170 lines
5.0 KiB
JavaScript
170 lines
5.0 KiB
JavaScript
'use strict';
|
|
|
|
const Util = require('util');
|
|
|
|
const Domain = require('./domain');
|
|
|
|
|
|
const internals = {
|
|
nonAsciiRx: /[^\x00-\x7f]/,
|
|
encoder: new (Util.TextEncoder || TextEncoder)() // $lab:coverage:ignore$
|
|
};
|
|
|
|
|
|
exports.analyze = function (email, options) {
|
|
|
|
return internals.email(email, options);
|
|
};
|
|
|
|
|
|
exports.isValid = function (email, options) {
|
|
|
|
return !internals.email(email, options);
|
|
};
|
|
|
|
|
|
internals.email = function (email, options = {}) {
|
|
|
|
if (typeof email !== 'string') {
|
|
throw new Error('Invalid input: email must be a string');
|
|
}
|
|
|
|
if (!email) {
|
|
return { error: 'Address must be a non-empty string' };
|
|
}
|
|
|
|
// Unicode
|
|
|
|
const ascii = !internals.nonAsciiRx.test(email);
|
|
if (!ascii) {
|
|
if (options.allowUnicode === false) { // Defaults to true
|
|
return { error: 'Address contains forbidden Unicode characters' };
|
|
}
|
|
|
|
email = email.normalize('NFC');
|
|
}
|
|
|
|
// Basic structure
|
|
|
|
const parts = email.split('@');
|
|
if (parts.length !== 2) {
|
|
return { error: parts.length > 2 ? 'Address cannot contain more than one @ character' : 'Address must contain one @ character' };
|
|
}
|
|
|
|
const [local, domain] = parts;
|
|
|
|
if (!local) {
|
|
return { error: 'Address local part cannot be empty' };
|
|
}
|
|
|
|
if (!options.ignoreLength) {
|
|
if (email.length > 254) { // http://tools.ietf.org/html/rfc5321#section-4.5.3.1.3
|
|
return { error: 'Address too long' };
|
|
}
|
|
|
|
if (internals.encoder.encode(local).length > 64) { // http://tools.ietf.org/html/rfc5321#section-4.5.3.1.1
|
|
return { error: 'Address local part too long' };
|
|
}
|
|
}
|
|
|
|
// Validate parts
|
|
|
|
return internals.local(local, ascii) || Domain.analyze(domain, options);
|
|
};
|
|
|
|
|
|
internals.local = function (local, ascii) {
|
|
|
|
const segments = local.split('.');
|
|
for (const segment of segments) {
|
|
if (!segment.length) {
|
|
return { error: 'Address local part contains empty dot-separated segment' };
|
|
}
|
|
|
|
if (ascii) {
|
|
if (!internals.atextRx.test(segment)) {
|
|
return { error: 'Address local part contains invalid character' };
|
|
}
|
|
|
|
continue;
|
|
}
|
|
|
|
for (const char of segment) {
|
|
if (internals.atextRx.test(char)) {
|
|
continue;
|
|
}
|
|
|
|
const binary = internals.binary(char);
|
|
if (!internals.atomRx.test(binary)) {
|
|
return { error: 'Address local part contains invalid character' };
|
|
}
|
|
}
|
|
}
|
|
};
|
|
|
|
|
|
internals.binary = function (char) {
|
|
|
|
return Array.from(internals.encoder.encode(char)).map((v) => String.fromCharCode(v)).join('');
|
|
};
|
|
|
|
|
|
/*
|
|
From RFC 5321:
|
|
|
|
Mailbox = Local-part "@" ( Domain / address-literal )
|
|
|
|
Local-part = Dot-string / Quoted-string
|
|
Dot-string = Atom *("." Atom)
|
|
Atom = 1*atext
|
|
atext = ALPHA / DIGIT / "!" / "#" / "$" / "%" / "&" / "'" / "*" / "+" / "-" / "/" / "=" / "?" / "^" / "_" / "`" / "{" / "|" / "}" / "~"
|
|
|
|
Domain = sub-domain *("." sub-domain)
|
|
sub-domain = Let-dig [Ldh-str]
|
|
Let-dig = ALPHA / DIGIT
|
|
Ldh-str = *( ALPHA / DIGIT / "-" ) Let-dig
|
|
|
|
ALPHA = %x41-5A / %x61-7A ; a-z, A-Z
|
|
DIGIT = %x30-39 ; 0-9
|
|
|
|
From RFC 6531:
|
|
|
|
sub-domain =/ U-label
|
|
atext =/ UTF8-non-ascii
|
|
|
|
UTF8-non-ascii = UTF8-2 / UTF8-3 / UTF8-4
|
|
|
|
UTF8-2 = %xC2-DF UTF8-tail
|
|
UTF8-3 = %xE0 %xA0-BF UTF8-tail /
|
|
%xE1-EC 2( UTF8-tail ) /
|
|
%xED %x80-9F UTF8-tail /
|
|
%xEE-EF 2( UTF8-tail )
|
|
UTF8-4 = %xF0 %x90-BF 2( UTF8-tail ) /
|
|
%xF1-F3 3( UTF8-tail ) /
|
|
%xF4 %x80-8F 2( UTF8-tail )
|
|
|
|
UTF8-tail = %x80-BF
|
|
|
|
Note: The following are not supported:
|
|
|
|
RFC 5321: address-literal, Quoted-string
|
|
RFC 5322: obs-*, CFWS
|
|
*/
|
|
|
|
|
|
internals.atextRx = /^[\w!#\$%&'\*\+\-/=\?\^`\{\|\}~]+$/; // _ included in \w
|
|
|
|
|
|
internals.atomRx = new RegExp([
|
|
|
|
// %xC2-DF UTF8-tail
|
|
'(?:[\\xc2-\\xdf][\\x80-\\xbf])',
|
|
|
|
// %xE0 %xA0-BF UTF8-tail %xE1-EC 2( UTF8-tail ) %xED %x80-9F UTF8-tail %xEE-EF 2( UTF8-tail )
|
|
'(?:\\xe0[\\xa0-\\xbf][\\x80-\\xbf])|(?:[\\xe1-\\xec][\\x80-\\xbf]{2})|(?:\\xed[\\x80-\\x9f][\\x80-\\xbf])|(?:[\\xee-\\xef][\\x80-\\xbf]{2})',
|
|
|
|
// %xF0 %x90-BF 2( UTF8-tail ) %xF1-F3 3( UTF8-tail ) %xF4 %x80-8F 2( UTF8-tail )
|
|
'(?:\\xf0[\\x90-\\xbf][\\x80-\\xbf]{2})|(?:[\\xf1-\\xf3][\\x80-\\xbf]{3})|(?:\\xf4[\\x80-\\x8f][\\x80-\\xbf]{2})'
|
|
|
|
].join('|'));
|