Support Unicode characters in the local part of an e-mail address.

See RFC 6531 (https://tools.ietf.org/html/rfc6531). Encode IDNA domains. Add the missing "Done" to the expected output. Add the FILTER_FLAG_EMAIL_RFC6531 flag. Fix the filter_var() call.
Metabolix · Jul 18, 2016 · 8f40507 · 8f40507
1 parent 4226032
commit 8f40507
Show file tree

Hide file tree

Showing 4 changed files with 67 additions and 1 deletion.
diff --git a/ext/filter/filter.c b/ext/filter/filter.c
@@ -286,6 +286,8 @@ PHP_MINIT_FUNCTION(filter)
 
 	REGISTER_LONG_CONSTANT("FILTER_FLAG_HOSTNAME", FILTER_FLAG_HOSTNAME, CONST_CS | CONST_PERSISTENT);
 
+	REGISTER_LONG_CONSTANT("FILTER_FLAG_EMAIL_RFC6531", FILTER_FLAG_EMAIL_RFC6531, CONST_CS | CONST_PERSISTENT);
+
 	sapi_register_input_filter(php_sapi_filter, php_sapi_filter_init);
 
 	return SUCCESS;

diff --git a/ext/filter/filter_private.h b/ext/filter/filter_private.h
@@ -57,6 +57,8 @@
 
 #define FILTER_FLAG_HOSTNAME               0x100000
 
+#define FILTER_FLAG_EMAIL_RFC6531          0x100000
+
 #define FILTER_VALIDATE_INT           0x0101
 #define FILTER_VALIDATE_BOOLEAN       0x0102
 #define FILTER_VALIDATE_FLOAT         0x0103

diff --git a/ext/filter/logical_filters.c b/ext/filter/logical_filters.c
@@ -598,7 +598,12 @@ void php_filter_validate_email(PHP_INPUT_FILTER_PARAM_DECL) /* {{{ */
 	 * Feel free to use and redistribute this code. But please keep this copyright notice.
 	 *
 	 */
-	const char regexp[] = "/^(?!(?:(?:\\x22?\\x5C[\\x00-\\x7E]\\x22?)|(?:\\x22?[^\\x5C\\x22]\\x22?)){255,})(?!(?:(?:\\x22?\\x5C[\\x00-\\x7E]\\x22?)|(?:\\x22?[^\\x5C\\x22]\\x22?)){65,}@)(?:(?:[\\x21\\x23-\\x27\\x2A\\x2B\\x2D\\x2F-\\x39\\x3D\\x3F\\x5E-\\x7E]+)|(?:\\x22(?:[\\x01-\\x08\\x0B\\x0C\\x0E-\\x1F\\x21\\x23-\\x5B\\x5D-\\x7F]|(?:\\x5C[\\x00-\\x7F]))*\\x22))(?:\\.(?:(?:[\\x21\\x23-\\x27\\x2A\\x2B\\x2D\\x2F-\\x39\\x3D\\x3F\\x5E-\\x7E]+)|(?:\\x22(?:[\\x01-\\x08\\x0B\\x0C\\x0E-\\x1F\\x21\\x23-\\x5B\\x5D-\\x7F]|(?:\\x5C[\\x00-\\x7F]))*\\x22)))*@(?:(?:(?!.*[^.]{64,})(?:(?:(?:xn--)?[a-z0-9]+(?:-+[a-z0-9]+)*\\.){1,126}){1,}(?:(?:[a-z][a-z0-9]*)|(?:(?:xn--)[a-z0-9]+))(?:-+[a-z0-9]+)*)|(?:\\[(?:(?:IPv6:(?:(?:[a-f0-9]{1,4}(?::[a-f0-9]{1,4}){7})|(?:(?!(?:.*[a-f0-9][:\\]]){7,})(?:[a-f0-9]{1,4}(?::[a-f0-9]{1,4}){0,5})?::(?:[a-f0-9]{1,4}(?::[a-f0-9]{1,4}){0,5})?)))|(?:(?:IPv6:(?:(?:[a-f0-9]{1,4}(?::[a-f0-9]{1,4}){5}:)|(?:(?!(?:.*[a-f0-9]:){5,})(?:[a-f0-9]{1,4}(?::[a-f0-9]{1,4}){0,3})?::(?:[a-f0-9]{1,4}(?::[a-f0-9]{1,4}){0,3}:)?)))?(?:(?:25[0-5])|(?:2[0-4][0-9])|(?:1[0-9]{2})|(?:[1-9]?[0-9]))(?:\\.(?:(?:25[0-5])|(?:2[0-4][0-9])|(?:1[0-9]{2})|(?:[1-9]?[0-9]))){3}))\\]))$/iD";
+	if (flags & FILTER_FLAG_EMAIL_RFC6531) {
+		const char regexp[] = "/^(?!(?:(?:\\x22?\\x5C[\\x00-\\x7E]\\x22?)|(?:\\x22?[^\\x5C\\x22]\\x22?)){255,})(?!(?:(?:\\x22?\\x5C[\\x00-\\x7E]\\x22?)|(?:\\x22?[^\\x5C\\x22]\\x22?)){65,}@)(?:(?:[\\x21\\x23-\\x27\\x2A\\x2B\\x2D\\x2F-\\x39\\x3D\\x3F\\x5E-\\x7E\\pL\\pN]+)|(?:\\x22(?:[\\x01-\\x08\\x0B\\x0C\\x0E-\\x1F\\x21\\x23-\\x5B\\x5D-\\x7F\\pL\\pN]|(?:\\x5C[\\x00-\\x7F]))*\\x22))(?:\\.(?:(?:[\\x21\\x23-\\x27\\x2A\\x2B\\x2D\\x2F-\\x39\\x3D\\x3F\\x5E-\\x7E\\pL\\pN]+)|(?:\\x22(?:[\\x01-\\x08\\x0B\\x0C\\x0E-\\x1F\\x21\\x23-\\x5B\\x5D-\\x7F\\pL\\pN]|(?:\\x5C[\\x00-\\x7F]))*\\x22)))*@(?:(?:(?!.*[^.]{64,})(?:(?:(?:xn--)?[a-z0-9]+(?:-+[a-z0-9]+)*\\.){1,126}){1,}(?:(?:[a-z][a-z0-9]*)|(?:(?:xn--)[a-z0-9]+))(?:-+[a-z0-9]+)*)|(?:\\[(?:(?:IPv6:(?:(?:[a-f0-9]{1,4}(?::[a-f0-9]{1,4}){7})|(?:(?!(?:.*[a-f0-9][:\\]]){7,})(?:[a-f0-9]{1,4}(?::[a-f0-9]{1,4}){0,5})?::(?:[a-f0-9]{1,4}(?::[a-f0-9]{1,4}){0,5})?)))|(?:(?:IPv6:(?:(?:[a-f0-9]{1,4}(?::[a-f0-9]{1,4}){5}:)|(?:(?!(?:.*[a-f0-9]:){5,})(?:[a-f0-9]{1,4}(?::[a-f0-9]{1,4}){0,3})?::(?:[a-f0-9]{1,4}(?::[a-f0-9]{1,4}){0,3}:)?)))?(?:(?:25[0-5])|(?:2[0-4][0-9])|(?:1[0-9]{2})|(?:[1-9]?[0-9]))(?:\\.(?:(?:25[0-5])|(?:2[0-4][0-9])|(?:1[0-9]{2})|(?:[1-9]?[0-9]))){3}))\\]))$/iDu";
+	} else {
+		const char regexp[] = "/^(?!(?:(?:\\x22?\\x5C[\\x00-\\x7E]\\x22?)|(?:\\x22?[^\\x5C\\x22]\\x22?)){255,})(?!(?:(?:\\x22?\\x5C[\\x00-\\x7E]\\x22?)|(?:\\x22?[^\\x5C\\x22]\\x22?)){65,}@)(?:(?:[\\x21\\x23-\\x27\\x2A\\x2B\\x2D\\x2F-\\x39\\x3D\\x3F\\x5E-\\x7E]+)|(?:\\x22(?:[\\x01-\\x08\\x0B\\x0C\\x0E-\\x1F\\x21\\x23-\\x5B\\x5D-\\x7F]|(?:\\x5C[\\x00-\\x7F]))*\\x22))(?:\\.(?:(?:[\\x21\\x23-\\x27\\x2A\\x2B\\x2D\\x2F-\\x39\\x3D\\x3F\\x5E-\\x7E]+)|(?:\\x22(?:[\\x01-\\x08\\x0B\\x0C\\x0E-\\x1F\\x21\\x23-\\x5B\\x5D-\\x7F]|(?:\\x5C[\\x00-\\x7F]))*\\x22)))*@(?:(?:(?!.*[^.]{64,})(?:(?:(?:xn--)?[a-z0-9]+(?:-+[a-z0-9]+)*\\.){1,126}){1,}(?:(?:[a-z][a-z0-9]*)|(?:(?:xn--)[a-z0-9]+))(?:-+[a-z0-9]+)*)|(?:\\[(?:(?:IPv6:(?:(?:[a-f0-9]{1,4}(?::[a-f0-9]{1,4}){7})|(?:(?!(?:.*[a-f0-9][:\\]]){7,})(?:[a-f0-9]{1,4}(?::[a-f0-9]{1,4}){0,5})?::(?:[a-f0-9]{1,4}(?::[a-f0-9]{1,4}){0,5})?)))|(?:(?:IPv6:(?:(?:[a-f0-9]{1,4}(?::[a-f0-9]{1,4}){5}:)|(?:(?!(?:.*[a-f0-9]:){5,})(?:[a-f0-9]{1,4}(?::[a-f0-9]{1,4}){0,3})?::(?:[a-f0-9]{1,4}(?::[a-f0-9]{1,4}){0,3}:)?)))?(?:(?:25[0-5])|(?:2[0-4][0-9])|(?:1[0-9]{2})|(?:[1-9]?[0-9]))(?:\\.(?:(?:25[0-5])|(?:2[0-4][0-9])|(?:1[0-9]{2})|(?:[1-9]?[0-9]))){3}))\\]))$/iD";
+	}
+
 	pcre       *re = NULL;
 	pcre_extra *pcre_extra = NULL;
 	int preg_options = 0;

diff --git a/ext/filter/tests/058.phpt b/ext/filter/tests/058.phpt
@@ -0,0 +1,57 @@
+--TEST--
+FILTER_VALIDATE_EMAIL unicode support (https://tools.ietf.org/html/rfc6531)
+--SKIPIF--
+<?php if (!extension_loaded("filter")) die("skip"); ?>
+--FILE--
+<?php
+$values = Array(
+'niceä[email protected]',
+'véry.ç[email protected]',
+'a.lîttle.lengthy.but.fiñ[email protected]',
+'dîsposable.style.é[email protected]',
+'other.é[email protected]',
+'üser@[IPv6:2001:db8:1ff::a0b:dbd0]',
+'"verî.uñ[email protected]ñusual.com"@example.com',
+'"verî.(),:;<>[]\".VERÎ.\"verî@\ \"verî\".unüsual"@strange.example.com',
+'té[email protected]',
+'té[email protected]',
+'té[email protected]',
+'té[email protected]',
+'té[email protected]',
+'tést@[255.255.255.255]',
+'tést@[IPv6:2001:0db8:85a3:08d3:1319:8a2e:0370:7344]',
+'tést@[IPv6:2001::7344]',
+'tést@[IPv6:1111:2222:3333:4444:5555:6666:255.255.255.255]',
+'té[email protected]',
+'üñîçøðé@example.com',
+'"üñîçøðé"@example.com',
+'ǅǼ੧ఘⅧ⒇৪@example.com',
+);
+foreach ($values as $value) {
+	var_dump(filter_var($value, FILTER_VALIDATE_EMAIL, FILTER_FLAG_EMAIL_RFC6531));
+}
+echo "Done\n";
+?>
+--EXPECT--
+string(26) "niceä[email protected]"
+string(25) "véry.ç[email protected]"
+string(44) "a.lîttle.lengthy.but.fiñ[email protected]"
+string(48) "dîsposable.style.é[email protected]"
+string(34) "other.é[email protected]"
+string(35) "üser@[IPv6:2001:db8:1ff::a0b:dbd0]"
+string(43) ""verî.uñ[email protected]ñusual.com"@example.com"
+string(74) ""verî.(),:;<>[]\".VERÎ.\"verî@\ \"verî\".unüsual"@strange.example.com"
+string(17) "té[email protected]"
+string(23) "té[email protected]"
+string(24) "té[email protected]"
+string(18) "té[email protected]"
+string(23) "té[email protected]"
+string(23) "tést@[255.255.255.255]"
+string(52) "tést@[IPv6:2001:0db8:85a3:08d3:1319:8a2e:0370:7344]"
+string(23) "tést@[IPv6:2001::7344]"
+string(58) "tést@[IPv6:1111:2222:3333:4444:5555:6666:255.255.255.255]"
+string(27) "té[email protected]"
+string(26) "üñîçøðé@example.com"
+string(28) ""üñîçøðé"@example.com"
+string(31) "ǅǼ੧ఘⅧ⒇৪@example.com"
+Done