Regular Expression operation email address regex: Support IPv4 domains (#2167)

Co-authored-by: GCHQDeveloper581 <63102987+GCHQDeveloper581@users.noreply.github.com>
This commit is contained in:
GCHQ Developer 85297 2026-04-13 13:04:33 +01:00 committed by GitHub
parent f646065c36
commit 535838146c
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
6 changed files with 123 additions and 16 deletions

View File

@ -45,6 +45,11 @@ export function search(input, searchRegex, removeRegex=null, sortBy=null, unique
return results;
}
/**
* Email regular expression
*/
export 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-\\uFFFF-a-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}\\])"
value: EMAIL_REGEX.source // We use a different regex library, so just take the source regex string here
},
{
name: "URL",

View File

@ -143,6 +143,7 @@ import "./tests/Rabbit.mjs";
import "./tests/RAKE.mjs";
import "./tests/Regex.mjs";
import "./tests/Register.mjs";
import "./tests/RegularExpression.mjs";
import "./tests/RisonEncodeDecode.mjs";
import "./tests/Rotate.mjs";
import "./tests/RSA.mjs";

View File

@ -11,44 +11,70 @@ TestRegister.addTests([
{
name: "Extract email address",
input: "email@example.com\nfirstname.lastname@example.com\nemail@subdomain.example.com\nfirstname+lastname@example.com\n1234567890@example.com\nemail@example-one.com\n_______@example.com email@example.name\nemail@example.museum email@example.co.jp firstname-lastname@example.com",
expectedOutput: "email@example.com\nfirstname.lastname@example.com\nemail@subdomain.example.com\nfirstname+lastname@example.com\n1234567890@example.com\nemail@example-one.com\n_______@example.com\nemail@example.name\nemail@example.museum\nemail@example.co.jp\nfirstname-lastname@example.com",
expectedOutput:
"email@example.com\nfirstname.lastname@example.com\nemail@subdomain.example.com\nfirstname+lastname@example.com\n1234567890@example.com\nemail@example-one.com\n_______@example.com\nemail@example.name\nemail@example.museum\nemail@example.co.jp\nfirstname-lastname@example.com",
recipeConfig: [
{
"op": "Extract email addresses",
"args": [false]
op: "Extract email addresses",
args: [false],
},
],
},
{
name: "Extract email address - Display total",
input: "email@example.com\nfirstname.lastname@example.com\nemail@subdomain.example.com\nfirstname+lastname@example.com\n1234567890@example.com\nemail@example-one.com\n_______@example.com email@example.name\nemail@example.museum email@example.co.jp firstname-lastname@example.com",
expectedOutput: "Total found: 11\n\nemail@example.com\nfirstname.lastname@example.com\nemail@subdomain.example.com\nfirstname+lastname@example.com\n1234567890@example.com\nemail@example-one.com\n_______@example.com\nemail@example.name\nemail@example.museum\nemail@example.co.jp\nfirstname-lastname@example.com",
expectedOutput:
"Total found: 11\n\nemail@example.com\nfirstname.lastname@example.com\nemail@subdomain.example.com\nfirstname+lastname@example.com\n1234567890@example.com\nemail@example-one.com\n_______@example.com\nemail@example.name\nemail@example.museum\nemail@example.co.jp\nfirstname-lastname@example.com",
recipeConfig: [
{
"op": "Extract email addresses",
"args": [true]
op: "Extract email addresses",
args: [true],
},
],
},
{
name: "Extract email address (Internationalized)",
input: "\u4f0a\u662d\u5091@\u90f5\u4ef6.\u5546\u52d9 \u093e\u092e@\u092e\u094b\u0939\u0928.\u0908\u0928\u094d\u092b\u094b\n\u044e\u0437\u0435\u0440@\u0435\u043a\u0437\u0430\u043c\u043f\u043b.\u043a\u043e\u043c \u03b8\u03c3\u03b5\u03c1@\u03b5\u03c7\u03b1\u03bc\u03c0\u03bb\u03b5.\u03c8\u03bf\u03bc Jos\u1ec5Silv\u1ec5@googl\u1ec5.com\nJos\u1ec5Silv\u1ec5@google.com and Jos\u1ec5Silva@google.com\nFoO@BaR.CoM, john@192.168.10.100\ng\xf3mez@junk.br and Abc.123@example.com.\nuser+mailbox/department=shipping@example.com\n\u7528\u6237@\u4f8b\u5b50.\u5e7f\u544a\n\u0909\u092a\u092f\u094b\u0917\u0915\u0930\u094d\u0924\u093e@\u0909\u0926\u093e\u0939\u0930\u0923.\u0915\u0949\u092e\n\u044e\u0437\u0435\u0440@\u0435\u043a\u0437\u0430\u043c\u043f\u043b.\u043a\u043e\u043c\n\u03b8\u03c3\u03b5\u03c1@\u03b5\u03c7\u03b1\u03bc\u03c0\u03bb\u03b5.\u03c8\u03bf\u03bc\nD\xf6rte@S\xf6rensen.example.com\n\u0430\u0434\u0436\u0430\u0439@\u044d\u043a\u0437\u0430\u043c\u043f\u043b.\u0440\u0443\u0441\ntest@xn--bcher-kva.com",
expectedOutput: "\u4f0a\u662d\u5091@\u90f5\u4ef6.\u5546\u52d9\n\u093e\u092e@\u092e\u094b\u0939\u0928.\u0908\u0928\u094d\u092b\u094b\n\u044e\u0437\u0435\u0440@\u0435\u043a\u0437\u0430\u043c\u043f\u043b.\u043a\u043e\u043c\n\u03b8\u03c3\u03b5\u03c1@\u03b5\u03c7\u03b1\u03bc\u03c0\u03bb\u03b5.\u03c8\u03bf\u03bc\nJos\u1ec5Silv\u1ec5@googl\u1ec5.com\nJos\u1ec5Silv\u1ec5@google.com\nJos\u1ec5Silva@google.com\nFoO@BaR.CoM\njohn@192.168.10.100\ng\xf3mez@junk.br\nAbc.123@example.com\nuser+mailbox/department=shipping@example.com\n\u7528\u6237@\u4f8b\u5b50.\u5e7f\u544a\n\u0909\u092a\u092f\u094b\u0917\u0915\u0930\u094d\u0924\u093e@\u0909\u0926\u093e\u0939\u0930\u0923.\u0915\u0949\u092e\n\u044e\u0437\u0435\u0440@\u0435\u043a\u0437\u0430\u043c\u043f\u043b.\u043a\u043e\u043c\n\u03b8\u03c3\u03b5\u03c1@\u03b5\u03c7\u03b1\u03bc\u03c0\u03bb\u03b5.\u03c8\u03bf\u03bc\nD\xf6rte@S\xf6rensen.example.com\n\u0430\u0434\u0436\u0430\u0439@\u044d\u043a\u0437\u0430\u043c\u043f\u043b.\u0440\u0443\u0441\ntest@xn--bcher-kva.com",
expectedOutput:
"\u4f0a\u662d\u5091@\u90f5\u4ef6.\u5546\u52d9\n\u093e\u092e@\u092e\u094b\u0939\u0928.\u0908\u0928\u094d\u092b\u094b\n\u044e\u0437\u0435\u0440@\u0435\u043a\u0437\u0430\u043c\u043f\u043b.\u043a\u043e\u043c\n\u03b8\u03c3\u03b5\u03c1@\u03b5\u03c7\u03b1\u03bc\u03c0\u03bb\u03b5.\u03c8\u03bf\u03bc\nJos\u1ec5Silv\u1ec5@googl\u1ec5.com\nJos\u1ec5Silv\u1ec5@google.com\nJos\u1ec5Silva@google.com\nFoO@BaR.CoM\njohn@192.168.10.100\ng\xf3mez@junk.br\nAbc.123@example.com\nuser+mailbox/department=shipping@example.com\n\u7528\u6237@\u4f8b\u5b50.\u5e7f\u544a\n\u0909\u092a\u092f\u094b\u0917\u0915\u0930\u094d\u0924\u093e@\u0909\u0926\u093e\u0939\u0930\u0923.\u0915\u0949\u092e\n\u044e\u0437\u0435\u0440@\u0435\u043a\u0437\u0430\u043c\u043f\u043b.\u043a\u043e\u043c\n\u03b8\u03c3\u03b5\u03c1@\u03b5\u03c7\u03b1\u03bc\u03c0\u03bb\u03b5.\u03c8\u03bf\u03bc\nD\xf6rte@S\xf6rensen.example.com\n\u0430\u0434\u0436\u0430\u0439@\u044d\u043a\u0437\u0430\u043c\u043f\u043b.\u0440\u0443\u0441\ntest@xn--bcher-kva.com",
recipeConfig: [
{
"op": "Extract email addresses",
"args": [false]
op: "Extract email addresses",
args: [false],
},
],
},
{
name: "Extract email address - Display total (Internationalized)",
input: "\u4f0a\u662d\u5091@\u90f5\u4ef6.\u5546\u52d9 \u093e\u092e@\u092e\u094b\u0939\u0928.\u0908\u0928\u094d\u092b\u094b\n\u044e\u0437\u0435\u0440@\u0435\u043a\u0437\u0430\u043c\u043f\u043b.\u043a\u043e\u043c \u03b8\u03c3\u03b5\u03c1@\u03b5\u03c7\u03b1\u03bc\u03c0\u03bb\u03b5.\u03c8\u03bf\u03bc Jos\u1ec5Silv\u1ec5@googl\u1ec5.com\nJos\u1ec5Silv\u1ec5@google.com and Jos\u1ec5Silva@google.com\nFoO@BaR.CoM, john@192.168.10.100\ng\xf3mez@junk.br and Abc.123@example.com.\nuser+mailbox/department=shipping@example.com\n\u7528\u6237@\u4f8b\u5b50.\u5e7f\u544a\n\u0909\u092a\u092f\u094b\u0917\u0915\u0930\u094d\u0924\u093e@\u0909\u0926\u093e\u0939\u0930\u0923.\u0915\u0949\u092e\n\u044e\u0437\u0435\u0440@\u0435\u043a\u0437\u0430\u043c\u043f\u043b.\u043a\u043e\u043c\n\u03b8\u03c3\u03b5\u03c1@\u03b5\u03c7\u03b1\u03bc\u03c0\u03bb\u03b5.\u03c8\u03bf\u03bc\nD\xf6rte@S\xf6rensen.example.com\n\u0430\u0434\u0436\u0430\u0439@\u044d\u043a\u0437\u0430\u043c\u043f\u043b.\u0440\u0443\u0441\ntest@xn--bcher-kva.com",
expectedOutput: "Total found: 19\n\n\u4f0a\u662d\u5091@\u90f5\u4ef6.\u5546\u52d9\n\u093e\u092e@\u092e\u094b\u0939\u0928.\u0908\u0928\u094d\u092b\u094b\n\u044e\u0437\u0435\u0440@\u0435\u043a\u0437\u0430\u043c\u043f\u043b.\u043a\u043e\u043c\n\u03b8\u03c3\u03b5\u03c1@\u03b5\u03c7\u03b1\u03bc\u03c0\u03bb\u03b5.\u03c8\u03bf\u03bc\nJos\u1ec5Silv\u1ec5@googl\u1ec5.com\nJos\u1ec5Silv\u1ec5@google.com\nJos\u1ec5Silva@google.com\nFoO@BaR.CoM\njohn@192.168.10.100\ng\xf3mez@junk.br\nAbc.123@example.com\nuser+mailbox/department=shipping@example.com\n\u7528\u6237@\u4f8b\u5b50.\u5e7f\u544a\n\u0909\u092a\u092f\u094b\u0917\u0915\u0930\u094d\u0924\u093e@\u0909\u0926\u093e\u0939\u0930\u0923.\u0915\u0949\u092e\n\u044e\u0437\u0435\u0440@\u0435\u043a\u0437\u0430\u043c\u043f\u043b.\u043a\u043e\u043c\n\u03b8\u03c3\u03b5\u03c1@\u03b5\u03c7\u03b1\u03bc\u03c0\u03bb\u03b5.\u03c8\u03bf\u03bc\nD\xf6rte@S\xf6rensen.example.com\n\u0430\u0434\u0436\u0430\u0439@\u044d\u043a\u0437\u0430\u043c\u043f\u043b.\u0440\u0443\u0441\ntest@xn--bcher-kva.com",
expectedOutput:
"Total found: 19\n\n\u4f0a\u662d\u5091@\u90f5\u4ef6.\u5546\u52d9\n\u093e\u092e@\u092e\u094b\u0939\u0928.\u0908\u0928\u094d\u092b\u094b\n\u044e\u0437\u0435\u0440@\u0435\u043a\u0437\u0430\u043c\u043f\u043b.\u043a\u043e\u043c\n\u03b8\u03c3\u03b5\u03c1@\u03b5\u03c7\u03b1\u03bc\u03c0\u03bb\u03b5.\u03c8\u03bf\u03bc\nJos\u1ec5Silv\u1ec5@googl\u1ec5.com\nJos\u1ec5Silv\u1ec5@google.com\nJos\u1ec5Silva@google.com\nFoO@BaR.CoM\njohn@192.168.10.100\ng\xf3mez@junk.br\nAbc.123@example.com\nuser+mailbox/department=shipping@example.com\n\u7528\u6237@\u4f8b\u5b50.\u5e7f\u544a\n\u0909\u092a\u092f\u094b\u0917\u0915\u0930\u094d\u0924\u093e@\u0909\u0926\u093e\u0939\u0930\u0923.\u0915\u0949\u092e\n\u044e\u0437\u0435\u0440@\u0435\u043a\u0437\u0430\u043c\u043f\u043b.\u043a\u043e\u043c\n\u03b8\u03c3\u03b5\u03c1@\u03b5\u03c7\u03b1\u03bc\u03c0\u03bb\u03b5.\u03c8\u03bf\u03bc\nD\xf6rte@S\xf6rensen.example.com\n\u0430\u0434\u0436\u0430\u0439@\u044d\u043a\u0437\u0430\u043c\u043f\u043b.\u0440\u0443\u0441\ntest@xn--bcher-kva.com",
recipeConfig: [
{
"op": "Extract email addresses",
"args": [true]
op: "Extract email addresses",
args: [true],
},
],
},
{
name: "Extract email address - IP address",
input: "yaunwfkb\nexample@[127.0.0.1]\n091nvka",
expectedOutput: "example@[127.0.0.1]",
recipeConfig: [
{
op: "Extract email addresses",
args: [false],
},
],
},
{
name: "Extract email address - invalid IP address",
input: "yaunwfkb\nfalse_positive@[1.2.3.]\n091nvka",
expectedOutput: "",
recipeConfig: [
{
op: "Extract email addresses",
args: [false],
},
],
},

View File

@ -0,0 +1,75 @@
/**
* Regular Expression tests.
*
* @author C85297 [95289555+C85297@users.noreply.github.com]
* @copyright Crown Copyright 2017
* @license Apache-2.0
*/
import TestRegister from "../../lib/TestRegister.mjs";
import { EMAIL_REGEX } from "../../../src/core/lib/Extract.mjs";
TestRegister.addTests([
{
name: "Regular Expression - built in email regex - IP address",
input: "yaunwfkb\nexample@[127.0.0.1]\n091nvka",
expectedOutput: "example@[127.0.0.1]",
recipeConfig: [
{
op: "Regular expression",
args: [
"Email address",
EMAIL_REGEX.source,
true,
true,
false,
false,
false,
false,
"List matches",
],
},
],
},
{
name: "Regular Expression - built in email regex - invalid IP address",
input: "yaunwfkb\nfalse_positive@[1.2.3.]\n091nvka",
expectedOutput: "",
recipeConfig: [
{
op: "Regular expression",
args: [
"Email address",
EMAIL_REGEX.source,
true,
true,
false,
false,
false,
false,
"List matches",
],
},
],
},
{
name: "Regular Expression - built in email regex - IPv4 from #2318",
input: "user@[1.2.3.4]\ntest@[192.168.0.1]\nno-match@[1.2.3.]",
expectedOutput: "user@[1.2.3.4]\ntest@[192.168.0.1]",
recipeConfig: [
{
op: "Regular expression",
args: [
"Email address",
EMAIL_REGEX.source,
true,
true,
false,
false,
false,
false,
"List matches",
],
},
],
},
]);