language.negotiation.inc

Language negotiation functions.

File

drupal/core/modules/language/language.negotiation.inc
View source
<?php

/**
 * @file
 * Language negotiation functions.
 */

/**
 * The language is determined using path prefix or domain.
 */
const LANGUAGE_NEGOTIATION_URL = 'language-url';

/**
 * The language is set based on the browser language settings.
 */
const LANGUAGE_NEGOTIATION_BROWSER = 'language-browser';

/**
 * The language is determined using the current interface language.
 */
const LANGUAGE_NEGOTIATION_INTERFACE = 'language-interface';

/**
 * If no URL language, language is determined using an already detected one.
 */
const LANGUAGE_NEGOTIATION_URL_FALLBACK = 'language-url-fallback';

/**
 * The language is set based on the user language settings.
 */
const LANGUAGE_NEGOTIATION_USER = 'language-user';

/**
 * The language is set based on the user admin language settings.
 */
const LANGUAGE_NEGOTIATION_USER_ADMIN = 'language-user-admin';

/**
 * The language is set based on the request/session parameters.
 */
const LANGUAGE_NEGOTIATION_SESSION = 'language-session';

/**
 * URL language negotiation: use the path prefix as URL language indicator.
 */
const LANGUAGE_NEGOTIATION_URL_PREFIX = 'path_prefix';

/**
 * URL language negotiation: use the domain as URL language indicator.
 */
const LANGUAGE_NEGOTIATION_URL_DOMAIN = 'domain';

/**
 * Identifies the language from the current interface language.
 *
 * @return
 *   The current interface language code.
 */
function language_from_interface() {
  return language(LANGUAGE_TYPE_INTERFACE)->langcode;
}

/**
 * Identify language from the Accept-language HTTP header we got.
 *
 * The algorithm works as follows:
 * - map browser language codes to Drupal language codes.
 * - order all browser language codes by qvalue from high to low.
 * - add generic browser language codes if they aren't already specified
 *   but with a slightly lower qvalue.
 * - find the most specific Drupal language code with the highest qvalue.
 * - if 2 or more languages are having the same qvalue, respect the order of
 *   them inside the $languages array.
 *
 * We perform browser accept-language parsing only if page cache is disabled,
 * otherwise we would cache a user-specific preference.
 *
 * @param $languages
 *   An array of language objects for enabled languages ordered by weight.
 *
 * @return
 *   A valid language code on success, FALSE otherwise.
 */
function language_from_browser($languages) {
  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"
  $browser_langcodes = array();
  if (preg_match_all('@(?<=[, ]|^)([a-zA-Z-]+|\\*)(?:;q=([0-9.]+))?(?:$|\\s*,\\s*)@', trim($_SERVER['HTTP_ACCEPT_LANGUAGE']), $matches, PREG_SET_ORDER)) {

    // Load custom mappings to support browsers that are sending non standard
    // language codes.
    $mappings = language_get_browser_drupal_langcode_mappings();
    foreach ($matches as $match) {
      if ($mappings) {
        $langcode = strtolower($match[1]);
        foreach ($mappings as $browser_langcode => $drupal_langcode) {
          if ($langcode == $browser_langcode) {
            $match[1] = $drupal_langcode;
          }
        }
      }

      // 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]) ? (double) $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) {

    // For Chinese languages the generic tag is either zh-hans or zh-hant, so we
    // need to handle this separately, we can not split $langcode on the
    // first occurence of '-' otherwise we get a non-existing language zh.
    // All other languages use a langcode without a '-', so we can safely split
    // on the first occurence of it.
    $generic_tag = '';
    if (strlen($langcode) > 7 && (substr($langcode, 0, 7) == 'zh-hant' || substr($langcode, 0, 7) == 'zh-hans')) {
      $generic_tag = substr($langcode, 0, 7);
    }
    else {
      $generic_tag = strtok($langcode, '-');
    }
    if (!empty($generic_tag) && !isset($browser_langcodes[$generic_tag])) {

      // Add the generic langcode, but make sure it has a lower qvalue as the
      // more specific one, so the more specific one gets selected if it's
      // defined by both the browser and Drupal.
      $browser_langcodes[$generic_tag] = $qvalue - 0.1;
    }
  }

  // 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, '-')));

    // Find the best match.
    if ($qvalue > $max_qvalue) {
      $best_match_langcode = $language->langcode;
      $max_qvalue = $qvalue;
    }
  }
  return $best_match_langcode;
}

/**
 * Identify language from the user preferences.
 *
 * @param $languages
 *   An array of valid language objects.
 *
 * @return
 *   A valid language code on success, FALSE otherwise.
 */
function language_from_user($languages) {

  // User preference (only for authenticated users).
  global $user;
  if ($user->uid && !empty($user->preferred_langcode) && isset($languages[$user->preferred_langcode])) {
    return $user->preferred_langcode;
  }

  // No language preference from the user.
  return FALSE;
}

/**
 * Identifies admin language from the user preferences.
 *
 * @param $languages
 *   An array of valid language objects.
 *
 * @return
 *   A valid language code on success, FALSE otherwise.
 */
function language_from_user_admin($languages) {

  // User preference (only for authenticated users).
  global $user;
  if ($user->uid && !empty($user->preferred_admin_langcode) && isset($languages[$user->preferred_admin_langcode]) && path_is_admin(current_path())) {
    return $user->preferred_admin_langcode;
  }

  // No language preference from the user or not on an admin path.
  return FALSE;
}

/**
 * Identify language from a request/session parameter.
 *
 * @param $languages
 *   An array of valid language objects.
 *
 * @return
 *   A valid language code on success, FALSE otherwise.
 */
function language_from_session($languages) {
  $param = config('language.negotiation')
    ->get('session.parameter');

  // Request parameter: we need to update the session parameter only if we have
  // an authenticated user.
  if (isset($_GET[$param]) && isset($languages[$langcode = $_GET[$param]])) {
    global $user;
    if ($user->uid) {
      $_SESSION[$param] = $langcode;
    }
    return $langcode;
  }

  // Session parameter.
  if (isset($_SESSION[$param])) {
    return $_SESSION[$param];
  }
  return FALSE;
}

/**
 * Identify language via URL prefix or domain.
 *
 * @param $languages
 *   An array of valid language objects.
 *
 * @param $request
 *   The HttpRequest object representing the current request.
 *
 * @return
 *   A valid language code on success, FALSE otherwise.
 */
function language_from_url($languages, $request) {
  $language_url = FALSE;
  if (!language_negotiation_method_enabled(LANGUAGE_NEGOTIATION_URL)) {
    return $language_url;
  }
  switch (config('language.negotiation')
    ->get('url.source')) {
    case LANGUAGE_NEGOTIATION_URL_PREFIX:
      $current_path = $request->attributes
        ->get('system_path');
      if (!isset($current_path)) {
        $current_path = trim($request
          ->getPathInfo(), '/');
      }
      list($language, $path) = language_url_split_prefix($current_path, $languages);

      // Store the correct system path, i.e. minus the path prefix, in the
      // request.
      $request->attributes
        ->set('system_path', $path);
      if ($language !== FALSE) {
        $language_url = $language->langcode;
      }
      break;
    case LANGUAGE_NEGOTIATION_URL_DOMAIN:

      // Get only the host, not the port.
      $http_host = $_SERVER['HTTP_HOST'];
      if (strpos($http_host, ':') !== FALSE) {
        $http_host_tmp = explode(':', $http_host);
        $http_host = current($http_host_tmp);
      }
      $domains = language_negotiation_url_domains();
      foreach ($languages as $language) {

        // Skip the check if the language doesn't have a domain.
        if (!empty($domains[$language->langcode])) {

          // Ensure that there is exactly one protocol in the URL when checking
          // the hostname.
          $host = 'http://' . str_replace(array(
            'http://',
            'https://',
          ), '', $domains[$language->langcode]);
          $host = parse_url($host, PHP_URL_HOST);
          if ($http_host == $host) {
            $language_url = $language->langcode;
            break;
          }
        }
      }
      break;
  }
  return $language_url;
}

/**
 * Determines the language to be assigned to URLs when none is detected.
 *
 * The language negotiation process has a fallback chain that ends with the
 * default language negotiation method. Each built-in language type has a
 * separate initialization:
 * - Interface language, which is the only configurable one, always gets a valid
 *   value. If no request-specific language is detected, the default language
 *   will be used.
 * - Content language merely inherits the interface language by default.
 * - URL language is detected from the requested URL and will be used to rewrite
 *   URLs appearing in the page being rendered. If no language can be detected,
 *   there are two possibilities:
 *   - If the default language has no configured path prefix or domain, then the
 *     default language is used. This guarantees that (missing) URL prefixes are
 *     preserved when navigating through the site.
 *   - If the default language has a configured path prefix or domain, a
 *     requested URL having an empty prefix or domain is an anomaly that must be
 *     fixed. This is done by introducing a prefix or domain in the rendered
 *     page matching the detected interface language.
 *
 * @param $languages
 *   (optional) An array of valid language objects. This is passed by
 *   language_negotiation_method_invoke() to every language method callback,
 *   but it is not actually needed here. Defaults to NULL.
 *
 * @param $request
 *   (optional) The HttpRequest object representing the current request.
 *
 * @param $language_type
 *   (optional) The language type to fall back to. Defaults to the interface
 *   language.
 *
 * @return
 *   A valid language code.
 */
function language_url_fallback($language = NULL, $request = NULL, $language_type = LANGUAGE_TYPE_INTERFACE) {
  $default = language_default();
  $prefix = config('language.negotiation')
    ->get('url.source') == LANGUAGE_NEGOTIATION_URL_PREFIX;

  // If the default language is not configured to convey language information,
  // a missing URL language information indicates that URL language should be
  // the default one, otherwise we fall back to an already detected language.
  $domains = language_negotiation_url_domains();
  $prefixes = language_negotiation_url_prefixes();
  if ($prefix && empty($prefixes[$default->langcode]) || !$prefix && empty($domains[$default->langcode])) {
    return $default->langcode;
  }
  else {
    $langcode = language($language_type)->langcode;
    return $langcode;
  }
}

/**
 * Return links for the URL language switcher block.
 *
 * Translation links may be provided by other modules.
 */
function language_switcher_url($type, $path) {
  $languages = language_list();
  $links = array();
  foreach ($languages as $language) {
    $links[$language->langcode] = array(
      'href' => $path,
      'title' => $language->name,
      'language' => $language,
      'attributes' => array(
        'class' => array(
          'language-link',
        ),
      ),
    );
  }
  return $links;
}

/**
 * Return the session language switcher block.
 */
function language_switcher_session($type, $path) {
  $param = config('language.negotiation')
    ->get('session.parameter');
  $language_query = isset($_SESSION[$param]) ? $_SESSION[$param] : language($type)->langcode;
  $languages = language_list();
  $links = array();
  $query = $_GET;
  foreach ($languages as $language) {
    $langcode = $language->langcode;
    $links[$langcode] = array(
      'href' => $path,
      'title' => $language->name,
      'attributes' => array(
        'class' => array(
          'language-link',
        ),
      ),
      'query' => $query,
    );
    if ($language_query != $langcode) {
      $links[$langcode]['query'][$param] = $langcode;
    }
    else {
      $links[$langcode]['attributes']['class'][] = ' session-active';
    }
  }
  return $links;
}

/**
 * Rewrite URLs for the URL language negotiation method.
 */
function language_url_rewrite_url(&$path, &$options) {
  static $drupal_static_fast;
  if (!isset($drupal_static_fast)) {
    $drupal_static_fast['languages'] =& drupal_static(__FUNCTION__);
  }
  $languages =& $drupal_static_fast['languages'];
  if (!isset($languages)) {
    $languages = language_list();
    $languages = array_flip(array_keys($languages));
  }

  // Language can be passed as an option, or we go for current URL language.
  if (!isset($options['language'])) {
    $language_url = language(LANGUAGE_TYPE_URL);
    $options['language'] = $language_url;
  }
  elseif (is_object($options['language']) && !isset($languages[$options['language']->langcode])) {
    unset($options['language']);
    return;
  }
  if (isset($options['language'])) {
    switch (config('language.negotiation')
      ->get('url.source')) {
      case LANGUAGE_NEGOTIATION_URL_DOMAIN:
        $domains = language_negotiation_url_domains();
        if (is_object($options['language']) && !empty($domains[$options['language']->langcode])) {
          global $is_https;

          // Save the original base URL. If it contains a port, we need to
          // retain it below.
          if (!empty($options['base_url'])) {

            // The colon in the URL scheme messes up the port checking below.
            $normalized_base_url = str_replace(array(
              'https://',
              'http://',
            ), '', $options['base_url']);
          }

          // Ask for an absolute URL with our modified base URL.
          $url_scheme = $is_https ? 'https://' : 'http://';
          $options['absolute'] = TRUE;
          $options['base_url'] = $url_scheme . $domains[$options['language']->langcode];

          // In case either the original base URL or the HTTP host contains a
          // port, retain it.
          $http_host = $_SERVER['HTTP_HOST'];
          if (isset($normalized_base_url) && strpos($normalized_base_url, ':') !== FALSE) {
            list($host, $port) = explode(':', $normalized_base_url);
            $options['base_url'] .= ':' . $port;
          }
          elseif (strpos($http_host, ':') !== FALSE) {
            list($host, $port) = explode(':', $http_host);
            $options['base_url'] .= ':' . $port;
          }
          if (isset($options['https']) && variable_get('https', FALSE)) {
            if ($options['https'] === TRUE) {
              $options['base_url'] = str_replace('http://', 'https://', $options['base_url']);
            }
            elseif ($options['https'] === FALSE) {
              $options['base_url'] = str_replace('https://', 'http://', $options['base_url']);
            }
          }
        }
        break;
      case LANGUAGE_NEGOTIATION_URL_PREFIX:
        $prefixes = language_negotiation_url_prefixes();
        if (is_object($options['language']) && !empty($prefixes[$options['language']->langcode])) {
          $options['prefix'] = $prefixes[$options['language']->langcode] . '/';
        }
        break;
    }
  }
}

/**
 * Reads language prefixes and uses the langcode if no prefix is set.
 */
function language_negotiation_url_prefixes() {
  return config('language.negotiation')
    ->get('url.prefixes');
}

/**
 * Update the list of prefixes from the installed languages.
 */
function language_negotiation_url_prefixes_update() {
  $prefixes = language_negotiation_url_prefixes();
  foreach (language_list() as $language) {

    // The prefix for this language should be updated if it's not assigned yet
    // or the prefix is set to the empty string.
    if (empty($prefixes[$language->langcode])) {

      // For the default language, set the prefix to the empty string,
      // otherwise use the langcode.
      $prefixes[$language->langcode] = !empty($language->default) ? '' : $language->langcode;
    }

    // Otherwise we keep the configured prefix.
  }
  language_negotiation_url_prefixes_save($prefixes);
}

/**
 * Saves language prefix settings.
 */
function language_negotiation_url_prefixes_save(array $prefixes) {
  config('language.negotiation')
    ->set('url.prefixes', $prefixes)
    ->save();
}

/**
 * Reads language domains.
 */
function language_negotiation_url_domains() {
  return config('language.negotiation')
    ->get('url.domains');
}

/**
 * Saves the language domain settings.
 */
function language_negotiation_url_domains_save(array $domains) {
  config('language.negotiation')
    ->set('url.domains', $domains)
    ->save();
}

/**
 * Rewrite URLs for the Session language negotiation method.
 */
function language_url_rewrite_session(&$path, &$options) {
  static $query_rewrite, $query_param, $query_value;

  // The following values are not supposed to change during a single page
  // request processing.
  if (!isset($query_rewrite)) {
    global $user;
    if (!$user->uid) {
      $languages = language_list();
      $query_param = check_plain(config('language.negotiation')
        ->get('session.parameter'));
      $query_value = isset($_GET[$query_param]) ? check_plain($_GET[$query_param]) : NULL;
      $query_rewrite = isset($languages[$query_value]) && language_negotiation_method_enabled(LANGUAGE_NEGOTIATION_SESSION);
    }
    else {
      $query_rewrite = FALSE;
    }
  }

  // If the user is anonymous, the user language negotiation method is enabled,
  // and the corresponding option has been set, we must preserve any explicit
  // user language preference even with cookies disabled.
  if ($query_rewrite) {
    if (is_string($options['query'])) {
      $options['query'] = drupal_get_query_array($options['query']);
    }
    if (!isset($options['query'][$query_param])) {
      $options['query'][$query_param] = $query_value;
    }
  }
}

Functions

Namesort descending Description
language_from_browser Identify language from the Accept-language HTTP header we got.
language_from_interface Identifies the language from the current interface language.
language_from_session Identify language from a request/session parameter.
language_from_url Identify language via URL prefix or domain.
language_from_user Identify language from the user preferences.
language_from_user_admin Identifies admin language from the user preferences.
language_negotiation_url_domains Reads language domains.
language_negotiation_url_domains_save Saves the language domain settings.
language_negotiation_url_prefixes Reads language prefixes and uses the langcode if no prefix is set.
language_negotiation_url_prefixes_save Saves language prefix settings.
language_negotiation_url_prefixes_update Update the list of prefixes from the installed languages.
language_switcher_session Return the session language switcher block.
language_switcher_url Return links for the URL language switcher block.
language_url_fallback Determines the language to be assigned to URLs when none is detected.
language_url_rewrite_session Rewrite URLs for the Session language negotiation method.
language_url_rewrite_url Rewrite URLs for the URL language negotiation method.

Constants

Namesort descending Description
LANGUAGE_NEGOTIATION_BROWSER The language is set based on the browser language settings.
LANGUAGE_NEGOTIATION_INTERFACE The language is determined using the current interface language.
LANGUAGE_NEGOTIATION_SESSION The language is set based on the request/session parameters.
LANGUAGE_NEGOTIATION_URL The language is determined using path prefix or domain.
LANGUAGE_NEGOTIATION_URL_DOMAIN URL language negotiation: use the domain as URL language indicator.
LANGUAGE_NEGOTIATION_URL_FALLBACK If no URL language, language is determined using an already detected one.
LANGUAGE_NEGOTIATION_URL_PREFIX URL language negotiation: use the path prefix as URL language indicator.
LANGUAGE_NEGOTIATION_USER The language is set based on the user language settings.
LANGUAGE_NEGOTIATION_USER_ADMIN The language is set based on the user admin language settings.