Index: includes/language.inc
===================================================================
RCS file: /cvs/drupal/drupal/includes/language.inc,v
retrieving revision 1.14
diff -u -p -r1.14 language.inc
--- includes/language.inc	6 Jan 2008 16:46:02 -0000	1.14
+++ includes/language.inc	3 Sep 2008 11:05:50 -0000
@@ -70,32 +70,48 @@ function language_initialize() {
  * Identify language from the Accept-language HTTP header we got.
  */
 function language_from_browser() {
-  // Specified by the user via the browser's Accept Language setting
-  // Samples: "hu, en-us;q=0.66, en;q=0.33", "hu,en-us;q=0.5"
-  $browser_langs = array();
-
-  if (isset($_SERVER['HTTP_ACCEPT_LANGUAGE'])) {
-    $browser_accept = explode(",", $_SERVER['HTTP_ACCEPT_LANGUAGE']);
-    for ($i = 0; $i < count($browser_accept); $i++) {
-      // The language part is either a code or a code with a quality.
-      // We cannot do anything with a * code, so it is skipped.
-      // If the quality is missing, it is assumed to be 1 according to the RFC.
-      if (preg_match("!([a-z-]+)(;q=([0-9\\.]+))?!", trim($browser_accept[$i]), $found)) {
-        $browser_langs[$found[1]] = (isset($found[3]) ? (float) $found[3] : 1.0);
-      }
-    }
+  if (!isset($_SERVER['HTTP_ACCEPT_LANGUAGE'])) {
+    return;
   }
 
-  // Order the codes by quality
-  arsort($browser_langs);
+  $browser_langs = array();  
+  if (preg_match_all('@([a-zA-Z]{1,8}(?:-[a-zA-Z]{1,8})?|\*)(?:;q=(1(?:\.000)?|0(?:\.[0-9]{0,3})?))?\s*,?\s*@', $_SERVER['HTTP_ACCEPT_LANGUAGE'], $matches, PREG_SET_ORDER)) {
+    foreach ($matches as $match) {
+      // We can safely use strtolower() here, tags are ASCII.
+      // RFC2616 mandates that the decimal part is no more than three digits,
+      // so we multiply the qvalue by 1000 to avoid floating point comparisons.
+      $browser_langs[strtolower($match[1])] = isset($match[2]) ? (int) ((float) $match[2] * 1000) : 1000;
+    }
+  }
 
-  // Try to find the first preferred language we have
+  // Find the enabled language with the greatest qvalue, following the rules
+  // of RFC2616 (section 14.4). If several languages have the same qvalue,
+  // prefer the one with the greatest weight.
   $languages = language_list('enabled');
-  foreach ($browser_langs as $langcode => $q) {
-    if (isset($languages['1'][$langcode])) {
-      return $languages['1'][$langcode];
+  $best_match = NULL;
+  $max_qvalue = 0;
+  foreach ($languages['1'] as $langcode => $language) {
+    // Language tags are case insensitive (RFC2616, sec 3.10).
+    $langcode = strtolower($langcode);
+    $qvalue = NULL;
+    if (isset($browser_langs[$langcode])) {
+      $qvalue = $browser_langs[$langcode];
+    }
+    else if ((($prefix = strtok($langcode, '-')) != $langcode) && isset($browser_langs[$prefix])) {
+      $qvalue = $browser_langs[$prefix];
+    }
+    else if (isset($browser_langs['*'])) {
+      $qvalue = $browser_langs['*'];
+    }
+    
+    if (!is_null($qvalue)) {
+      if ($qvalue > $max_qvalue) {
+        $best_match = $language;
+        $max_qvalue = $qvalue;
+      }
     }
   }
+  return $best_match;
 }
 
 /**