From 7be7cfad05ea747c0fed358e238c5ea6303e328c Mon Sep 17 00:00:00 2001 From: C85297 <95289555+C85297@users.noreply.github.com> Date: Mon, 13 Apr 2026 08:42:06 +0100 Subject: [PATCH] Match RegularExpression and ExtractEmailAdresses behaviour --- src/core/lib/Extract.mjs | 5 +++++ src/core/operations/ExtractEmailAddresses.mjs | 5 ++--- src/core/operations/RegularExpression.mjs | 3 ++- 3 files changed, 9 insertions(+), 4 deletions(-) diff --git a/src/core/lib/Extract.mjs b/src/core/lib/Extract.mjs index 3de2dd6d..e415bfd3 100644 --- a/src/core/lib/Extract.mjs +++ b/src/core/lib/Extract.mjs @@ -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 diff --git a/src/core/operations/ExtractEmailAddresses.mjs b/src/core/operations/ExtractEmailAddresses.mjs index 34b838ab..fe368a12 100644 --- a/src/core/operations/ExtractEmailAddresses.mjs +++ b/src/core/operations/ExtractEmailAddresses.mjs @@ -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, diff --git a/src/core/operations/RegularExpression.mjs b/src/core/operations/RegularExpression.mjs index e0ecd7cc..c3ab5b1d 100644 --- a/src/core/operations/RegularExpression.mjs +++ b/src/core/operations/RegularExpression.mjs @@ -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",