欢迎您访问程序员文章站本站旨在为大家提供分享程序员计算机编程知识！
您现在的位置是： 首页  >  后端开发

php实现RFC兼容的电子邮件地址验证

程序员文章站 2024-01-01 11:34:34
...

  4. /*
  5. Copyright 2009 Dominic Sayers
  6. (dominic_sayers@hotmail.com)
  7. (http://www.dominicsayers.com)

  8. This source file is subject to the Common Public Attribution License Version 1.0 (CPAL) license.

  9. The license terms are available through the world-wide-web at http://www.opensource.org/licenses/cpal_1.0
  10. */
  11. function is_email ($email, $checkDNS = false) {
  12. // Check that $email is a valid address
  13. // (http://tools.ietf.org/html/rfc3696)
  14. // (http://tools.ietf.org/html/rfc5322#section-3.4.1)
  15. // (http://tools.ietf.org/html/rfc5321#section-4.1.3)
  16. // (http://tools.ietf.org/html/rfc4291#section-2.2)
  17. // (http://tools.ietf.org/html/rfc1123#section-2.1)
  19. // Contemporary email addresses consist of a "local part" separated from
  20. // a "domain part" (a fully-qualified domain name) by an at-sign ("@").
  21. // (http://tools.ietf.org/html/rfc3696#section-3)
  22. $index = strrpos($email,'@');

  23. if ($index === false) return false; // No at-sign

  24. if ($index === 0) return false; // No local part
  25. if ($index > 64) return false; // Local part too long

  26. $localPart = substr($email, 0, $index);

  27. $domain = substr($email, $index + 1);
  28. $domainLength = strlen($domain);
  30. if ($domainLength === 0) return false; // No domain part
  31. if ($domainLength > 255) return false; // Domain part too long

  32. // Let's check the local part for RFC compliance...

  33. //
  34. // Period (".") may...appear, but may not be used to start or end the
  35. // local part, nor may two or more consecutive periods appear.
  36. // (http://tools.ietf.org/html/rfc3696#section-3)
  37. if (preg_match('/^\\.|\\.\\.|\\.$/', $localPart) > 0) return false; // Dots in wrong place

  38. // Any ASCII graphic (printing) character other than the

  39. // at-sign ("@"), backslash, double quote, comma, or square brackets may
  40. // appear without quoting. If any of that list of excluded characters
  41. // are to appear, they must be quoted
  42. // (http://tools.ietf.org/html/rfc3696#section-3)
  43. if (preg_match('/^"(?:.)*"$/', $localPart) > 0) {
  44. // Local part is a quoted string
  45. if (preg_match('/(?:.)+[^\\\\]"(?:.)+/', $localPart) > 0) return false; // Unescaped quote character inside quoted string
  46. } else {
  47. if (preg_match('/[ @\\[\\]\\\\",]/', $localPart) > 0)
  48. // Check all excluded characters are escaped
  49. $stripped = preg_replace('/\\\\[ @\\[\\]\\\\",]/', '', $localPart);
  50. if (preg_match('/[ @\\[\\]\\\\",]/', $stripped) > 0) return false; // Unquoted excluded characters
  51. }

  52. // Now let's check the domain part...

  53. // The domain name can also be replaced by an IP address in square brackets

  54. // (http://tools.ietf.org/html/rfc3696#section-3)
  55. // (http://tools.ietf.org/html/rfc5321#section-4.1.3)
  56. // (http://tools.ietf.org/html/rfc4291#section-2.2)
  57. if (preg_match('/^\\[(.)+]$/', $domain) === 1) {
  58. // It's an address-literal
  59. $addressLiteral = substr($domain, 1, $domainLength - 2);
  60. $matchesIP = array();
  62. // Extract IPv4 part from the end of the address-literal (if there is one)
  63. if (preg_match('/\\b(?:(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)\\.){3}(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)$/', $addressLiteral, $matchesIP) > 0) {
  64. $index = strrpos($addressLiteral, $matchesIP[0]);
  66. if ($index === 0) {
  67. // Nothing there except a valid IPv4 address, so...
  68. return true;
  69. } else {
  70. // Assume it's an attempt at a mixed address (IPv6 + IPv4)
  71. if ($addressLiteral[$index - 1] !== ':') return false; // Character preceding IPv4 address must be ':'
  72. if (substr($addressLiteral, 0, 5) !== 'IPv6:') return false; // RFC5321 section 4.1.3

  73. $IPv6 = substr($addressLiteral, 5, ($index ===7) ? 2 : $index - 6);

  74. $groupMax = 6;
  75. }
  76. } else {
  77. // It must be an attempt at pure IPv6
  78. if (substr($addressLiteral, 0, 5) !== 'IPv6:') return false; // RFC5321 section 4.1.3
  79. $IPv6 = substr($addressLiteral, 5);
  80. $groupMax = 8;
  81. }

  82. $groupCount = preg_match_all('/^[0-9a-fA-F]{0,4}|\\:[0-9a-fA-F]{0,4}|(.)/', $IPv6, $matchesIP);

  83. $index = strpos($IPv6,'::');

  84. if ($index === false) {

  85. // We need exactly the right number of groups
  86. if ($groupCount !== $groupMax) return false; // RFC5321 section 4.1.3
  87. } else {
  88. if ($index !== strrpos($IPv6,'::')) return false; // More than one '::'
  89. $groupMax = ($index === 0 || $index === (strlen($IPv6) - 2)) ? $groupMax : $groupMax - 1;
  90. if ($groupCount > $groupMax) return false; // Too many IPv6 groups in address
  91. }

  92. // Check for unmatched characters

  93. array_multisort($matchesIP[1], SORT_DESC);
  94. if ($matchesIP[1][0] !== '') return false; // Illegal characters in address

  95. // It's a valid IPv6 address, so...

  96. return true;
  97. } else {
  98. // It's a domain name...

  99. // The syntax of a legal Internet host name was specified in RFC-952

  100. // One aspect of host name syntax is hereby changed: the
  101. // restriction on the first character is relaxed to allow either a
  102. // letter or a digit.
  103. // (http://tools.ietf.org/html/rfc1123#section-2.1)
  104. //
  105. // NB RFC 1123 updates RFC 1035, but this is not currently apparent from reading RFC 1035.
  106. //
  107. // Most common applications, including email and the Web, will generally not permit...escaped strings
  108. // (http://tools.ietf.org/html/rfc3696#section-2)
  109. //
  110. // Characters outside the set of alphabetic characters, digits, and hyphen MUST NOT appear in domain name
  111. // labels for SMTP clients or servers
  112. // (http://tools.ietf.org/html/rfc5321#section-4.1.2)
  113. //
  114. // RFC5321 precludes the use of a trailing dot in a domain name for SMTP purposes
  115. // (http://tools.ietf.org/html/rfc5321#section-4.1.2)
  116. $matches = array();
  117. $groupCount = preg_match_all('/(?:[0-9a-zA-Z][0-9a-zA-Z-]{0,61}[0-9a-zA-Z]|[a-zA-Z])(?:\\.|$)|(.)/', $domain, $matches);
  118. $level = count($matches[0]);

  119. if ($level == 1) return false; // Mail host can't be a TLD

  120. $TLD = $matches[0][$level - 1];

  121. if (substr($TLD, strlen($TLD) - 1, 1) === '.') return false; // TLD can't end in a dot
  122. if (preg_match('/^[0-9]+$/', $TLD) > 0) return false; // TLD can't be all-numeric

  123. // Check for unmatched characters

  124. array_multisort($matches[1], SORT_DESC);
  125. if ($matches[1][0] !== '') return false; // Illegal characters in domain, or label longer than 63 characters

  126. // Check DNS?

  127. if ($checkDNS && function_exists('checkdnsrr')) {
  128. if (!(checkdnsrr($domain, 'A') || checkdnsrr($domain, 'MX'))) {
  129. return false; // Domain doesn't actually exist
  130. }
  131. }

  132. // Eliminate all other factors, and the one which remains must be the truth.

  133. // (Sherlock Holmes, The Sign of Four)
  134. return true;
  135. }
  136. }

  137. function unitTest ($email, $reason = '') {

  138. $expected = ($reason === '') ? true : false;
  139. $valid = is_email($email);
  140. $not = ($valid) ? '' : ' not';
  141. $unexpected = ($valid !== $expected) ? ' This was unexpected!' : '';
  142. $reason = ($reason === '') ? "" : " Reason: $reason";
  144. return "The address $email is$not valid.$unexpected$reason
    \n";
  145. }

  146. // Email validator test cases (Dominic Sayers, January 2009)

  147. // Valid addresses
  148. echo unitTest('first.last@example.com');
  149. echo unitTest('1234567890123456789012345678901234567890123456789012345678901234@example.com');
  150. echo unitTest('"first last"@example.com');
  151. echo unitTest('"first\\"last"@example.com'); // Not totally sure whether this is valid or not
  152. echo unitTest('first\\@last@example.com');
  153. echo unitTest('"first@last"@example.com');
  154. echo unitTest('first\\\\last@example.com'); // Note that \ is escaped even in single-quote strings, so this is testing "first\\last"@example.com
  155. echo unitTest('first.last@x23456789.x23456789.x23456789.x23456789.x23456789.x23456789.x23456789.x23456789.x23456789.x23456789.x23456789.x23456789.x23456789.x23456789.
  156. x23456789.x23456789.x23456789.x23456789.x23456789.x23456789.x23456789.x23456789.x23456789.x23456789.x23456789.x2345');
  157. echo unitTest('first.last@[12.34.56.78]');
  158. echo unitTest('first.last@[IPv6:::12.34.56.78]');
  159. echo unitTest('first.last@[IPv6:1111:2222:3333::4444:12.34.56.78]');
  160. echo unitTest('first.last@[IPv6:1111:2222:3333:4444:5555:6666:12.34.56.78]');
  161. echo unitTest('first.last@[IPv6:::1111:2222:3333:4444:5555:6666]');
  162. echo unitTest('first.last@[IPv6:1111:2222:3333::4444:5555:6666]');
  163. echo unitTest('first.last@[IPv6:1111:2222:3333:4444:5555:6666::]');
  164. echo unitTest('first.last@[IPv6:1111:2222:3333:4444:5555:6666:7777:8888]');
  165. echo unitTest('first.last@x23456789012345678901234567890123456789012345678901234567890123.example.com');
  166. echo unitTest('first.last@1xample.com');
  167. echo unitTest('first.last@123.example.com');

  168. // Invalid addresses

  169. echo unitTest('first.last', "No @");
  170. echo unitTest('@example.com', "No local part");
  171. echo unitTest('12345678901234567890123456789012345678901234567890123456789012345@example.com', "Local part more than 64 characters");
  172. echo unitTest('.first.last@example.com', "Local part starts with a dot");
  173. echo unitTest('first.last.@example.com', "Local part ends with a dot");
  174. echo unitTest('first..last@example.com', "Local part has consecutive dots");
  175. echo unitTest('"first"last"@example.com', "Local part contains unescaped excluded characters");
  176. echo unitTest('first\\\\@last@example.com', "Local part contains unescaped excluded characters");
  177. echo unitTest('first.last@', "No domain");
  178. echo unitTest('first.last@x23456789.x23456789.x23456789.x23456789.x23456789.x23456789.x23456789.x23456789.x23456789.x23456789.x23456789.x23456789.x23456789.x23456789.
  179. x23456789.x23456789.x23456789.x23456789.x23456789.x23456789.x23456789.x23456789.x23456789.x23456789.x23456789.x23456', "Domain exceeds 255 chars");
  180. echo unitTest('first.last@[.12.34.56.78]', "Only char that can precede IPv4 address is ':'");
  181. echo unitTest('first.last@[12.34.56.789]', "Can't be interpreted as IPv4 so IPv6 tag is missing");
  182. echo unitTest('first.last@[::12.34.56.78]', "IPv6 tag is missing");
  183. echo unitTest('first.last@[IPv5:::12.34.56.78]', "IPv6 tag is wrong");
  184. echo unitTest('first.last@[IPv6:1111:2222:3333::4444:5555:12.34.56.78]', "Too many IPv6 groups (4 max)");
  185. echo unitTest('first.last@[IPv6:1111:2222:3333:4444:5555:12.34.56.78]', "Not enough IPv6 groups");
  186. echo unitTest('first.last@[IPv6:1111:2222:3333:4444:5555:6666:7777:12.34.56.78]', "Too many IPv6 groups (6 max)");
  187. echo unitTest('first.last@[IPv6:1111:2222:3333:4444:5555:6666:7777]', "Not enough IPv6 groups");
  188. echo unitTest('first.last@[IPv6:1111:2222:3333:4444:5555:6666:7777:8888:9999]', "Too many IPv6 groups (8 max)");
  189. echo unitTest('first.last@[IPv6:1111:2222::3333::4444:5555:6666]', "Too many '::' (can be none or one)");
  190. echo unitTest('first.last@[IPv6:1111:2222:3333::4444:5555:6666:7777]', "Too many IPv6 groups (6 max)");
  191. echo unitTest('first.last@[IPv6:1111:2222:333x::4444:5555]', "x is not valid in an IPv6 address");
  192. echo unitTest('first.last@[IPv6:1111:2222:33333::4444:5555]', "33333 is not a valid group in an IPv6 address");
  193. echo unitTest('first.last@example.123', "TLD can't be all digits");
  194. echo unitTest('first.last@com', "Mail host must be second- or lower level");
  195. echo unitTest('first.last@-xample.com', "Label can't begin with a hyphen");
  196. echo unitTest('first.last@exampl-.com', "Label can't end with a hyphen");
  197. echo unitTest('first.last@x234567890123456789012345678901234567890123456789012345678901234.example.com', "Label can't be longer than 63 octets");

  198. // Test cases from RFC3696 (February 2004, http://tools.ietf.org/html/rfc3696#section-3)

  199. echo unitTest('Abc\\@def@example.com');
  200. echo unitTest('Fred\\ Bloggs@example.com');
  201. echo unitTest('Joe.\\\\Blow@example.com');
  202. echo unitTest('"Abc@def"@example.com');
  203. echo unitTest('"Fred Bloggs"@example.com');
  204. echo unitTest('user+mailbox@example.com');
  205. echo unitTest('customer/department=shipping@example.com');
  206. echo unitTest('$A12345@example.com');
  207. echo unitTest('!def!xyz%abc@example.com');
  208. echo unitTest('_somename@example.com');

  209. // Test cases from Doug Lovell (LinuxJournal, June 2007, http://www.linuxjournal.com/article/9585)

  210. echo unitTest("dclo@us.ibm.com");
  211. echo unitTest("abc\\@def@example.com");
  212. echo unitTest("abc\\\\@example.com");
  213. echo unitTest("Fred\\ Bloggs@example.com");
  214. echo unitTest("Joe.\\\\Blow@example.com");
  215. echo unitTest("\"Abc@def\"@example.com");
  216. echo unitTest("\"Fred Bloggs\"@example.com");
  217. echo unitTest("customer/department=shipping@example.com");
  218. echo unitTest("\$A12345@example.com");
  219. echo unitTest("!def!xyz%abc@example.com");
  220. echo unitTest("_somename@example.com");
  221. echo unitTest("user+mailbox@example.com");
  222. echo unitTest("peter.piper@example.com");
  223. echo unitTest("Doug\\ \\\"Ace\\\"\\ Lovell@example.com");
  224. echo unitTest("\"Doug \\\"Ace\\\" L.\"@example.com");
  225. echo unitTest("abc@def@example.com", "Doug Lovell says this should fail");
  226. echo unitTest("abc\\\\@def@example.com", "Doug Lovell says this should fail");
  227. echo unitTest("abc\\@example.com", "Doug Lovell says this should fail");
  228. echo unitTest("@example.com", "Doug Lovell says this should fail");
  229. echo unitTest("doug@", "Doug Lovell says this should fail");
  230. echo unitTest("\"qu@example.com", "Doug Lovell says this should fail");
  231. echo unitTest("ote\"@example.com", "Doug Lovell says this should fail");
  232. echo unitTest(".dot@example.com", "Doug Lovell says this should fail");
  233. echo unitTest("dot.@example.com", "Doug Lovell says this should fail");
  234. echo unitTest("two..dot@example.com", "Doug Lovell says this should fail");
  235. echo unitTest("\"Doug \"Ace\" L.\"@example.com", "Doug Lovell says this should fail");
  236. echo unitTest("Doug\\ \\\"Ace\\\"\\ L\\.@example.com", "Doug Lovell says this should fail");
  237. echo unitTest("hello world@example.com", "Doug Lovell says this should fail");
  238. echo unitTest("gatsby@f.sc.ot.t.f.i.tzg.era.l.d.", "Doug Lovell says this should fail");
  239. ?>
复制代码
相关标签： php实现RFC兼容的电子邮件地址验证

上一篇：

下一篇：

推荐阅读