From 16641ea5117ab13ae0d9ebe3418169a484a54d4a Mon Sep 17 00:00:00 2001
From: Juan Cruz Viotti <jv@jviotti.com>
Date: Thu, 16 Oct 2025 12:22:14 -0400
Subject: [PATCH] Implement a schema for e-mail addresses

---
 schemas/ietf/email/address.json    |  56 +++++
 tests/ietf/email/address.test.json | 366 +++++++++++++++++++++++++++++
 2 files changed, 422 insertions(+)
 create mode 100644 schemas/ietf/email/address.json
 create mode 100644 tests/ietf/email/address.test.json

diff --git a/schemas/ietf/email/address.json b/schemas/ietf/email/address.json
new file mode 100644
index 00000000..b1ee608c
--- /dev/null
+++ b/schemas/ietf/email/address.json
@@ -0,0 +1,56 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "title": "RFC 5322 Email Address (Addr-Spec)",
+  "description": "A specific Internet identifier that represents an e-mail box to which messages are delivered",
+  "$comment": "https://www.rfc-editor.org/rfc/rfc5322#section-3.4.1",
+  "examples": [
+    "simple@example.com",
+    "\"very.unusual.@.unusual.com\"@example.com",
+    "user@[IPv6:2001:db8::1]",
+    "(comment)john.smith@(comment)example.com(comment)",
+    "jo(comment)hn@example.com",
+    "user@[abc.def]"
+  ],
+  "x-license": "https://github.com/sourcemeta/std/blob/main/LICENSE",
+  "type": "string",
+  "anyOf": [
+    {
+      "$comment": "Unquoted (dot-atom) local-part with dot-atom domain — both allow inline single-level comments",
+      "pattern": "^(?:(?:[ \\t]|\\((?:[^()\\\\]|\\\\.)*\\))*)(?:[A-Za-z0-9!#$%&'*+\\/=?^_`{|}~-]+(?:(?:[ \\t]*\\((?:[^()\\\\]|\\\\.)*\\)[ \\t]*[A-Za-z0-9!#$%&'*+\\/=?^_`{|}~-]+)|(?:\\.[A-Za-z0-9!#$%&'*+\\/=?^_`{|}~-]+))*)(?:[ \\t]|\\((?:[^()\\\\]|\\\\.)*\\))*@(?:(?:[ \\t]|\\((?:[^()\\\\]|\\\\.)*\\))*(?:[A-Za-z0-9](?:[A-Za-z0-9-]{0,61}[A-Za-z0-9])?))(?:((?:[ \\t]|\\((?:[^()\\\\]|\\\\.)*\\))*\\.(?:[ \\t]|\\((?:[^()\\\\]|\\\\.)*\\))*(?:[A-Za-z0-9](?:[A-Za-z0-9-]{0,61}[A-Za-z0-9])?)))*(?:[ \\t]|\\((?:[^()\\\\]|\\\\.)*\\))*$"
+    },
+    {
+      "$comment": "Quoted local-part (with escapes) + dot-atom domain. Comments allowed around the quoted string and around domain labels",
+      "pattern": "^(?:[ \\t]|\\((?:[^()\\\\]|\\\\.)*\\))*(?:\"(?:[^\"\\\\\\r]|\\\\.)*\")(?:[ \\t]|\\((?:[^()\\\\]|\\\\.)*\\))*@(?:(?:[ \\t]|\\((?:[^()\\\\]|\\\\.)*\\))*(?:[A-Za-z0-9](?:[A-Za-z0-9-]{0,61}[A-Za-z0-9])?))(?:((?:[ \\t]|\\((?:[^()\\\\]|\\\\.)*\\))*\\.(?:[ \\t]|\\((?:[^()\\\\]|\\\\.)*\\))*(?:[A-Za-z0-9](?:[A-Za-z0-9-]{0,61}[A-Za-z0-9])?)))*(?:[ \\t]|\\((?:[^()\\\\]|\\\\.)*\\))*$"
+    },
+    {
+      "$comment": "Unquoted local-part + domain-literal (arbitrary dtext / quoted-pairs inside brackets). Comments allowed around tokens",
+      "pattern": "^(?:(?:[ \\t]|\\((?:[^()\\\\]|\\\\.)*\\))*)(?:[A-Za-z0-9!#$%&'*+\\/=?^_`{|}~-]+(?:(?:[ \\t]*\\((?:[^()\\\\]|\\\\.)*\\)[ \\t]*[A-Za-z0-9!#$%&'*+\\/=?^_`{|}~-]+)|(?:\\.[A-Za-z0-9!#$%&'*+\\/=?^_`{|}~-]+))*)(?:[ \\t]|\\((?:[^()\\\\]|\\\\.)*\\))*@(?:[ \\t]|\\((?:[^()\\\\]|\\\\.)*\\))*\\[(?:[^\\[\\]\\\\\\r]|\\\\.)*\\](?:[ \\t]|\\((?:[^()\\\\]|\\\\.)*\\))*$"
+    },
+    {
+      "$comment": "Quoted local-part + domain-literal. Comments allowed around quoted local and around the literal",
+      "pattern": "^(?:[ \\t]|\\((?:[^()\\\\]|\\\\.)*\\))*(?:\"(?:[^\"\\\\\\r]|\\\\.)*\")(?:[ \\t]|\\((?:[^()\\\\]|\\\\.)*\\))*@(?:[ \\t]|\\((?:[^()\\\\]|\\\\.)*\\))*\\[(?:[^\\[\\]\\\\\\r]|\\\\.)*\\](?:[ \\t]|\\((?:[^()\\\\]|\\\\.)*\\))*$"
+    }
+  ],
+  "not": {
+    "anyOf": [
+      {
+        "$comment": "Disallow bare IPv4 address in domain (must be bracketed)",
+        "pattern": "@([0-9]{1,3}\\.){3}[0-9]{1,3}(?:$|\\s)"
+      },
+      {
+        "$comment": "Disallow IPv6 literal without brackets",
+        "pattern": "@IPv6:"
+      },
+      {
+        "$comment": "Disallow numeric-only final label (numeric TLDs like example.123)",
+        "pattern": "@[^@\\s]*\\.\\d+(?:$|\\s)"
+      },
+      {
+        "$comment": "Reject addresses that start with a single-quote delimiter",
+        "pattern": "^'"
+      }
+    ]
+  },
+  "format": "email",
+  "minLength": 1
+}
diff --git a/tests/ietf/email/address.test.json b/tests/ietf/email/address.test.json
new file mode 100644
index 00000000..f24e9426
--- /dev/null
+++ b/tests/ietf/email/address.test.json
@@ -0,0 +1,366 @@
+{
+  "x-license": "https://github.com/sourcemeta/std/blob/main/LICENSE",
+  "target": "../../../schemas/ietf/email/address.json",
+  "tests": [
+    {
+      "description": "Invalid type",
+      "data": 1,
+      "valid": false
+    },
+    {
+      "description": "Basic email format",
+      "data": "simple@example.com",
+      "valid": true
+    },
+    {
+      "description": "Local-part with dot",
+      "data": "very.common@example.com",
+      "valid": true
+    },
+    {
+      "description": "Mixed case local and domain",
+      "data": "FirstName.LastName@EasierReading.org",
+      "valid": true
+    },
+    {
+      "description": "Single character local part",
+      "data": "x@example.com",
+      "valid": true
+    },
+    {
+      "description": "Local-part with hyphens and subdomains",
+      "data": "long.email-address-with-hyphens@and.subdomains.example.com",
+      "valid": true
+    },
+    {
+      "description": "Local-part with plus sign and tags",
+      "data": "user.name+tag+sorting@example.com",
+      "valid": true
+    },
+    {
+      "description": "Local-part with slash",
+      "data": "name/surname@example.com",
+      "valid": true
+    },
+    {
+      "description": "Local-part with underscore",
+      "data": "user_name@example.com",
+      "valid": true
+    },
+    {
+      "description": "Local-part and domain with hyphen",
+      "data": "user-name@sub-domain.example.co.uk",
+      "valid": true
+    },
+    {
+      "description": "Quoted local-part with double dot inside",
+      "data": "\"john..doe\"@example.org",
+      "valid": true
+    },
+    {
+      "description": "Quoted local-part with space",
+      "data": "\" \"@example.org",
+      "valid": true
+    },
+    {
+      "description": "Quoted local-part ending with dot",
+      "data": "\"john.doe.\"@example.com",
+      "valid": true
+    },
+    {
+      "description": "Quoted local-part containing @ symbol",
+      "data": "\"john@doe\"@example.com",
+      "valid": true
+    },
+    {
+      "description": "Example with all allowed special characters in local-part",
+      "data": "test!#$%&'*+/=?^_`{|}~@example.com",
+      "valid": true
+    },
+    {
+      "description": "Bang path style local-part",
+      "data": "mailhost!username@example.org",
+      "valid": true
+    },
+    {
+      "description": "Percent hack routing",
+      "data": "user%example.com@example.org",
+      "valid": true
+    },
+    {
+      "description": "Local-part ending with dash",
+      "data": "user-@example.org",
+      "valid": true
+    },
+    {
+      "description": "IPv4 address literal domain",
+      "data": "postmaster@[123.123.123.123]",
+      "valid": true
+    },
+    {
+      "description": "IPv6 address literal domain",
+      "data": "postmaster@[IPv6:2001:db8::85a3:0:0:8a2e:370:7334]",
+      "valid": true
+    },
+    {
+      "description": "Local-part starts with underscore",
+      "data": "_test123@example.org",
+      "valid": true
+    },
+    {
+      "description": "Plus in local-part with uppercase domain",
+      "data": "test+filter@Example.COM",
+      "valid": true
+    },
+    {
+      "description": "Dot in local-part",
+      "data": "test.filter@example.com",
+      "valid": true
+    },
+    {
+      "description": "Underscore in local-part",
+      "data": "test_filter@example.com",
+      "valid": true
+    },
+    {
+      "description": "Domain with no TLD (dotless domain)",
+      "data": "admin@example",
+      "valid": true
+    },
+    {
+      "description": "Comments around local, domain, and address",
+      "data": "(comment)john.smith@(comment)example.com(comment)",
+      "valid": true
+    },
+    {
+      "description": "Quoted local-part with space and letters",
+      "data": "\"Fred Bloggs\"@example.com",
+      "valid": true
+    },
+    {
+      "description": "Domain literal with letters and dot",
+      "data": "user@[abc.def]",
+      "valid": true
+    },
+    {
+      "description": "All uppercase local and domain",
+      "data": "USER@EXAMPLE.COM",
+      "valid": true
+    },
+    {
+      "description": "Local-part with tilde and domain with hyphen",
+      "data": "a~b@c-domain.com",
+      "valid": true
+    },
+    {
+      "description": "Local-part with slash and plus",
+      "data": "first.last+category/department@domain.com",
+      "valid": true
+    },
+    {
+      "description": "Local-part with apostrophe",
+      "data": "o'reilly@example.com",
+      "valid": true
+    },
+    {
+      "description": "Local-part with multiple route characters",
+      "data": "dizzy%example.com+tag@example.org",
+      "valid": true
+    },
+    {
+      "description": "Email with comment in domain",
+      "data": "john.smith@(comment)example.com",
+      "valid": true
+    },
+    {
+      "description": "Email with comment in local part",
+      "data": "jo(comment)hn@example.com",
+      "valid": true
+    },
+    {
+      "description": "Complex quoted local-part with many allowed symbols",
+      "data": "\"very.(),:;<>[]\\\".VERY.\\\"very@\\\\ \\\"very\\\".unusual\"@strange.example.com",
+      "valid": true
+    },
+    {
+      "description": "Missing @ symbol",
+      "data": "plainaddress",
+      "valid": false
+    },
+    {
+      "description": "Missing local part",
+      "data": "@no-local-part.com",
+      "valid": false
+    },
+    {
+      "description": "Missing domain",
+      "data": "user@",
+      "valid": false
+    },
+    {
+      "description": "Missing both local and domain parts",
+      "data": "@",
+      "valid": false
+    },
+    {
+      "description": "Leading dot in local-part",
+      "data": ".user@example.com",
+      "valid": false
+    },
+    {
+      "description": "Trailing dot in local-part",
+      "data": "user.@example.com",
+      "valid": false
+    },
+    {
+      "description": "Consecutive dots in local-part",
+      "data": "user..user@example.com",
+      "valid": false
+    },
+    {
+      "description": "Leading dot in domain",
+      "data": "user@.example.com",
+      "valid": false
+    },
+    {
+      "description": "Trailing dot in domain",
+      "data": "user@example.com.",
+      "valid": false
+    },
+    {
+      "description": "Consecutive dots in domain",
+      "data": "user@example..com",
+      "valid": false
+    },
+    {
+      "description": "Domain label starts with hyphen",
+      "data": "user@-example.com",
+      "valid": false
+    },
+    {
+      "description": "Domain label ends with hyphen",
+      "data": "user@example-.com",
+      "valid": false
+    },
+    {
+      "description": "Underscore in domain part",
+      "data": "user@exam_ple.com",
+      "valid": false
+    },
+    {
+      "description": "Numeric TLD in domain",
+      "data": "user@example.123",
+      "valid": false
+    },
+    {
+      "description": "Multiple @ symbols",
+      "data": "A@b@c@example.com",
+      "valid": false
+    },
+    {
+      "description": "Invalid characters in local-part (unquoted specials)",
+      "data": "a\"b(c)d,e:f;g<h>i[j\\k]l@example.com",
+      "valid": false
+    },
+    {
+      "description": "Incorrect quoted string placement in local-part",
+      "data": "just\"not\"right@example.com",
+      "valid": false
+    },
+    {
+      "description": "Unquoted space in local-part",
+      "data": "this is\"not\\allowed@example.com",
+      "valid": false
+    },
+    {
+      "description": "Escaped characters outside quotes in local-part",
+      "data": "this\\ still\\\"not\\\\allowed@example.com",
+      "valid": false
+    },
+    {
+      "description": "Just a quoted string with no @ and domain",
+      "data": "\"test\"",
+      "valid": false
+    },
+    {
+      "description": "Unclosed comment in local-part",
+      "data": "john(dôe@example.com",
+      "valid": false
+    },
+    {
+      "description": "Unmatched parenthesis in domain",
+      "data": "john@example.com)",
+      "valid": false
+    },
+    {
+      "description": "Non-ASCII character in local-part",
+      "data": "mañana@example.com",
+      "valid": false
+    },
+    {
+      "description": "Non-ASCII character in domain",
+      "data": "user@exámple.com",
+      "valid": false
+    },
+    {
+      "description": "Missing closing bracket in domain literal",
+      "data": "test@[127.0.0.1",
+      "valid": false
+    },
+    {
+      "description": "Missing opening bracket in domain literal",
+      "data": "test@127.0.0.1]",
+      "valid": false
+    },
+    {
+      "description": "Trailing dot after domain literal",
+      "data": "test@[127.0.0.1].",
+      "valid": false
+    },
+    {
+      "description": "Unclosed IPv6 literal",
+      "data": "test@[IPv6:2001:db8::1",
+      "valid": false
+    },
+    {
+      "description": "Extra characters after domain literal",
+      "data": "test@[IPv6:2001:db8::1]extra",
+      "valid": false
+    },
+    {
+      "description": "Uppercase numeric TLD (invalid as TLD numeric only)",
+      "data": "user@EXAMPLE.123",
+      "valid": false
+    },
+    {
+      "description": "IP address without brackets in domain",
+      "data": "user@123.123.123.123",
+      "valid": false
+    },
+    {
+      "description": "IPv6 address without brackets",
+      "data": "user@IPv6:2001:db8::1",
+      "valid": false
+    },
+    {
+      "description": "Single quote used as delimiter (invalid)",
+      "data": "'test'@example.com",
+      "valid": false
+    },
+    {
+      "description": "Double quotes misplacement",
+      "data": "\"\"test@example.com",
+      "valid": false
+    },
+    {
+      "description": "Escaped @ outside quoted string (invalid)",
+      "data": "test\\@example.com",
+      "valid": false
+    },
+    {
+      "description": "Empty string",
+      "data": "",
+      "valid": false
+    }
+  ]
+}