Issue #221712 by Damien Tournoud, Gábor Hojtsy, iliphil, Bodo Maass, idflood, loganfsmyth: Fixed locale_language_from_browser() doesn't parse language tags correctly, has a broken logic.

1 files changed, 63 insertions, 20 deletions

diff --git a/includes/locale.inc b/includes/locale.inc
index 99abdfa44..6ebb8972c 100644
--- a/includes/locale.inc
+++ b/includes/locale.inc
@@ -93,39 +93,82 @@ function locale_language_from_interface() {
  * otherwise we would cache a user-specific preference.
  *
  * @param $languages
- *   An array of valid language objects.
+ *   An array of language objects for enabled languages ordered by weight.
  *
  * @return
  *   A valid language code on success, FALSE otherwise.
  */
 function locale_language_from_browser($languages) {
-  // Specified by the user via the browser's Accept Language setting
+  if (empty($_SERVER['HTTP_ACCEPT_LANGUAGE'])) {
+    return FALSE;
+  }
+
+  // The Accept-Language header contains information about the language
+  // preferences configured in the user's browser / operating system.
+  // RFC 2616 (section 14.4) defines the Accept-Language header as follows:
+  //   Accept-Language = "Accept-Language" ":"
+  //                  1#( language-range [ ";" "q" "=" qvalue ] )
+  //   language-range  = ( ( 1*8ALPHA *( "-" 1*8ALPHA ) ) | "*" )
   // 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(",", $_SERVER['HTTP_ACCEPT_LANGUAGE']);
-    foreach ($browser_accept as $langpart) {
-      // The language part is either a code or a code with a quality.
-      // We cannot do anything with a * code, so it is skipped.
-      // If the quality is missing, it is assumed to be 1 according to the RFC.
-      if (preg_match("!([a-z-]+)(;q=([0-9\\.]+))?!", trim($langpart), $found)) {
-        $browser_langs[$found[1]] = (isset($found[3]) ? (float) $found[3] : 1.0);
-      }
+  $browser_langcodes = array();
+  if (preg_match_all('@([a-zA-Z-]+|\*)(?:;q=([0-9.]+))?(?:$|\s*,\s*)@', trim($_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.
+      $langcode = strtolower($match[1]);
+      $qvalue = isset($match[2]) ? (float) $match[2] : 1;
+      $browser_langcodes[$langcode] = (int) ($qvalue * 1000);
+    }
+  }
+
+  // We should take pristine values from the HTTP headers, but Internet Explorer
+  // from version 7 sends only specific language tags (eg. fr-CA) without the
+  // corresponding generic tag (fr) unless explicitly configured. In that case,
+  // we assume that the lowest value of the specific tags is the value of the
+  // generic language to be as close to the HTTP 1.1 spec as possible.
+  // See http://www.w3.org/Protocols/rfc2616/rfc2616-sec14.html#sec14.4 and
+  // http://blogs.msdn.com/b/ie/archive/2006/10/17/accept-language-header-for-internet-explorer-7.aspx
+  asort($browser_langcodes);
+  foreach ($browser_langcodes as $langcode => $qvalue) {
+    $generic_tag = strtok($langcode, '-');
+    if (!isset($browser_langcodes[$generic_tag])) {
+      $browser_langcodes[$generic_tag] = $qvalue;
     }
   }
 
-  // Order the codes by quality
-  arsort($browser_langs);
+  // Find the enabled language with the greatest qvalue, following the rules
+  // of RFC 2616 (section 14.4). If several languages have the same qvalue,
+  // prefer the one with the greatest weight.
+  $best_match_langcode = FALSE;
+  $max_qvalue = 0;
+  foreach ($languages as $langcode => $language) {
+    // Language tags are case insensitive (RFC2616, sec 3.10).
+    $langcode = strtolower($langcode);
+
+    // If nothing matches below, the default qvalue is the one of the wildcard
+    // language, if set, or is 0 (which will never match).
+    $qvalue = isset($browser_langcodes['*']) ? $browser_langcodes['*'] : 0;
+
+    // Find the longest possible prefix of the browser-supplied language
+    // ('the language-range') that matches this site language ('the language tag').
+    $prefix = $langcode;
+    do {
+      if (isset($browser_langcodes[$prefix])) {
+        $qvalue = $browser_langcodes[$prefix];
+        break;
+      }
+    }
+    while ($prefix = substr($prefix, 0, strrpos($prefix, '-')));
 
-  // Try to find the first preferred language we have
-  foreach ($browser_langs as $langcode => $q) {
-    if (isset($languages[$langcode])) {
-      return $langcode;
+    // Find the best match.
+    if ($qvalue > $max_qvalue) {
+      $best_match_langcode = $language->language;
+      $max_qvalue = $qvalue;
     }
   }
 
-  return FALSE;
+  return $best_match_langcode;
 }
 
 /**