrap();
let between_words = Regex::new(r"\w\s+\w").unwrap();
let spaces_before_close = Regex::new(r##""\s+>"##).unwrap();
let spaces_before_close2 = Regex::new(r"'\s+>").unwrap();
let extra_spaces2 = Regex::new(r##""\s\s+\w+="|'\s\s+\w+='|"\s\s+\w+=|'\s\s+\w+="##).unwrap();
let extra_spaces3 = Regex::new(r"\d\s+>").unwrap();
let quotes_in_tag = Regex::new(r##"([a-zA-Z]+)="([a-zA-Z0-9-_\.]+)""##).unwrap();
any_tag.replace_all(source, |caps: &Captures| {
let cap = format!("{}", &caps[0]);
if cap.starts_with("<!") || cap.find("</").is_some() {
cap
} else {
let tag = spaces_before_close.replace_all(&cap, "\">").into_owned();
let mut tag = spaces_before_close2.replace_all(&tag, "'>").into_owned();
let tag_c = tag.clone();
let space1_matches: Vec<_> = between_words.find_iter(&tag_c).collect();
let space6_matches: Vec<_> = extra_spaces3.find_iter(&tag_c).collect();
let mut pos = 0;
loop {
let replacement = match (space1_matches.get(pos), space6_matches.get(pos)) {
(Some(a), Some(b)) => format!("{}{}", a.as_str(), b.as_str()),
(None, Some(b)) => format!("{}", b.as_str()),
(Some(a), None) => format!("{}", a.as_str()),
_ => break,
};
pos += 1;
tag = tag.replace(&replacement,
&extra_spaces.replace_all(&replacement, " ").into_owned());
}
let mut output = tag.clone();
for caps in extra_spaces2.find_iter(&tag) {
let c = caps.as_str().chars().next().unwrap_or('\0');
output = output.replace(caps.as_str(),
&format!("{} {}",
if c == '\0' { String::new() }
else { format!("{}", c) },
caps.as_str()[1..].trim_left()));
}
tag = quotes_in_tag.replace_all(&output, |caps: &Captures| {
match &caps[1] {
"width" | "height" => format!("{}={}", &caps[1], &caps[2]),
x => format!("{}=\"{}\"", x, &caps[2]),
}
}).into_owned();
if cap != tag {
tag
} else {
cap
}
}
}).trim()
.to_owned()
}
pub fn minify(source: &str) -> String {
let source = remove_comments(source);
let source = condense(&source);
let source = clean_unneeded_tags(&source);
let source = condense_whitespace(&source);
unquote_attributes(&source).trim().to_owned()
}
#[test]
fn html_minify_test() {
let source = r##"<head>
<title>Some huge title</title>
<link rel="stylesheet" type="text/css" href="something.css" >
<style type="text/css">
.some_class {
color: red;
}
</style>
</head>
<body>
<header>
<div>
<i> <b><a href="www.somewhere.com" class="some_class">Narnia</a> </b> </i>
<h1 style="width:100%;text-align:center;" >Big header</h1>
</div>
<!-- commeeeeeeeents !!! -->
</header>
<div id="some_id">
<!-- another comment
on
multi
lines -->
<div id="another_id" class="another_class" width="100">
<h2>A little sub title</h2>
<ul>
<li>A list!</li>
<li>Who doesn't like lists?</li>
<li height="12" class="fooool">Well, who cares...</li>
</ul>
</div>
</div>
<script type="text/javascript" >
console.log("foo");
</script>
</body>
"##;
let expected_result = "<title>Some huge title</title> <link rel=\"stylesheet\" \
type=\"text/css\" href=\"something.css\"> <style> .some_class \
{ color: red; } </style> <header> <div> <i> <b><a \
href=\"www.somewhere.com\" class=\"some_class\">Narnia</a> </b> </i> \
<h1 style=\"width:100%;text-align:center;\">Big header</h1> </div> \
</header> <div id=\"some_id\"> <div id=\"another_id\" \
class=\"another_class\" width=100> <h2>A little sub \
title</h2> <ul> <li>A list! <li>Who doesn't like lists? \
<li height=12 class=\"fooool\">Well, who cares... </ul> </div> \
</div> <script> console.log(\"foo\"); </script>";
assert_eq!(minify(source), expected_result);
}