Ticket #1281: JID validation now more or less follows spec instead of calling e-mail validator

Basic splitting/validation code submitted via http://status.net/wiki/XMPP/JID_validation -- Copyright 2009 Patrick Georgi <patrick@georgi-clan.de> Licensed under ISC-L, which is compatible with everything else that keeps the copyright notice intact.

Added PEAR Net_IDNA package to extlib to handle IDN normalization (also used by Validate's email verifier if present).

* added test suite, supplemented my own test cases with JID validation and normalization test cases from libpurple
* follows XMPP rules for validation of name part
* fixes for normalization with non-ASCII names
* will do domain checks if $config['email']['check_domain'] is on, checking for an XMPP-server SRV record or any lookup. (We don't actually need to ping those direct though.)
* some more obscure stringprep validation rules aren't quite followed yet, but we err on the side of permissiveness.
* we still don't actually let you save your address with a resource on it, as we strip resources when looking up users who've sent us presence or message updates. I would recommend saving the outgoing resource as a separate field if/when we add that..?

1 files changed, 49 insertions, 0 deletions

diff --git a/lib/util.php b/lib/util.php
index 795997868..f4ee26bbf 100644
--- a/lib/util.php
+++ b/lib/util.php
@@ -1397,6 +1397,55 @@ function common_valid_tag($tag)
     return false;
 }
 
+/**
+ * Determine if given domain or address literal is valid
+ * eg for use in JIDs and URLs. Does not check if the domain
+ * exists!
+ * 
+ * @param string $domain
+ * @return boolean valid or not
+ */
+function common_valid_domain($domain)
+{
+    $octet = "(?:25[0-5]|2[0-4][0-9]|1[0-9]{2}|[1-9][0-9]|[0-9])";
+    $ipv4 = "(?:$octet(?:\.$octet){3})";
+    if (preg_match("/^$ipv4$/u", $domain)) return true;
+
+    $group = "(?:[0-9a-f]{1,4})";
+    $ipv6 = "(?:\[($group(?::$group){0,7})?(::)?($group(?::$group){0,7})?\])"; // http://tools.ietf.org/html/rfc3513#section-2.2
+
+    if (preg_match("/^$ipv6$/ui", $domain, $matches)) {
+        $before = explode(":", $matches[1]);
+        $zeroes = $matches[2];
+        $after = explode(":", $matches[3]);
+        if ($zeroes) {
+            $min = 0;
+            $max = 7;
+        } else {
+            $min = 1;
+            $max = 8;
+        }
+        $explicit = count($before) + count($after);
+        if ($explicit < $min || $explicit > $max) {
+            return false;
+        }
+        return true;
+    }
+
+    try {
+        require_once "Net/IDNA.php";
+        $idn = Net_IDNA::getInstance();
+        $domain = $idn->encode($domain);
+    } catch (Exception $e) {
+        return false;
+    }
+
+    $subdomain = "(?:[a-z0-9][a-z0-9-]*)"; // @fixme
+    $fqdn = "(?:$subdomain(?:\.$subdomain)*\.?)";
+
+    return preg_match("/^$fqdn$/ui", $domain);
+}
+
 /* Following functions are copied from MediaWiki GlobalFunctions.php
  * and written by Evan Prodromou. */