Update regex to support a wider variety of email addresses.

This commit is contained in:
Klaxon 2018-10-11 18:25:05 +10:00
parent a69063de9b
commit 3079059ce3

View File

@ -39,8 +39,8 @@ class ExtractEmailAddresses extends Operation {
*/
run(input, args) {
const displayTotal = args[0],
// email regex from: https://www.regular-expressions.info/email.html
regex = /\b[A-Z0-9._%+-]+@[A-Z0-9.-]+\.[A-Z]{2,}\b/ig;
// email regex from: https://www.regextester.com/98066
regex = /(?:[\u00A0-\uD7FF\uE000-\uFFFF-a-z0-9!#$%&'*+/=?^_`{|}~-]+(?:\.[\u00A0-\uD7FF\uE000-\uFFFF-a-z0-9!#$%&'*+/=?^_`{|}~-]+)*|"(?:[\x01-\x08\x0b\x0c\x0e-\x1f\x21\x23-\x5b\x5d-\x7f]|\\[\x01-\x09\x0b\x0c\x0e-\x7f])*")@(?:(?:[\u00A0-\uD7FF\uE000-\uFFFF-a-z0-9](?:[\u00A0-\uD7FF\uE000-\uFFFF-a-z0-9-]*[\u00A0-\uD7FF\uE000-\uFFFF-a-z0-9])?\.)+[\u00A0-\uD7FF\uE000-\uFFFF-a-z0-9](?:[\u00A0-\uD7FF\uE000-\uFFFF-a-z0-9-]*[\u00A0-\uD7FF\uE000-\uFFFF-a-z0-9])?|\[(?:(?:(2(5[0-5]|[0-4][0-9])|1[0-9][0-9]|[1-9]?[0-9]))\.){3}(?:(2(5[0-5]|[0-4][0-9])|1[0-9][0-9]|[1-9]?[0-9])|[a-z0-9-]*[a-z0-9]:(?:[\x01-\x08\x0b\x0c\x0e-\x1f\x21-\x5a\x53-\x7f]|\\[\x01-\x09\x0b\x0c\x0e-\x7f])+)\])/ig;
return search(input, regex, null, displayTotal);
}