Match RegularExpression and ExtractEmailAdresses behaviour

This commit is contained in:
C85297 2026-04-13 08:42:06 +01:00
parent 9ae588d106
commit 7be7cfad05
No known key found for this signature in database
3 changed files with 9 additions and 4 deletions

View File

@ -45,6 +45,11 @@ export function search(input, searchRegex, removeRegex=null, sortBy=null, unique
return results;
}
/**
* Email regular expression
*/
const EMAIL_REGEX = /(?:[\u00A0-\uD7FF\uE000-\uFFFFa-z0-9!#$%&'*+/=?^_`{|}~-]+(?:\.[\u00A0-\uD7FF\uE000-\uFFFFa-z0-9!#$%&'*+/=?^_`{|}~-]+)*|"(?:[\x01-\x08\x0b\x0c\x0e-\x1f\x21\x23-\x5b\x5d-\x7f]|\\[\x01-\x09\x0b\x0c\x0e-\x7f])*")@(?:(?:[\u00A0-\uD7FF\uE000-\uFFFFa-z0-9](?:[\u00A0-\uD7FF\uE000-\uFFFFa-z0-9-]*[\u00A0-\uD7FF\uE000-\uFFFFa-z0-9])?\.)+[\u00A0-\uD7FF\uE000-\uFFFFa-z0-9](?:[\u00A0-\uD7FF\uE000-\uFFFFa-z0-9-]*[\u00A0-\uD7FF\uE000-\uFFFFa-z0-9])?|\[(?:(?:(2(5[0-5]|[0-4][0-9])|1[0-9][0-9]|[1-9]?[0-9]))\.){3}(?:(2(5[0-5]|[0-4][0-9])|1[0-9][0-9]|[1-9]?[0-9]))\])/ig;
/**
* URL regular expression

View File

@ -5,7 +5,7 @@
*/
import Operation from "../Operation.mjs";
import { search } from "../lib/Extract.mjs";
import { EMAIL_REGEX, search } from "../lib/Extract.mjs";
import { caseInsensitiveSort } from "../lib/Sort.mjs";
/**
@ -50,8 +50,7 @@ class ExtractEmailAddresses extends Operation {
*/
run(input, args) {
const [displayTotal, sort, unique] = args,
// email regex from: https://www.regextester.com/98066
regex = /(?:[\u00A0-\uD7FF\uE000-\uFFFFa-z0-9!#$%&'*+/=?^_`{|}~-]+(?:\.[\u00A0-\uD7FF\uE000-\uFFFFa-z0-9!#$%&'*+/=?^_`{|}~-]+)*|"(?:[\x01-\x08\x0b\x0c\x0e-\x1f\x21\x23-\x5b\x5d-\x7f]|\\[\x01-\x09\x0b\x0c\x0e-\x7f])*")@(?:(?:[\u00A0-\uD7FF\uE000-\uFFFFa-z0-9](?:[\u00A0-\uD7FF\uE000-\uFFFFa-z0-9-]*[\u00A0-\uD7FF\uE000-\uFFFFa-z0-9])?\.)+[\u00A0-\uD7FF\uE000-\uFFFFa-z0-9](?:[\u00A0-\uD7FF\uE000-\uFFFFa-z0-9-]*[\u00A0-\uD7FF\uE000-\uFFFFa-z0-9])?|\[(?:(?:(2(5[0-5]|[0-4][0-9])|1[0-9][0-9]|[1-9]?[0-9]))\.){3}(?:(2(5[0-5]|[0-4][0-9])|1[0-9][0-9]|[1-9]?[0-9]))\])/ig;
regex = EMAIL_REGEX;
const results = search(
input,

View File

@ -7,6 +7,7 @@
import XRegExp from "xregexp";
import Operation from "../Operation.mjs";
import Utils from "../Utils.mjs";
import { EMAIL_REGEX } from "../lib/Extract.mjs";
import OperationError from "../errors/OperationError.mjs";
/**
@ -45,7 +46,7 @@ class RegularExpression extends Operation {
},
{
name: "Email address",
value: "(?:[\u00A0-\uD7FF\uE000-\uFFFFa-z0-9!#$%&'*+/=?^_`{|}~-]+(?:\.[\u00A0-\uD7FF\uE000-\uFFFFa-z0-9!#$%&'*+/=?^_`{|}~-]+)*|"(?:[\x01-\x08\x0b\x0c\x0e-\x1f\x21\x23-\x5b\x5d-\x7f]|\\[\x01-\x09\x0b\x0c\x0e-\x7f])*")@(?:(?:[\u00A0-\uD7FF\uE000-\uFFFFa-z0-9](?:[\u00A0-\uD7FF\uE000-\uFFFFa-z0-9-]*[\u00A0-\uD7FF\uE000-\uFFFFa-z0-9])?\.)+[\u00A0-\uD7FF\uE000-\uFFFFa-z0-9](?:[\u00A0-\uD7FF\uE000-\uFFFFa-z0-9-]*[\u00A0-\uD7FF\uE000-\uFFFFa-z0-9])?|\[(?:(?:(2(5[0-5]|[0-4][0-9])|1[0-9][0-9]|[1-9]?[0-9]))\.){3}(?:(2(5[0-5]|[0-4][0-9])|1[0-9][0-9]|[1-9]?[0-9]))\])"
value: EMAIL_REGEX.source // We use a different regex library, so just take the source regex string here
},
{
name: "URL",