-
Notifications
You must be signed in to change notification settings - Fork 682
/
findLinks.js
56 lines (46 loc) · 1.61 KB
/
findLinks.js
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
"use strict";
const URI = require("urijs");
// Known schemes to detect in a text. If a text contains `foo...bar://foo.com`,
// the parsed scheme should be `foo...bar` but if it contains
// `foo...http://foo.com`, we assume the scheme to extract will be `http`.
const commonSchemes = [
"http", "https",
"ftp", "sftp",
"smb", "file",
"irc", "ircs",
"svn", "git",
"steam", "mumble", "ts3server",
"svn+ssh", "ssh",
];
function findLinks(text) {
const result = [];
// URI.withinString() identifies URIs within text, e.g. to translate them to
// <a>-Tags.
// See https://medialize.github.io/URI.js/docs.html#static-withinString
// In our case, we store each URI encountered in a result array.
URI.withinString(text, function(url, start, end) {
// Extract the scheme of the URL detected, if there is one
const parsedScheme = URI(url).scheme().toLowerCase();
// Check if the scheme of the detected URL matches a common one above.
// In a URL like `foo..http://example.com`, the scheme would be `foo..http`,
// so we need to clean up the end of the scheme and filter out the rest.
const matchedScheme = commonSchemes.find((scheme) => parsedScheme.endsWith(scheme));
// A known scheme was found, extract the unknown part from the URL
if (matchedScheme) {
const prefix = parsedScheme.length - matchedScheme.length;
start += prefix;
url = url.slice(prefix);
}
// The URL matched but does not start with a scheme (`www.foo.com`), add it
if (!parsedScheme.length) {
url = "http://" + url;
}
result.push({
start: start,
end: end,
link: url
});
});
return result;
}
module.exports = findLinks;