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
|
use psl_types::List;
pub trait TldExtract {
fn extract<'a>(&self, host: &'a str) -> Option<Parts<'a>>;
}
impl<T: List> TldExtract for T {
fn extract<'a>(&self, host: &'a str) -> Option<Parts<'a>> {
let host_len = host.len();
let suffix_len = self.suffix(host.as_bytes())?.as_bytes().len();
let suffix = {
let offset = host_len - suffix_len;
&host[offset..]
};
let suffix_plus_dot = suffix_len + 1;
let (subdomain, domain) = if host_len > suffix_plus_dot {
match host.get(..host_len - suffix_plus_dot) {
Some(prefix) => match prefix.rfind('.') {
Some(offset) => (prefix.get(..offset), prefix.get(offset + 1..)),
None => (None, Some(prefix)),
},
None => (None, None),
}
} else {
(None, None)
};
Some(Parts {
suffix,
domain,
subdomain,
})
}
}
#[derive(Debug, Clone, Copy, Default, PartialEq, Eq, Hash)]
pub struct Parts<'a> {
pub suffix: &'a str,
pub domain: Option<&'a str>,
pub subdomain: Option<&'a str>,
}
// This example is inspired by https://github.com/john-kurkowski/tldextract
// Unlike that project, we don't try to parse URLs though. That can easily
// be done by using the `url` crate and feeding the output of `Url::domain`
// to `TldExtract::extract`.
fn main() {
use psl::List;
use std::env;
let domain = match env::args().nth(1) {
Some(name) => name,
None => {
eprintln!("Usage: {} <domain name>", env::args().nth(0).unwrap());
std::process::exit(1);
}
};
match List.extract(&domain) {
Some(info) => println!(
"{} {} {}",
info.subdomain.unwrap_or("(None)"),
info.domain.unwrap_or("(None)"),
info.suffix
),
None => eprintln!("`{}` is not domain name", domain),
}
}
|
