Make email regex reasonable (#2157)

* Remove logging

* Clean up email testsg

* Add back 1char tld test

* Final tweaks to email regex

* Fix test

* Update test

Author: colinhacks

deno/lib/__tests__/string.test.ts

@@ -39,70 +39,97 @@ test("failing validations", () => {
 });
 
 test("email validations", () => {
-  const email = z.string().email();
-  email.parse("mojojojo@example.com");
-  expect(() => email.parse("asdf")).toThrow();
-  expect(() => email.parse("@lkjasdf.com")).toThrow();
-  expect(() => email.parse("asdf@sdf.")).toThrow();
-  expect(() => email.parse("asdf@asdf.com-")).toThrow();
-  expect(() => email.parse("asdf@-asdf.com")).toThrow();
-  expect(() => email.parse("asdf@-a(sdf.com")).toThrow();
-  expect(() => email.parse("asdf@-asdf.com(")).toThrow();
-  expect(() =>
-    email.parse("pawan.anand@%9y83&#$%R&#$%R&%#$R%%^^%5rw3ewe.d.d.aaaa.wef.co")
-  ).toThrow();
-});
-
-test("more email validations", () => {
   const validEmails = [
+    `email@domain.com`,
+    `firstname.lastname@domain.com`,
+    `email@subdomain.domain.com`,
+    `firstname+lastname@domain.com`,
+    `1234567890@domain.com`,
+    `email@domain-one.com`,
+    `_______@domain.com`,
+    `email@domain.name`,
+    `email@domain.co.jp`,
+    `firstname-lastname@domain.com`,
     `very.common@example.com`,
     `disposable.style.email.with+symbol@example.com`,
     `other.email-with-hyphen@example.com`,
     `fully-qualified-domain@example.com`,
     `user.name+tag+sorting@example.com`,
     `x@example.com`,
+    `mojojojo@asdf.example.com`,
     `example-indeed@strange-example.com`,
-    `test/test@test.com`,
     `example@s.example`,
-    `" "@example.org`,
-    `"john..doe"@example.org`,
-    `mailhost!username@example.org`,
-    `"very.(),:;<>[]\".VERY.\"very@\\ \"very\".unusual"@strange.example.com`,
-    `user%example.com@example.org`,
     `user-@example.org`,
-    `postmaster@[123.123.123.123]`,
     `user@my-example.com`,
     `a@b.cd`,
     `work+user@mail.com`,
+    `tom@test.te-st.com`,
+    `something@subdomain.domain-with-hyphens.tld`,
+    `francois@etu.inp-n7.fr`,
+  ];
+  const invalidEmails = [
+    // no "printable characters"
+    // `user%example.com@example.org`,
+    // `mailhost!username@example.org`,
+    // `test/test@test.com`,
+
+    // double @
+    `francois@@etu.inp-n7.fr`,
+    // do not support quotes
+    `"email"@domain.com`,
+    `"e asdf sadf ?<>ail"@domain.com`,
+    `" "@example.org`,
+    `"john..doe"@example.org`,
+    `"very.(),:;<>[]\".VERY.\"very@\\ \"very\".unusual"@strange.example.com`,
+
+    // do not support IPv4
+    `email@123.123.123.123`,
+    `email@[123.123.123.123]`,
+    `postmaster@123.123.123.123`,
     `user@[68.185.127.196]`,
     `ipv4@[85.129.96.247]`,
     `valid@[79.208.229.53]`,
     `valid@[255.255.255.255]`,
     `valid@[255.0.55.2]`,
     `valid@[255.0.55.2]`,
+
+    // do not support ipv6
     `hgrebert0@[IPv6:4dc8:ac7:ce79:8878:1290:6098:5c50:1f25]`,
     `bshapiro4@[IPv6:3669:c709:e981:4884:59a3:75d1:166b:9ae]`,
     `jsmith@[IPv6:2001:db8::1]`,
     `postmaster@[IPv6:2001:0db8:85a3:0000:0000:8a2e:0370:7334]`,
     `postmaster@[IPv6:2001:0db8:85a3:0000:0000:8a2e:0370:192.168.1.1]`,
-    `test@any.th1ng.com`,
-    `me@y.z.com`,
-    `me@y.z.co.jp`,
-    `example@subdomain.hyphenated-domain.com`,
-    `example@atlanta.k12.ga.us`,
-    `a.b@c.d`,
-  ];
-  const invalidEmails = [
+
+    // microsoft test cases
+    `plainaddress`,
+    `#@%^%#$@#$@#.com`,
+    `@domain.com`,
+    `Joe Smith &lt;email@domain.com&gt;`,
+    `email.domain.com`,
+    `email@domain@domain.com`,
+    `.email@domain.com`,
+    `email.@domain.com`,
+    `email..email@domain.com`,
+    `あいうえお@domain.com`,
+    `email@domain.com (Joe Smith)`,
+    `email@domain`,
+    `email@-domain.com`,
+    `email@111.222.333.44444`,
+    `email@domain..com`,
     `Abc.example.com`,
     `A@b@c@example.com`,
+    `colin..hacks@domain.com`,
     `a"b(c)d,e:f;g<h>i[j\k]l@example.com`,
     `just"not"right@example.com`,
     `this is"not\allowed@example.com`,
     `this\ still\"not\\allowed@example.com`,
+
+    // random
     `i_like_underscore@but_its_not_allowed_in_this_part.example.com`,
     `QA[icon]CHOCOLATE[icon]@test.com`,
     `invalid@-start.com`,
     `invalid@end.com-`,
+    `a.b@c.d`,
     `invalid@[1.1.1.-1]`,
     `invalid@[68.185.127.196.55]`,
     `temp@[192.168.1]`,
@@ -121,13 +148,16 @@ test("more email validations", () => {
     `test@.com`,
   ];
   const emailSchema = z.string().email();
+
   expect(
-    validEmails.every((email) => emailSchema.safeParse(email).success)
+    validEmails.every((email) => {
+      return emailSchema.safeParse(email).success;
+    })
   ).toBe(true);
   expect(
-    invalidEmails.every(
-      (email) => emailSchema.safeParse(email).success === false
-    )
+    invalidEmails.every((email) => {
+      return emailSchema.safeParse(email).success === false;
+    })
   ).toBe(true);
 });
 

deno/lib/types.ts

@@ -551,9 +551,17 @@ const uuidRegex =
 //old email regex
 // const emailRegex = /^(([^<>()[\].,;:\s@"]+(\.[^<>()[\].,;:\s@"]+)*)|(".+"))@((?!-)([^<>()[\].,;:\s@"]+\.)+[^<>()[\].,;:\s@"]{1,})[^-<>()[\].,;:\s@"]$/i;
 // eslint-disable-next-line
-
+// const emailRegex =
+//   /^(([^<>()[\]\\.,;:\s@\"]+(\.[^<>()[\]\\.,;:\s@\"]+)*)|(\".+\"))@((\[(((25[0-5])|(2[0-4][0-9])|(1[0-9]{2})|([0-9]{1,2}))\.){3}((25[0-5])|(2[0-4][0-9])|(1[0-9]{2})|([0-9]{1,2}))\])|(\[IPv6:(([a-f0-9]{1,4}:){7}|::([a-f0-9]{1,4}:){0,6}|([a-f0-9]{1,4}:){1}:([a-f0-9]{1,4}:){0,5}|([a-f0-9]{1,4}:){2}:([a-f0-9]{1,4}:){0,4}|([a-f0-9]{1,4}:){3}:([a-f0-9]{1,4}:){0,3}|([a-f0-9]{1,4}:){4}:([a-f0-9]{1,4}:){0,2}|([a-f0-9]{1,4}:){5}:([a-f0-9]{1,4}:){0,1})([a-f0-9]{1,4}|(((25[0-5])|(2[0-4][0-9])|(1[0-9]{2})|([0-9]{1,2}))\.){3}((25[0-5])|(2[0-4][0-9])|(1[0-9]{2})|([0-9]{1,2})))\])|([A-Za-z0-9]([A-Za-z0-9-]*[A-Za-z0-9])*(\.[A-Za-z]{2,})+))$/;
+// const emailRegex =
+//   /^[a-zA-Z0-9\.\!\#\$\%\&\'\*\+\/\=\?\^\_\`\{\|\}\~\-]+@[a-zA-Z0-9](?:[a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?(?:\.[a-zA-Z0-9](?:[a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?)*$/;
+// const emailRegex =
+//   /^(?:[a-z0-9!#$%&'*+/=?^_`{|}~-]+(?:\.[a-z0-9!#$%&'*+/=?^_`{|}~-]+)*|"(?:[\x01-\x08\x0b\x0c\x0e-\x1f\x21\x23-\x5b\x5d-\x7f]|\\[\x01-\x09\x0b\x0c\x0e-\x7f])*")@(?:(?:[a-z0-9](?:[a-z0-9-]*[a-z0-9])?\.)+[a-z0-9](?:[a-z0-9-]*[a-z0-9])?|\[(?:(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)\.){3}(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?|[a-z0-9-]*[a-z0-9]:(?:[\x01-\x08\x0b\x0c\x0e-\x1f\x21-\x5a\x53-\x7f]|\\[\x01-\x09\x0b\x0c\x0e-\x7f])+)\])$/i;
 const emailRegex =
-  /^(([^<>()[\]\\.,;:\s@\"]+(\.[^<>()[\]\\.,;:\s@\"]+)*)|(\".+\"))@((\[(((25[0-5])|(2[0-4][0-9])|(1[0-9]{2})|([0-9]{1,2}))\.){3}((25[0-5])|(2[0-4][0-9])|(1[0-9]{2})|([0-9]{1,2}))\])|(\[IPv6:(([a-f0-9]{1,4}:){7}|::([a-f0-9]{1,4}:){0,6}|([a-f0-9]{1,4}:){1}:([a-f0-9]{1,4}:){0,5}|([a-f0-9]{1,4}:){2}:([a-f0-9]{1,4}:){0,4}|([a-f0-9]{1,4}:){3}:([a-f0-9]{1,4}:){0,3}|([a-f0-9]{1,4}:){4}:([a-f0-9]{1,4}:){0,2}|([a-f0-9]{1,4}:){5}:([a-f0-9]{1,4}:){0,1})([a-f0-9]{1,4}|(((25[0-5])|(2[0-4][0-9])|(1[0-9]{2})|([0-9]{1,2}))\.){3}((25[0-5])|(2[0-4][0-9])|(1[0-9]{2})|([0-9]{1,2})))\])|([A-Za-z0-9]\.?([A-Za-z0-9-]+\.)*([A-Za-z0-9-])*[A-Za-z0-9]))$/;
+  /^([A-Z0-9_+-]+\.?)*[A-Z0-9_+-]@([A-Z0-9][A-Z0-9\-]*\.)+[A-Z]{2,}$/i;
+// const emailRegex =
+//   /^[a-z0-9.!#$%&’*+/=?^_`{|}~-]+@[a-z0-9-]+(?:\.[a-z0-9\-]+)*$/i;
+
 // from https://thekevinscott.com/emojis-in-javascript/#writing-a-regular-expression
 const emojiRegex = /^(\p{Extended_Pictographic}|\p{Emoji_Component})+$/u;
 
@@ -4174,7 +4182,10 @@ export class ZodPromise<T extends ZodTypeAny> extends ZodType<
 //////////////////////////////////////////////
 
 export type Refinement<T> = (arg: T, ctx: RefinementCtx) => any;
-export type SuperRefinement<T> = (arg: T, ctx: RefinementCtx) => void | Promise<void>;
+export type SuperRefinement<T> = (
+  arg: T,
+  ctx: RefinementCtx
+) => void | Promise<void>;
 
 export type RefinementEffect<T> = {
   type: "refinement";

playground.ts

@@ -1,2 +1,130 @@
 import { z } from "./src";
 z;
+
+const validEmails = [
+  `email@domain.com`,
+  `firstname.lastname@domain.com`,
+  `email@subdomain.domain.com`,
+  `firstname+lastname@domain.com`,
+  `1234567890@domain.com`,
+  `email@domain-one.com`,
+  `_______@domain.com`,
+  `email@domain.name`,
+  `email@domain.co.jp`,
+  `firstname-lastname@domain.com`,
+  `very.common@example.com`,
+  `disposable.style.email.with+symbol@example.com`,
+  `other.email-with-hyphen@example.com`,
+  `fully-qualified-domain@example.com`,
+  `user.name+tag+sorting@example.com`,
+  `x@example.com`,
+  `mojojojo@asdf.example.com`,
+  `example-indeed@strange-example.com`,
+  `example@s.example`,
+  `user-@example.org`,
+  `user@my-example.com`,
+  `a@b.cd`,
+  `work+user@mail.com`,
+  `tom@test.te-st.com`,
+  `something@subdomain.domain-with-hyphens.tld`,
+  `francois@etu.inp-n7.fr`,
+];
+const invalidEmails = [
+  // no "printable characters"
+  // `user%example.com@example.org`,
+  // `mailhost!username@example.org`,
+  // `test/test@test.com`,
+
+  // double @
+  `francois@@etu.inp-n7.fr`,
+
+  // do not support quotes
+  `"email"@domain.com`,
+  `"e asdf sadf ?<>ail"@domain.com`,
+  `" "@example.org`,
+  `"john..doe"@example.org`,
+  `"very.(),:;<>[]\".VERY.\"very@\\ \"very\".unusual"@strange.example.com`,
+
+  // do not support IPv4
+  `email@123.123.123.123`,
+  `email@[123.123.123.123]`,
+  `postmaster@123.123.123.123`,
+  `user@[68.185.127.196]`,
+  `ipv4@[85.129.96.247]`,
+  `valid@[79.208.229.53]`,
+  `valid@[255.255.255.255]`,
+  `valid@[255.0.55.2]`,
+  `valid@[255.0.55.2]`,
+
+  // do not support ipv6
+  `hgrebert0@[IPv6:4dc8:ac7:ce79:8878:1290:6098:5c50:1f25]`,
+  `bshapiro4@[IPv6:3669:c709:e981:4884:59a3:75d1:166b:9ae]`,
+  `jsmith@[IPv6:2001:db8::1]`,
+  `postmaster@[IPv6:2001:0db8:85a3:0000:0000:8a2e:0370:7334]`,
+  `postmaster@[IPv6:2001:0db8:85a3:0000:0000:8a2e:0370:192.168.1.1]`,
+
+  // microsoft test cases
+  `plainaddress`,
+  `#@%^%#$@#$@#.com`,
+  `@domain.com`,
+  `Joe Smith &lt;email@domain.com&gt;`,
+  `email.domain.com`,
+  `email@domain@domain.com`,
+  `.email@domain.com`,
+  `email.@domain.com`,
+  `email..email@domain.com`,
+  `あいうえお@domain.com`,
+  `email@domain.com (Joe Smith)`,
+  `email@domain`,
+  `email@-domain.com`,
+  `email@111.222.333.44444`,
+  `email@domain..com`,
+  `Abc.example.com`,
+  `A@b@c@example.com`,
+  `colin..hacks@domain.com`,
+  `a"b(c)d,e:f;g<h>i[j\k]l@example.com`,
+  `just"not"right@example.com`,
+  `this is"not\allowed@example.com`,
+  `this\ still\"not\\allowed@example.com`,
+
+  // random
+  `i_like_underscore@but_its_not_allowed_in_this_part.example.com`,
+  `QA[icon]CHOCOLATE[icon]@test.com`,
+  `invalid@-start.com`,
+  `invalid@end.com-`,
+  `a.b@c.d`,
+  `invalid@[1.1.1.-1]`,
+  `invalid@[68.185.127.196.55]`,
+  `temp@[192.168.1]`,
+  `temp@[9.18.122.]`,
+  `double..point@test.com`,
+  `asdad@test..com`,
+  `asdad@hghg...sd...au`,
+  `asdad@hghg........au`,
+  `invalid@[256.2.2.48]`,
+  `invalid@[256.2.2.48]`,
+  `invalid@[999.465.265.1]`,
+  `jkibbey4@[IPv6:82c4:19a8::70a9:2aac:557::ea69:d985:28d]`,
+  `mlivesay3@[9952:143f:b4df:2179:49a1:5e82:b92e:6b6]`,
+  `gbacher0@[IPv6:bc37:4d3f:5048:2e26:37cc:248e:df8e:2f7f:af]`,
+  `invalid@[IPv6:5348:4ed3:5d38:67fb:e9b:acd2:c13:192.168.256.1]`,
+];
+
+const emailSchema = z.string().email();
+console.log(
+  validEmails.every((email) => {
+    const val = emailSchema.safeParse(email).success;
+    if (!val) console.log(`fail`, email);
+    return val;
+  })
+);
+// for (const email of validEmails) {
+//   console.log("good", email);
+//   emailSchema.parse(email);
+// }
+for (const email of invalidEmails) {
+  try {
+    emailSchema.parse(email);
+    console.log(`PASS`, email);
+  } catch (_) {}
+}