php实现RFC兼容的电子邮件地址验证

WBOY
Lepaskan: 2016-07-25 08:56:42
asal
1438 orang telah melayarinya
  1. /*
  2. Copyright 2009 Dominic Sayers
  3. (dominic_sayers@hotmail.com)
  4. (http://www.dominicsayers.com)
  5. This source file is subject to the Common Public Attribution License Version 1.0 (CPAL) license.

  6. The license terms are available through the world-wide-web at http://www.opensource.org/licenses/cpal_1.0
  7. */
  8. function is_email ($email, $checkDNS = false) {
  9. // Check that $email is a valid address
  10. // (http://tools.ietf.org/html/rfc3696)
  11. // (http://tools.ietf.org/html/rfc5322#section-3.4.1)
  12. // (http://tools.ietf.org/html/rfc5321#section-4.1.3)
  13. // (http://tools.ietf.org/html/rfc4291#section-2.2)
  14. // (http://tools.ietf.org/html/rfc1123#section-2.1)
  15. // Contemporary email addresses consist of a "local part" separated from
  16. // a "domain part" (a fully-qualified domain name) by an at-sign ("@").
  17. // (http://tools.ietf.org/html/rfc3696#section-3)
  18. $index = strrpos($email,'@');
  19. if ($index === false) return false; // No at-sign

  20. if ($index === 0) return false; // No local part
  21. if ($index > 64) return false; // Local part too long
  22. $localPart = substr($email, 0, $index);

  23. $domain = substr($email, $index + 1);
  24. $domainLength = strlen($domain);
  25. if ($domainLength === 0) return false; // No domain part
  26. if ($domainLength > 255) return false; // Domain part too long
  27. // Let's check the local part for RFC compliance...

  28. //
  29. // Period (".") may...appear, but may not be used to start or end the
  30. // local part, nor may two or more consecutive periods appear.
  31. // (http://tools.ietf.org/html/rfc3696#section-3)
  32. if (preg_match('/^\\.|\\.\\.|\\.$/', $localPart) > 0) return false; // Dots in wrong place
  33. // Any ASCII graphic (printing) character other than the

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

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

  49. // (http://tools.ietf.org/html/rfc3696#section-3)
  50. // (http://tools.ietf.org/html/rfc5321#section-4.1.3)
  51. // (http://tools.ietf.org/html/rfc4291#section-2.2)
  52. if (preg_match('/^\\[(.)+]$/', $domain) === 1) {
  53. // It's an address-literal
  54. $addressLiteral = substr($domain, 1, $domainLength - 2);
  55. $matchesIP = array();
  56. // Extract IPv4 part from the end of the address-literal (if there is one)
  57. if (preg_match('/\\b(?:(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)\\.){3}(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)$/', $addressLiteral, $matchesIP) > 0) {
  58. $index = strrpos($addressLiteral, $matchesIP[0]);
  59. if ($index === 0) {
  60. // Nothing there except a valid IPv4 address, so...
  61. return true;
  62. } else {
  63. // Assume it's an attempt at a mixed address (IPv6 + IPv4)
  64. if ($addressLiteral[$index - 1] !== ':') return false; // Character preceding IPv4 address must be ':'
  65. if (substr($addressLiteral, 0, 5) !== 'IPv6:') return false; // RFC5321 section 4.1.3
  66. $IPv6 = substr($addressLiteral, 5, ($index ===7) ? 2 : $index - 6);

  67. $groupMax = 6;
  68. }
  69. } else {
  70. // It must be an attempt at pure IPv6
  71. if (substr($addressLiteral, 0, 5) !== 'IPv6:') return false; // RFC5321 section 4.1.3
  72. $IPv6 = substr($addressLiteral, 5);
  73. $groupMax = 8;
  74. }
  75. $groupCount = preg_match_all('/^[0-9a-fA-F]{0,4}|\\:[0-9a-fA-F]{0,4}|(.)/', $IPv6, $matchesIP);

  76. $index = strpos($IPv6,'::');
  77. if ($index === false) {

  78. // We need exactly the right number of groups
  79. if ($groupCount !== $groupMax) return false; // RFC5321 section 4.1.3
  80. } else {
  81. if ($index !== strrpos($IPv6,'::')) return false; // More than one '::'
  82. $groupMax = ($index === 0 || $index === (strlen($IPv6) - 2)) ? $groupMax : $groupMax - 1;
  83. if ($groupCount > $groupMax) return false; // Too many IPv6 groups in address
  84. }
  85. // Check for unmatched characters

  86. array_multisort($matchesIP[1], SORT_DESC);
  87. if ($matchesIP[1][0] !== '') return false; // Illegal characters in address
  88. // It's a valid IPv6 address, so...

  89. return true;
  90. } else {
  91. // It's a domain name...
  92. // The syntax of a legal Internet host name was specified in RFC-952

  93. // One aspect of host name syntax is hereby changed: the
  94. // restriction on the first character is relaxed to allow either a
  95. // letter or a digit.
  96. // (http://tools.ietf.org/html/rfc1123#section-2.1)
  97. //
  98. // NB RFC 1123 updates RFC 1035, but this is not currently apparent from reading RFC 1035.
  99. //
  100. // Most common applications, including email and the Web, will generally not permit...escaped strings
  101. // (http://tools.ietf.org/html/rfc3696#section-2)
  102. //
  103. // Characters outside the set of alphabetic characters, digits, and hyphen MUST NOT appear in domain name
  104. // labels for SMTP clients or servers
  105. // (http://tools.ietf.org/html/rfc5321#section-4.1.2)
  106. //
  107. // RFC5321 precludes the use of a trailing dot in a domain name for SMTP purposes
  108. // (http://tools.ietf.org/html/rfc5321#section-4.1.2)
  109. $matches = array();
  110. $groupCount = preg_match_all('/(?:[0-9a-zA-Z][0-9a-zA-Z-]{0,61}[0-9a-zA-Z]|[a-zA-Z])(?:\\.|$)|(.)/', $domain, $matches);
  111. $level = count($matches[0]);
  112. if ($level == 1) return false; // Mail host can't be a TLD

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

  114. if (substr($TLD, strlen($TLD) - 1, 1) === '.') return false; // TLD can't end in a dot
  115. if (preg_match('/^[0-9]+$/', $TLD) > 0) return false; // TLD can't be all-numeric
  116. // Check for unmatched characters

  117. array_multisort($matches[1], SORT_DESC);
  118. if ($matches[1][0] !== '') return false; // Illegal characters in domain, or label longer than 63 characters
  119. // Check DNS?

  120. if ($checkDNS && function_exists('checkdnsrr')) {
  121. if (!(checkdnsrr($domain, 'A') || checkdnsrr($domain, 'MX'))) {
  122. return false; // Domain doesn't actually exist
  123. }
  124. }
  125. // Eliminate all other factors, and the one which remains must be the truth.

  126. // (Sherlock Holmes, The Sign of Four)
  127. return true;
  128. }
  129. }
  130. function unitTest ($email, $reason = '') {

  131. $expected = ($reason === '') ? true : false;
  132. $valid = is_email($email);
  133. $not = ($valid) ? '' : ' not';
  134. $unexpected = ($valid !== $expected) ? ' This was unexpected!' : '';
  135. $reason = ($reason === '') ? "" : " Reason: $reason";
  136. return "The address $email is$not valid.$unexpected$reason
    \n";
  137. }
  138. // Email validator test cases (Dominic Sayers, January 2009)

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

  161. echo unitTest('first.last', "No @");
  162. echo unitTest('@example.com', "No local part");
  163. echo unitTest('12345678901234567890123456789012345678901234567890123456789012345@example.com', "Local part more than 64 characters");
  164. echo unitTest('.first.last@example.com', "Local part starts with a dot");
  165. echo unitTest('first.last.@example.com', "Local part ends with a dot");
  166. echo unitTest('first..last@example.com', "Local part has consecutive dots");
  167. echo unitTest('"first"last"@example.com', "Local part contains unescaped excluded characters");
  168. echo unitTest('first\\\\@last@example.com', "Local part contains unescaped excluded characters");
  169. echo unitTest('first.last@', "No domain");
  170. echo unitTest('first.last@x23456789.x23456789.x23456789.x23456789.x23456789.x23456789.x23456789.x23456789.x23456789.x23456789.x23456789.x23456789.x23456789.x23456789.
  171. x23456789.x23456789.x23456789.x23456789.x23456789.x23456789.x23456789.x23456789.x23456789.x23456789.x23456789.x23456', "Domain exceeds 255 chars");
  172. echo unitTest('first.last@[.12.34.56.78]', "Only char that can precede IPv4 address is ':'");
  173. echo unitTest('first.last@[12.34.56.789]', "Can't be interpreted as IPv4 so IPv6 tag is missing");
  174. echo unitTest('first.last@[::12.34.56.78]', "IPv6 tag is missing");
  175. echo unitTest('first.last@[IPv5:::12.34.56.78]', "IPv6 tag is wrong");
  176. echo unitTest('first.last@[IPv6:1111:2222:3333::4444:5555:12.34.56.78]', "Too many IPv6 groups (4 max)");
  177. echo unitTest('first.last@[IPv6:1111:2222:3333:4444:5555:12.34.56.78]', "Not enough IPv6 groups");
  178. echo unitTest('first.last@[IPv6:1111:2222:3333:4444:5555:6666:7777:12.34.56.78]', "Too many IPv6 groups (6 max)");
  179. echo unitTest('first.last@[IPv6:1111:2222:3333:4444:5555:6666:7777]', "Not enough IPv6 groups");
  180. echo unitTest('first.last@[IPv6:1111:2222:3333:4444:5555:6666:7777:8888:9999]', "Too many IPv6 groups (8 max)");
  181. echo unitTest('first.last@[IPv6:1111:2222::3333::4444:5555:6666]', "Too many '::' (can be none or one)");
  182. echo unitTest('first.last@[IPv6:1111:2222:3333::4444:5555:6666:7777]', "Too many IPv6 groups (6 max)");
  183. echo unitTest('first.last@[IPv6:1111:2222:333x::4444:5555]', "x is not valid in an IPv6 address");
  184. echo unitTest('first.last@[IPv6:1111:2222:33333::4444:5555]', "33333 is not a valid group in an IPv6 address");
  185. echo unitTest('first.last@example.123', "TLD can't be all digits");
  186. echo unitTest('first.last@com', "Mail host must be second- or lower level");
  187. echo unitTest('first.last@-xample.com', "Label can't begin with a hyphen");
  188. echo unitTest('first.last@exampl-.com', "Label can't end with a hyphen");
  189. echo unitTest('first.last@x234567890123456789012345678901234567890123456789012345678901234.example.com', "Label can't be longer than 63 octets");
  190. // Test cases from RFC3696 (February 2004, http://tools.ietf.org/html/rfc3696#section-3)

  191. echo unitTest('Abc\\@def@example.com');
  192. echo unitTest('Fred\\ Bloggs@example.com');
  193. echo unitTest('Joe.\\\\Blow@example.com');
  194. echo unitTest('"Abc@def"@example.com');
  195. echo unitTest('"Fred Bloggs"@example.com');
  196. echo unitTest('user+mailbox@example.com');
  197. echo unitTest('customer/department=shipping@example.com');
  198. echo unitTest('$A12345@example.com');
  199. echo unitTest('!def!xyz%abc@example.com');
  200. echo unitTest('_somename@example.com');
  201. // Test cases from Doug Lovell (LinuxJournal, June 2007, http://www.linuxjournal.com/article/9585)

  202. echo unitTest("dclo@us.ibm.com");
  203. echo unitTest("abc\\@def@example.com");
  204. echo unitTest("abc\\\\@example.com");
  205. echo unitTest("Fred\\ Bloggs@example.com");
  206. echo unitTest("Joe.\\\\Blow@example.com");
  207. echo unitTest("\"Abc@def\"@example.com");
  208. echo unitTest("\"Fred Bloggs\"@example.com");
  209. echo unitTest("customer/department=shipping@example.com");
  210. echo unitTest("\$A12345@example.com");
  211. echo unitTest("!def!xyz%abc@example.com");
  212. echo unitTest("_somename@example.com");
  213. echo unitTest("user+mailbox@example.com");
  214. echo unitTest("peter.piper@example.com");
  215. echo unitTest("Doug\\ \\\"Ace\\\"\\ Lovell@example.com");
  216. echo unitTest("\"Doug \\\"Ace\\\" L.\"@example.com");
  217. echo unitTest("abc@def@example.com", "Doug Lovell says this should fail");
  218. echo unitTest("abc\\\\@def@example.com", "Doug Lovell says this should fail");
  219. echo unitTest("abc\\@example.com", "Doug Lovell says this should fail");
  220. echo unitTest("@example.com", "Doug Lovell says this should fail");
  221. echo unitTest("doug@", "Doug Lovell says this should fail");
  222. echo unitTest("\"qu@example.com", "Doug Lovell says this should fail");
  223. echo unitTest("ote\"@example.com", "Doug Lovell says this should fail");
  224. echo unitTest(".dot@example.com", "Doug Lovell says this should fail");
  225. echo unitTest("dot.@example.com", "Doug Lovell says this should fail");
  226. echo unitTest("two..dot@example.com", "Doug Lovell says this should fail");
  227. echo unitTest("\"Doug \"Ace\" L.\"@example.com", "Doug Lovell says this should fail");
  228. echo unitTest("Doug\\ \\\"Ace\\\"\\ L\\.@example.com", "Doug Lovell says this should fail");
  229. echo unitTest("hello world@example.com", "Doug Lovell says this should fail");
  230. echo unitTest("gatsby@f.sc.ot.t.f.i.tzg.era.l.d.", "Doug Lovell says this should fail");
  231. ?>
复制代码


sumber:php.cn
Kenyataan Laman Web ini
Kandungan artikel ini disumbangkan secara sukarela oleh netizen, dan hak cipta adalah milik pengarang asal. Laman web ini tidak memikul tanggungjawab undang-undang yang sepadan. Jika anda menemui sebarang kandungan yang disyaki plagiarisme atau pelanggaran, sila hubungi admin@php.cn
Tutorial Popular
Lagi>
Muat turun terkini
Lagi>
kesan web
Kod sumber laman web
Bahan laman web
Templat hujung hadapan