drupal/core/modules/aggregator/aggregator.module

178 lines
7.7 KiB
Plaintext
Raw Normal View History

- Rewrote the headline module from scratch. Note that the old headline code is still in place 'till the new code has proven to be stable. See "syndication.module" for the new code. Changes: + Improved the parser and tested it against RSS 0.9, RSS 0.91, RSS 0.92, RSS 1.0, RDF and XML feeds. + Improved the administration interface. It might be a bit fuzzy at first. Maybe some native English like Julian, Michael (or any one else with knowledge in the field) can help out by suggesting better naming, terminology or descriptions - as well as by writing the help section for this module? I'd have no idea how much this would be appreciated. + We can *easily* recognize new tags or extensions: we parse out "link", "title", "description" and "author" right now, but we will have to revise which tags to support and which not. New tags can be added in less than 10 minutes (if you are familiar with the code). Read: we have something we can build on. + Within each item, tags can now appear is random order which is or was not the case with the old headline code where we expect <link>s prior to <description>s for example. + Feed updates only (ie. always) happen through cron. Neither do we use one global cron for updating all feeds; instead, every feed can specify his own update-interval. + Newly fetched headlines are "appended" to the pool of existing headlines (read: we don't replace the whole feed), and headlines automatically "expire" after x days or hours. (Every headline has a timestamp.) + Got rid of backend.class; it is integrated in the module. + Switched to more generic names: "headline" became "item" and "backend" became "feed". This should ease future non-headline oriented syndication. + You can associate attributes or keyword lists with every feed. At the moment new items will automatically inherit their feeds attributes but in future we can use heuristics to make these attributes "mutate" when and where we see fit. The attributes can be maintained by hand as well. + We don't export any blocks yet; we will soon do as soon this new code has been tested for a bit more. We will only export bundles though so if you want to export by feed/source, you will have to make a source-specific bundle. - Polished a bit on a few other modules: nothing major.
2001-05-26 18:26:56 +00:00
<?php
/**
* @file
* Used to aggregate syndicated content (RSS, RDF, and Atom).
*/
use Drupal\aggregator\Entity\Feed;
use Drupal\Core\Routing\RouteMatchInterface;
/**
* Denotes that a feed's items should never expire.
*/
const AGGREGATOR_CLEAR_NEVER = 0;
/**
* Implements hook_help().
*/
function aggregator_help($route_name, RouteMatchInterface $route_match) {
switch ($route_name) {
case 'help.page.aggregator':
$path_validator = \Drupal::pathValidator();
$output = '';
$output .= '<h3>' . t('About') . '</h3>';
$output .= '<p>' . t('The Aggregator module is an on-site syndicator and news reader that gathers and displays fresh content from RSS-, RDF-, and Atom-based feeds made available across the web. Thousands of sites (particularly news sites and blogs) publish their latest headlines in feeds, using a number of standardized XML-based formats. For more information, see the <a href="!aggregator-module">online documentation for the Aggregator module</a>.', array('!aggregator-module' => 'https://www.drupal.org/documentation/modules/aggregator')) . '</p>';
$output .= '<h3>' . t('Uses') . '</h3>';
$output .= '<dl>';
// Check if the aggregator sources View is enabled.
if ($url = $path_validator->getUrlIfValid('aggregator/sources')) {
$output .= '<dt>' . t('Viewing feeds') . '</dt>';
$output .= '<dd>' . t('Users view feed content in the <a href="!aggregator">main aggregator display</a>, or by <a href="!aggregator-sources">their source</a> (usually via an RSS feed reader). The most recent content in a feed can be displayed as a block through the <a href="!admin-block">Blocks administration page</a>.', array('!aggregator' => \Drupal::url('aggregator.page_last'), '!aggregator-sources' => $url->toString(), '!admin-block' => (\Drupal::moduleHandler()->moduleExists('block')) ? \Drupal::url('block.admin_display') : '#')) . '</dd>';
}
$output .= '<dt>' . t('Adding, editing, and deleting feeds') . '</dt>';
$output .= '<dd>' . t('Administrators can add, edit, and delete feeds, and choose how often to check each feed for newly updated items on the <a href="!feededit">Feed aggregator administration page</a>.', array('!feededit' => \Drupal::url('aggregator.admin_overview'))) . '</dd>';
$output .= '<dt>' . t('<abbr title="Outline Processor Markup Language">OPML</abbr> integration') . '</dt>';
// Check if the aggregator opml View is enabled.
if ($url = $path_validator->getUrlIfValid('aggregator/opml')) {
$output .= '<dd>' . t('A <a href="!aggregator-opml">machine-readable OPML file</a> of all feeds is available. OPML is an XML-based file format used to share outline-structured information such as a list of RSS feeds. Feeds can also be <a href="!import-opml">imported via an OPML file</a>.', array('!aggregator-opml' => $url->toString(), '!import-opml' => \Drupal::url('aggregator.opml_add'))) . '</dd>';
}
$output .= '<dt>' . t('Configuring cron') . '</dt>';
$output .= '<dd>' . t('A working <a href="!cron">cron maintenance task</a> is required to update feeds automatically.', array('!cron' => \Drupal::url('system.cron_settings'))) . '</dd>';
$output .= '</dl>';
return $output;
case 'aggregator.admin_overview':
// Don't use placeholders for possibility to change URLs for translators.
$output = '<p>' . t('Many sites publish their headlines and posts in feeds, using a number of standardized XML-based formats. The aggregator supports <a href="http://en.wikipedia.org/wiki/Rss">RSS</a>, <a href="http://en.wikipedia.org/wiki/Resource_Description_Framework">RDF</a>, and <a href="http://en.wikipedia.org/wiki/Atom_%28standard%29">Atom</a>.') . '</p>';
$output .= '<p>' . t('Current feeds are listed below, and <a href="!addfeed">new feeds may be added</a>. For each feed, the <em>latest items</em> block may be enabled at the <a href="!block">blocks administration page</a>.', array('!addfeed' => \Drupal::url('aggregator.feed_add'), '!block' => (\Drupal::moduleHandler()->moduleExists('block')) ? \Drupal::url('block.admin_display') : '#')) . '</p>';
return $output;
case 'aggregator.feed_add':
return '<p>' . t('Add a feed in RSS, RDF or Atom format. A feed may only have one entry.') . '</p>';
case 'aggregator.opml_add':
return '<p>' . t('<abbr title="Outline Processor Markup Language">OPML</abbr> is an XML format for exchanging feeds between aggregators. A single OPML document may contain many feeds. Aggregator uses this file to import all feeds at once. Upload a file from your computer or enter a URL where the OPML file can be downloaded.') . '</p>';
}
- Rewrote the headline module from scratch. Note that the old headline code is still in place 'till the new code has proven to be stable. See "syndication.module" for the new code. Changes: + Improved the parser and tested it against RSS 0.9, RSS 0.91, RSS 0.92, RSS 1.0, RDF and XML feeds. + Improved the administration interface. It might be a bit fuzzy at first. Maybe some native English like Julian, Michael (or any one else with knowledge in the field) can help out by suggesting better naming, terminology or descriptions - as well as by writing the help section for this module? I'd have no idea how much this would be appreciated. + We can *easily* recognize new tags or extensions: we parse out "link", "title", "description" and "author" right now, but we will have to revise which tags to support and which not. New tags can be added in less than 10 minutes (if you are familiar with the code). Read: we have something we can build on. + Within each item, tags can now appear is random order which is or was not the case with the old headline code where we expect <link>s prior to <description>s for example. + Feed updates only (ie. always) happen through cron. Neither do we use one global cron for updating all feeds; instead, every feed can specify his own update-interval. + Newly fetched headlines are "appended" to the pool of existing headlines (read: we don't replace the whole feed), and headlines automatically "expire" after x days or hours. (Every headline has a timestamp.) + Got rid of backend.class; it is integrated in the module. + Switched to more generic names: "headline" became "item" and "backend" became "feed". This should ease future non-headline oriented syndication. + You can associate attributes or keyword lists with every feed. At the moment new items will automatically inherit their feeds attributes but in future we can use heuristics to make these attributes "mutate" when and where we see fit. The attributes can be maintained by hand as well. + We don't export any blocks yet; we will soon do as soon this new code has been tested for a bit more. We will only export bundles though so if you want to export by feed/source, you will have to make a source-specific bundle. - Polished a bit on a few other modules: nothing major.
2001-05-26 18:26:56 +00:00
}
/**
* Implements hook_theme().
*/
function aggregator_theme() {
return array(
'aggregator_feed' => array(
'render element' => 'elements',
'file' => 'aggregator.theme.inc',
),
'aggregator_item' => array(
'render element' => 'elements',
'file' => 'aggregator.theme.inc',
),
);
}
/**
* Implements hook_entity_extra_field_info().
*/
function aggregator_entity_extra_field_info() {
$extra = array();
$extra['aggregator_feed']['aggregator_feed'] = array(
'display' => array(
'items' => array(
'label' => t('Items'),
'description' => t('Items associated with this feed'),
'weight' => 0,
),
// @todo Move to a formatter at https://www.drupal.org/node/2339917.
'image' => array(
'label' => t('Image'),
'description' => t('The feed image'),
'weight' => 2,
),
// @todo Move to a formatter at https://www.drupal.org/node/2149845.
'description' => array(
'label' => t('Description'),
'description' => t('The description of this feed'),
'weight' => 3,
),
'more_link' => array(
'label' => t('More link'),
'description' => t('A more link to the feed detail page'),
'weight' => 5,
),
'feed_icon' => array(
'label' => t('Feed icon'),
'description' => t('An icon that links to the feed url'),
'weight' => 6,
),
),
);
$extra['aggregator_item']['aggregator_item'] = array(
'display' => array(
// @todo Move to a formatter at https://www.drupal.org/node/2149845.
'description' => array(
'label' => t('Description'),
'description' => t('The description of this feed item'),
'weight' => 2,
),
),
);
return $extra;
}
/**
* Implements hook_cron().
*
* Queues news feeds for updates once their refresh interval has elapsed.
*/
function aggregator_cron() {
$queue = \Drupal::queue('aggregator_feeds');
$ids = \Drupal::entityManager()->getStorage('aggregator_feed')->getFeedIdsToRefresh();
foreach (Feed::loadMultiple($ids) as $feed) {
if ($queue->createItem($feed)) {
// Add timestamp to avoid queueing item more than once.
$feed->setQueuedTime(REQUEST_TIME);
$feed->save();
}
}
// Delete queued timestamp after 6 hours assuming the update has failed.
$ids = \Drupal::entityQuery('aggregator_feed')
->condition('queued', REQUEST_TIME - (3600 * 6), '<')
->execute();
if ($ids) {
$feeds = Feed::loadMultiple($ids);
foreach ($feeds as $feed) {
$feed->setQueuedTime(0);
$feed->save();
}
}
}
/**
* Gets the list of allowed tags.
*
* @return array
* The list of allowed tags.
*
* @internal
*/
function _aggregator_allowed_tags() {
return preg_split('/\s+|<|>/', \Drupal::config('aggregator.settings')->get('items.allowed_html'), -1, PREG_SPLIT_NO_EMPTY);
}
/**
* Implements hook_preprocess_HOOK() for block templates.
*/
function aggregator_preprocess_block(&$variables) {
if ($variables['configuration']['provider'] == 'aggregator') {
$variables['attributes']['role'] = 'complementary';
}
}