<?php
/**
- * @file src/Protocol/Feed.php
- * @brief Imports RSS/RDF/Atom feeds
+ * @copyright Copyright (C) 2020, Friendica
+ *
+ * @license GNU AGPL version 3 or any later version
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as
+ * published by the Free Software Foundation, either version 3 of the
+ * License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU Affero General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with this program. If not, see <https://www.gnu.org/licenses/>.
*
*/
+
namespace Friendica\Protocol;
use DOMDocument;
use Friendica\Database\DBA;
use Friendica\DI;
use Friendica\Model\Item;
+use Friendica\Model\Tag;
use Friendica\Util\Network;
use Friendica\Util\ParseUrl;
use Friendica\Util\XML;
/**
- * @brief This class contain functions to import feeds
- *
+ * This class contain functions to import feeds (RSS/RDF/Atom)
*/
class Feed {
/**
- * @brief Read a RSS/RDF/Atom feed and create an item entry for it
+ * Read a RSS/RDF/Atom feed and create an item entry for it
*
* @param string $xml The feed data
* @param array $importer The user record of the importer
* @param array $contact The contact record of the feed
- * @param string $hub Unused dummy value for compatibility reasons
- * @param bool $simulate If enabled, no data is imported
*
- * @return array In simulation mode it returns the header and the first item
+ * @return array Returns the header and the first item in dry run mode
* @throws \Friendica\Network\HTTPException\InternalServerErrorException
*/
- public static function import($xml, $importer, &$contact, &$hub, $simulate = false)
+ public static function import($xml, array $importer = [], array $contact = [])
{
- $a = \get_app();
+ $dryRun = empty($importer) && empty($contact);
- if (!$simulate) {
- Logger::log("Import Atom/RSS feed '" . $contact["name"] . "' (Contact " . $contact["id"] . ") for user " . $importer["uid"], Logger::DEBUG);
+ if ($dryRun) {
+ Logger::info("Test Atom/RSS feed");
} else {
- Logger::log("Test Atom/RSS feed", Logger::DEBUG);
+ Logger::info("Import Atom/RSS feed '" . $contact["name"] . "' (Contact " . $contact["id"] . ") for user " . $importer["uid"]);
}
if (empty($xml)) {
- Logger::log('XML is empty.', Logger::DEBUG);
- return;
+ Logger::info('XML is empty.');
+ return [];
}
if (!empty($contact['poll'])) {
$author["author-name"] = $value;
}
- if ($simulate) {
+ if ($dryRun) {
$author["author-id"] = XML::getFirstNodeValue($xpath, '/atom:feed/atom:author/atom:id/text()');
// See https://tools.ietf.org/html/rfc4287#section-3.2.2
$entries = $xpath->query('/rss/channel/item');
}
- if (!$simulate) {
+ if (!$dryRun) {
$author["author-link"] = $contact["url"];
if (empty($author["author-name"])) {
}
$header = [];
- $header["uid"] = $importer["uid"];
+ $header["uid"] = $importer["uid"] ?? 0;
$header["network"] = Protocol::FEED;
$header["wall"] = 0;
$header["origin"] = 0;
$header["gravity"] = GRAVITY_PARENT;
- $header["private"] = 2;
+ $header["private"] = Item::PUBLIC;
$header["verb"] = Activity::POST;
$header["object-type"] = Activity\ObjectType::NOTE;
- $header["contact-id"] = $contact["id"];
+ $header["contact-id"] = $contact["id"] ?? 0;
if (!is_object($entries)) {
- Logger::log("There are no entries in this feed.", Logger::DEBUG);
- return;
+ Logger::info("There are no entries in this feed.");
+ return [];
}
$items = [];
+
+ // Limit the number of items that are about to be fetched
+ $total_items = ($entries->length - 1);
+ $max_items = DI::config()->get('system', 'max_feed_items');
+ if (($max_items > 0) && ($total_items > $max_items)) {
+ $total_items = $max_items;
+ }
+
// Importing older entries first
- for ($i = $entries->length - 1; $i >= 0; --$i) {
+ for ($i = $total_items; $i >= 0; --$i) {
$entry = $entries->item($i);
$item = array_merge($header, $author);
$item["parent-uri"] = $item["uri"];
- if (!$simulate) {
+ if (!$dryRun) {
$condition = ["`uid` = ? AND `uri` = ? AND `network` IN (?, ?)",
$importer["uid"], $item["uri"], Protocol::FEED, Protocol::DFRN];
$previous = Item::selectFirst(['id'], $condition);
if (DBA::isResult($previous)) {
- Logger::log("Item with uri " . $item["uri"] . " for user " . $importer["uid"] . " already existed under id " . $previous["id"], Logger::DEBUG);
+ Logger::info("Item with uri " . $item["uri"] . " for user " . $importer["uid"] . " already existed under id " . $previous["id"]);
continue;
}
}
$item["attach"] .= '[attach]href="' . $href . '" length="' . $length . '" type="' . $type . '"[/attach]';
}
- $tags = '';
+ $taglist = [];
$categories = $xpath->query("category", $entry);
foreach ($categories AS $category) {
- $hashtag = $category->nodeValue;
- if ($tags != '') {
- $tags .= ', ';
- }
-
- $taglink = "#[url=" . DI::baseUrl() . "/search?tag=" . $hashtag . "]" . $hashtag . "[/url]";
- $tags .= $taglink;
+ $taglist[] = $category->nodeValue;
}
$body = trim(XML::getFirstNodeValue($xpath, 'atom:content/text()', $entry));
// We always strip the title since it will be added in the page information
$item["title"] = "";
- $item["body"] = $item["body"] . add_page_info($item["plink"], false, $preview, ($contact["fetch_further_information"] == 2), $contact["ffi_keyword_blacklist"]);
- $item["tag"] = add_page_keywords($item["plink"], $preview, ($contact["fetch_further_information"] == 2), $contact["ffi_keyword_blacklist"]);
+ $item["body"] = $item["body"] . add_page_info($item["plink"], false, $preview, ($contact["fetch_further_information"] == 2), $contact["ffi_keyword_denylist"]);
+ $taglist = get_page_keywords($item["plink"], $preview, ($contact["fetch_further_information"] == 2), $contact["ffi_keyword_denylist"]);
$item["object-type"] = Activity\ObjectType::BOOKMARK;
unset($item["attach"]);
} else {
$item["body"] = '[abstract]' . HTML::toBBCode($summary, $basepath) . "[/abstract]\n" . $item["body"];
}
- if ($contact["fetch_further_information"] == 3) {
- if (!empty($tags)) {
- $item["tag"] = $tags;
- } else {
- // @todo $preview is never set in this case, is it intended? - @MrPetovan 2018-02-13
- $item["tag"] = add_page_keywords($item["plink"], $preview, true, $contact["ffi_keyword_blacklist"]);
+ if (!empty($contact["fetch_further_information"]) && ($contact["fetch_further_information"] == 3)) {
+ if (empty($taglist)) {
+ $taglist = get_page_keywords($item["plink"], $preview, true, $contact["ffi_keyword_denylist"]);
}
- $item["body"] .= "\n" . $item['tag'];
+ $item["body"] .= "\n" . self::tagToString($taglist);
+ } else {
+ $taglist = [];
}
// Add the link to the original feed entry if not present in feed
}
}
- if (!$simulate) {
- Logger::log("Stored feed: " . print_r($item, true), Logger::DEBUG);
+ if ($dryRun) {
+ $items[] = $item;
+ break;
+ } else {
+ Logger::info("Stored feed: " . print_r($item, true));
$notify = Item::isRemoteSelf($contact, $item);
$notify = PRIORITY_MEDIUM;
}
- $id = Item::insert($item, false, $notify);
+ $id = Item::insert($item, $notify);
- Logger::log("Feed for contact " . $contact["url"] . " stored under id " . $id);
- } else {
- $items[] = $item;
- }
-
- if ($simulate) {
- break;
+ Logger::info("Feed for contact " . $contact["url"] . " stored under id " . $id);
+
+ if (!empty($id) && !empty($taglist)) {
+ $feeditem = Item::selectFirst(['uri-id'], ['id' => $id]);
+ foreach ($taglist as $tag) {
+ Tag::store($feeditem['uri-id'], Tag::HASHTAG, $tag);
+ }
+ }
}
}
- if ($simulate) {
- return ["header" => $author, "items" => $items];
+ return ["header" => $author, "items" => $items];
+ }
+
+ /**
+ * Convert a tag array to a tag string
+ *
+ * @param array $tags
+ * @return string tag string
+ */
+ private static function tagToString(array $tags)
+ {
+ $tagstr = '';
+
+ foreach ($tags as $tag) {
+ if ($tagstr != "") {
+ $tagstr .= ", ";
+ }
+
+ $tagstr .= "#[url=" . DI::baseUrl() . "/search?tag=" . urlencode($tag) . "]" . $tag . "[/url]";
}
+
+ return $tagstr;
}
private static function titleIsBody($title, $body)