friendica/src/Protocol/Feed.php

637 lines
20 KiB
PHP
Raw Normal View History

<?php
2017-12-13 02:03:42 -05:00
/**
* @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/>.
2017-12-13 02:03:42 -05:00
*
*/
2017-12-13 02:03:42 -05:00
namespace Friendica\Protocol;
use DOMDocument;
use DOMXPath;
use Friendica\Content\Text\HTML;
2018-10-29 17:20:46 -04:00
use Friendica\Core\Logger;
use Friendica\Core\Protocol;
use Friendica\Database\DBA;
use Friendica\DI;
use Friendica\Model\Item;
use Friendica\Model\Tag;
use Friendica\Util\Network;
2020-01-03 09:09:03 -05:00
use Friendica\Util\ParseUrl;
2018-07-08 09:39:48 -04:00
use Friendica\Util\XML;
2018-03-08 14:58:35 -05:00
2016-02-16 02:06:55 -05:00
/**
* This class contain functions to import feeds (RSS/RDF/Atom)
2016-02-16 02:06:55 -05:00
*/
class Feed
{
/**
* consume - process atom feed and update anything/everything we might need to update
*
* $xml = the (atom) feed to consume - RSS isn't as fully supported but may work for simple feeds.
*
* $importer = the contact_record (joined to user_record) of the local user who owns this relationship.
* It is this person's stuff that is going to be updated.
* $contact = the person who is sending us stuff. If not set, we MAY be processing a "follow" activity
* from an external network and MAY create an appropriate contact record. Otherwise, we MUST
* have a contact record.
* $hub = should we find a hub declation in the feed, pass it back to our calling process, who might (or
* might not) try and subscribe to it.
* $datedir sorts in reverse order
* $pass - by default ($pass = 0) we cannot guarantee that a parent item has been
* imported prior to its children being seen in the stream unless we are certain
* of how the feed is arranged/ordered.
* With $pass = 1, we only pull parent items out of the stream.
* With $pass = 2, we only pull children (comments/likes).
*
* So running this twice, first with pass 1 and then with pass 2 will do the right
* thing regardless of feed ordering. This won't be adequate in a fully-threaded
* model where comments can have sub-threads. That would require some massive sorting
* to get all the feed items into a mostly linear ordering, and might still require
* recursion.
*
* @param $xml
* @param array $importer
* @param array $contact
* @param $hub
* @throws ImagickException
* @throws \Friendica\Network\HTTPException\InternalServerErrorException
*/
public static function consume($xml, array $importer, array $contact, &$hub)
{
if ($contact['network'] === Protocol::OSTATUS) {
Logger::log('Consume OStatus messages ', Logger::DEBUG);
OStatus::import($xml, $importer, $contact, $hub);
return;
}
if ($contact['network'] === Protocol::FEED) {
Logger::log('Consume feeds', Logger::DEBUG);
self::import($xml, $importer, $contact);
return;
}
if ($contact['network'] === Protocol::DFRN) {
Logger::log('Consume DFRN messages', Logger::DEBUG);
$dfrn_importer = DFRN::getImporter($contact['id'], $importer['uid']);
if (!empty($dfrn_importer)) {
Logger::log('Now import the DFRN feed');
DFRN::import($xml, $dfrn_importer, true);
return;
}
}
}
2017-12-13 02:03:42 -05:00
/**
2020-01-19 01:05:23 -05:00
* Read a RSS/RDF/Atom feed and create an item entry for it
2017-12-13 02:03:42 -05:00
*
2019-01-06 16:06:53 -05:00
* @param string $xml The feed data
* @param array $importer The user record of the importer
* @param array $contact The contact record of the feed
2017-12-13 02:03:42 -05:00
*
* @return array Returns the header and the first item in dry run mode
2019-01-06 16:06:53 -05:00
* @throws \Friendica\Network\HTTPException\InternalServerErrorException
2017-12-13 02:03:42 -05:00
*/
public static function import($xml, array $importer = [], array $contact = [])
2020-01-03 09:09:03 -05:00
{
$dryRun = empty($importer) && empty($contact);
2017-12-13 02:03:42 -05:00
if ($dryRun) {
Logger::info("Test Atom/RSS feed");
2017-12-13 02:03:42 -05:00
} else {
Logger::info("Import Atom/RSS feed '" . $contact["name"] . "' (Contact " . $contact["id"] . ") for user " . $importer["uid"]);
2017-12-13 02:03:42 -05:00
}
2020-01-03 09:09:03 -05:00
if (empty($xml)) {
Logger::info('XML is empty.');
return [];
2017-12-13 02:03:42 -05:00
}
2017-12-13 02:03:42 -05:00
if (!empty($contact['poll'])) {
$basepath = $contact['poll'];
} elseif (!empty($contact['url'])) {
$basepath = $contact['url'];
} else {
$basepath = '';
}
2017-12-13 02:03:42 -05:00
$doc = new DOMDocument();
@$doc->loadXML(trim($xml));
$xpath = new DOMXPath($doc);
2019-10-24 18:32:35 -04:00
$xpath->registerNamespace('atom', ActivityNamespace::ATOM1);
2017-12-13 02:03:42 -05:00
$xpath->registerNamespace('dc', "http://purl.org/dc/elements/1.1/");
$xpath->registerNamespace('content', "http://purl.org/rss/1.0/modules/content/");
$xpath->registerNamespace('rdf', "http://www.w3.org/1999/02/22-rdf-syntax-ns#");
$xpath->registerNamespace('rss', "http://purl.org/rss/1.0/");
$xpath->registerNamespace('media', "http://search.yahoo.com/mrss/");
2019-10-24 18:32:35 -04:00
$xpath->registerNamespace('poco', ActivityNamespace::POCO);
$author = [];
$entries = null;
2017-12-13 02:03:42 -05:00
// Is it RDF?
if ($xpath->query('/rdf:RDF/rss:channel')->length > 0) {
$author["author-link"] = XML::getFirstNodeValue($xpath, '/rdf:RDF/rss:channel/rss:link/text()');
$author["author-name"] = XML::getFirstNodeValue($xpath, '/rdf:RDF/rss:channel/rss:title/text()');
if (empty($author["author-name"])) {
$author["author-name"] = XML::getFirstNodeValue($xpath, '/rdf:RDF/rss:channel/rss:description/text()');
2017-03-15 02:00:22 -04:00
}
2017-12-13 02:03:42 -05:00
$entries = $xpath->query('/rdf:RDF/rss:item');
2017-03-15 02:00:22 -04:00
}
2017-12-13 02:03:42 -05:00
// Is it Atom?
if ($xpath->query('/atom:feed')->length > 0) {
$alternate = XML::getFirstAttributes($xpath, "atom:link[@rel='alternate']");
2017-12-13 02:03:42 -05:00
if (is_object($alternate)) {
foreach ($alternate AS $attribute) {
if ($attribute->name == "href") {
$author["author-link"] = $attribute->textContent;
2017-03-15 02:00:22 -04:00
}
}
}
if (empty($author["author-link"])) {
$self = XML::getFirstAttributes($xpath, "atom:link[@rel='self']");
2017-12-13 02:03:42 -05:00
if (is_object($self)) {
foreach ($self AS $attribute) {
if ($attribute->name == "href") {
$author["author-link"] = $attribute->textContent;
2017-12-13 02:03:42 -05:00
}
}
}
}
if (empty($author["author-link"])) {
$author["author-link"] = XML::getFirstNodeValue($xpath, '/atom:feed/atom:id/text()');
2017-12-13 02:03:42 -05:00
}
$author["author-avatar"] = XML::getFirstNodeValue($xpath, '/atom:feed/atom:logo/text()');
$author["author-name"] = XML::getFirstNodeValue($xpath, '/atom:feed/atom:title/text()');
if (empty($author["author-name"])) {
$author["author-name"] = XML::getFirstNodeValue($xpath, '/atom:feed/atom:subtitle/text()');
2017-03-15 02:00:22 -04:00
}
2020-01-03 09:09:03 -05:00
if (empty($author["author-name"])) {
$author["author-name"] = XML::getFirstNodeValue($xpath, '/atom:feed/atom:author/atom:name/text()');
2017-03-15 02:00:22 -04:00
}
2020-01-03 09:09:03 -05:00
$value = XML::getFirstNodeValue($xpath, 'atom:author/poco:displayName/text()');
2017-03-15 02:00:22 -04:00
if ($value != "") {
2017-12-13 02:03:42 -05:00
$author["author-name"] = $value;
2017-03-15 02:00:22 -04:00
}
2020-01-03 09:09:03 -05:00
if ($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
$value = XML::getFirstNodeValue($xpath, 'atom:author/atom:uri/text()');
if ($value != "") {
$author["author-link"] = $value;
}
2017-12-13 02:03:42 -05:00
$value = XML::getFirstNodeValue($xpath, 'atom:author/poco:preferredUsername/text()');
2017-12-13 02:03:42 -05:00
if ($value != "") {
$author["author-nick"] = $value;
}
2020-01-03 09:09:03 -05:00
$value = XML::getFirstNodeValue($xpath, 'atom:author/poco:address/poco:formatted/text()');
2017-12-13 02:03:42 -05:00
if ($value != "") {
$author["author-location"] = $value;
}
2020-01-03 09:09:03 -05:00
$value = XML::getFirstNodeValue($xpath, 'atom:author/poco:note/text()');
2017-12-13 02:03:42 -05:00
if ($value != "") {
$author["author-about"] = $value;
}
2020-01-03 09:09:03 -05:00
$avatar = XML::getFirstAttributes($xpath, "atom:author/atom:link[@rel='avatar']");
2017-12-13 02:03:42 -05:00
if (is_object($avatar)) {
foreach ($avatar AS $attribute) {
if ($attribute->name == "href") {
$author["author-avatar"] = $attribute->textContent;
2017-12-13 02:03:42 -05:00
}
2017-08-21 16:21:04 -04:00
}
}
}
$author["edited"] = $author["created"] = XML::getFirstNodeValue($xpath, '/atom:feed/atom:updated/text()');
$author["app"] = XML::getFirstNodeValue($xpath, '/atom:feed/atom:generator/text()');
2017-12-13 02:03:42 -05:00
$entries = $xpath->query('/atom:feed/atom:entry');
}
2017-12-13 02:03:42 -05:00
// Is it RSS?
if ($xpath->query('/rss/channel')->length > 0) {
$author["author-link"] = XML::getFirstNodeValue($xpath, '/rss/channel/link/text()');
$author["author-name"] = XML::getFirstNodeValue($xpath, '/rss/channel/title/text()');
$author["author-avatar"] = XML::getFirstNodeValue($xpath, '/rss/channel/image/url/text()');
if (empty($author["author-name"])) {
$author["author-name"] = XML::getFirstNodeValue($xpath, '/rss/channel/copyright/text()');
2017-12-13 02:03:42 -05:00
}
2020-01-03 09:09:03 -05:00
if (empty($author["author-name"])) {
$author["author-name"] = XML::getFirstNodeValue($xpath, '/rss/channel/description/text()');
2017-12-13 02:03:42 -05:00
}
2020-01-03 09:09:03 -05:00
$author["edited"] = $author["created"] = XML::getFirstNodeValue($xpath, '/rss/channel/pubDate/text()');
$author["app"] = XML::getFirstNodeValue($xpath, '/rss/channel/generator/text()');
2017-12-13 02:03:42 -05:00
$entries = $xpath->query('/rss/channel/item');
}
if (!$dryRun) {
2017-12-13 02:03:42 -05:00
$author["author-link"] = $contact["url"];
if (empty($author["author-name"])) {
2017-12-13 02:03:42 -05:00
$author["author-name"] = $contact["name"];
}
2020-01-03 09:09:03 -05:00
2017-12-13 02:03:42 -05:00
$author["author-avatar"] = $contact["thumb"];
2017-12-13 02:03:42 -05:00
$author["owner-link"] = $contact["url"];
$author["owner-name"] = $contact["name"];
$author["owner-avatar"] = $contact["thumb"];
2017-03-15 02:00:22 -04:00
}
$header = [];
$header["uid"] = $importer["uid"] ?? 0;
$header["network"] = Protocol::FEED;
2017-12-13 02:03:42 -05:00
$header["wall"] = 0;
$header["origin"] = 0;
$header["gravity"] = GRAVITY_PARENT;
2020-03-02 02:57:23 -05:00
$header["private"] = Item::PUBLIC;
$header["verb"] = Activity::POST;
2019-10-24 18:10:20 -04:00
$header["object-type"] = Activity\ObjectType::NOTE;
$header["contact-id"] = $contact["id"] ?? 0;
2015-10-03 07:58:10 -04:00
2017-12-13 02:03:42 -05:00
if (!is_object($entries)) {
Logger::info("There are no entries in this feed.");
return [];
2017-12-13 02:03:42 -05:00
}
$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 = $max_items;
}
2018-03-10 12:40:21 -05:00
// Importing older entries first
for ($i = $total_items; $i >= 0; --$i) {
2018-03-10 12:40:21 -05:00
$entry = $entries->item($i);
2017-12-13 02:03:42 -05:00
$item = array_merge($header, $author);
$alternate = XML::getFirstAttributes($xpath, "atom:link[@rel='alternate']", $entry);
2017-12-13 02:03:42 -05:00
if (!is_object($alternate)) {
$alternate = XML::getFirstAttributes($xpath, "atom:link", $entry);
2017-12-13 02:03:42 -05:00
}
if (is_object($alternate)) {
foreach ($alternate AS $attribute) {
if ($attribute->name == "href") {
$item["plink"] = $attribute->textContent;
2017-12-13 02:03:42 -05:00
}
2017-03-15 02:00:22 -04:00
}
}
2020-01-03 09:09:03 -05:00
if (empty($item["plink"])) {
$item["plink"] = XML::getFirstNodeValue($xpath, 'link/text()', $entry);
2017-12-13 02:03:42 -05:00
}
2020-01-03 09:09:03 -05:00
if (empty($item["plink"])) {
$item["plink"] = XML::getFirstNodeValue($xpath, 'rss:link/text()', $entry);
2017-12-13 02:03:42 -05:00
}
$item["uri"] = XML::getFirstNodeValue($xpath, 'atom:id/text()', $entry);
if (empty($item["uri"])) {
$item["uri"] = XML::getFirstNodeValue($xpath, 'guid/text()', $entry);
2017-12-13 02:03:42 -05:00
}
2020-01-03 09:09:03 -05:00
if (empty($item["uri"])) {
2017-12-13 02:03:42 -05:00
$item["uri"] = $item["plink"];
}
2017-12-13 02:03:42 -05:00
$orig_plink = $item["plink"];
$item["plink"] = Network::finalUrl($item["plink"]);
2017-12-13 02:03:42 -05:00
$item["parent-uri"] = $item["uri"];
if (!$dryRun) {
2017-12-13 02:03:42 -05:00
$condition = ["`uid` = ? AND `uri` = ? AND `network` IN (?, ?)",
$importer["uid"], $item["uri"], Protocol::FEED, Protocol::DFRN];
$previous = Item::selectFirst(['id'], $condition);
2018-07-21 08:46:04 -04:00
if (DBA::isResult($previous)) {
Logger::info("Item with uri " . $item["uri"] . " for user " . $importer["uid"] . " already existed under id " . $previous["id"]);
2017-12-13 02:03:42 -05:00
continue;
}
}
$item["title"] = XML::getFirstNodeValue($xpath, 'atom:title/text()', $entry);
if (empty($item["title"])) {
$item["title"] = XML::getFirstNodeValue($xpath, 'title/text()', $entry);
2017-12-13 02:03:42 -05:00
}
if (empty($item["title"])) {
$item["title"] = XML::getFirstNodeValue($xpath, 'rss:title/text()', $entry);
2017-12-13 02:03:42 -05:00
}
$item["title"] = html_entity_decode($item["title"], ENT_QUOTES, 'UTF-8');
$published = XML::getFirstNodeValue($xpath, 'atom:published/text()', $entry);
if (empty($published)) {
$published = XML::getFirstNodeValue($xpath, 'pubDate/text()', $entry);
2017-12-13 02:03:42 -05:00
}
2020-01-03 09:09:03 -05:00
if (empty($published)) {
$published = XML::getFirstNodeValue($xpath, 'dc:date/text()', $entry);
2017-12-13 02:03:42 -05:00
}
2020-01-03 09:09:03 -05:00
$updated = XML::getFirstNodeValue($xpath, 'atom:updated/text()', $entry);
if (empty($updated) && !empty($published)) {
2017-12-13 02:03:42 -05:00
$updated = $published;
}
if (empty($published) && !empty($updated)) {
$published = $updated;
}
2017-12-13 02:03:42 -05:00
if ($published != "") {
$item["created"] = $published;
}
2020-01-03 09:09:03 -05:00
2017-12-13 02:03:42 -05:00
if ($updated != "") {
$item["edited"] = $updated;
}
2020-01-03 09:09:03 -05:00
$creator = XML::getFirstNodeValue($xpath, 'author/text()', $entry);
if (empty($creator)) {
$creator = XML::getFirstNodeValue($xpath, 'atom:author/atom:name/text()', $entry);
2017-12-13 02:03:42 -05:00
}
2020-01-03 09:09:03 -05:00
if (empty($creator)) {
$creator = XML::getFirstNodeValue($xpath, 'dc:creator/text()', $entry);
2017-12-13 02:03:42 -05:00
}
2020-01-03 09:09:03 -05:00
2017-12-13 02:03:42 -05:00
if ($creator != "") {
$item["author-name"] = $creator;
}
2020-01-03 09:09:03 -05:00
$creator = XML::getFirstNodeValue($xpath, 'dc:creator/text()', $entry);
2017-12-13 02:03:42 -05:00
if ($creator != "") {
$item["author-name"] = $creator;
}
2017-12-13 02:03:42 -05:00
/// @TODO ?
// <category>Ausland</category>
// <media:thumbnail width="152" height="76" url="http://www.taz.de/picture/667875/192/14388767.jpg"/>
$attachments = [];
2017-12-13 02:03:42 -05:00
2018-03-10 12:40:21 -05:00
$enclosures = $xpath->query("enclosure|atom:link[@rel='enclosure']", $entry);
2017-12-13 02:03:42 -05:00
foreach ($enclosures AS $enclosure) {
$href = "";
$length = "";
$type = "";
foreach ($enclosure->attributes AS $attribute) {
if (in_array($attribute->name, ["url", "href"])) {
$href = $attribute->textContent;
} elseif ($attribute->name == "length") {
$length = $attribute->textContent;
} elseif ($attribute->name == "type") {
$type = $attribute->textContent;
2017-12-13 02:03:42 -05:00
}
}
2020-01-03 09:09:03 -05:00
if (!empty($item["attach"])) {
2017-12-13 02:03:42 -05:00
$item["attach"] .= ',';
} else {
$item["attach"] = '';
2017-03-15 02:00:22 -04:00
}
$attachments[] = ["link" => $href, "type" => $type, "length" => $length];
2020-01-03 09:09:03 -05:00
$item["attach"] .= '[attach]href="' . $href . '" length="' . $length . '" type="' . $type . '"[/attach]';
2017-12-13 02:03:42 -05:00
}
$taglist = [];
2017-12-13 02:03:42 -05:00
$categories = $xpath->query("category", $entry);
foreach ($categories AS $category) {
2020-05-02 01:08:05 -04:00
$taglist[] = $category->nodeValue;
2017-12-13 02:03:42 -05:00
}
$body = trim(XML::getFirstNodeValue($xpath, 'atom:content/text()', $entry));
2017-10-17 05:10:19 -04:00
if (empty($body)) {
$body = trim(XML::getFirstNodeValue($xpath, 'content:encoded/text()', $entry));
2017-12-13 02:03:42 -05:00
}
$summary = trim(XML::getFirstNodeValue($xpath, 'atom:summary/text()', $entry));
if (empty($summary)) {
$summary = trim(XML::getFirstNodeValue($xpath, 'description/text()', $entry));
2017-12-13 02:03:42 -05:00
}
if (empty($body)) {
$body = $summary;
$summary = '';
}
if ($body == $summary) {
$summary = '';
2017-12-13 02:03:42 -05:00
}
2017-10-17 05:10:19 -04:00
2017-12-13 02:03:42 -05:00
// remove the content of the title if it is identically to the body
// This helps with auto generated titles e.g. from tumblr
if (self::titleIsBody($item["title"], $body)) {
2017-12-13 02:03:42 -05:00
$item["title"] = "";
}
2018-03-08 14:58:35 -05:00
$item["body"] = HTML::toBBCode($body, $basepath);
2017-10-17 05:10:19 -04:00
2017-12-13 02:03:42 -05:00
if (($item["body"] == '') && ($item["title"] != '')) {
$item["body"] = $item["title"];
$item["title"] = '';
}
2017-10-17 05:10:19 -04:00
$preview = '';
2017-12-13 02:03:42 -05:00
if (!empty($contact["fetch_further_information"]) && ($contact["fetch_further_information"] < 3)) {
// Handle enclosures and treat them as preview picture
foreach ($attachments AS $attachment) {
if ($attachment["type"] == "image/jpeg") {
$preview = $attachment["link"];
}
2017-03-15 02:00:22 -04:00
}
2017-12-13 02:03:42 -05:00
// Remove a possible link to the item itself
$item["body"] = str_replace($item["plink"], '', $item["body"]);
$item["body"] = trim(preg_replace('/\[url\=\](\w+.*?)\[\/url\]/i', '', $item["body"]));
2017-10-17 07:39:09 -04:00
2017-12-13 02:03:42 -05:00
// Replace the content when the title is longer than the body
$replace = (strlen($item["title"]) > strlen($item["body"]));
2017-10-17 05:58:29 -04:00
2017-12-13 02:03:42 -05:00
// Replace it, when there is an image in the body
if (strstr($item["body"], '[/img]')) {
$replace = true;
}
2017-10-17 05:58:29 -04:00
2017-12-13 02:03:42 -05:00
// Replace it, when there is a link in the body
if (strstr($item["body"], '[/url]')) {
$replace = true;
}
2017-10-17 05:58:29 -04:00
2017-12-13 02:03:42 -05:00
if ($replace) {
$item["body"] = trim($item["title"]);
2017-12-13 02:03:42 -05:00
}
2020-01-03 09:09:03 -05:00
$data = ParseUrl::getSiteinfoCached($item['plink'], true);
if (!empty($data['text']) && !empty($data['title']) && (mb_strlen($item['body']) < mb_strlen($data['text']))) {
// When the fetched page info text is longer than the body, we do try to enhance the body
2019-11-18 13:09:21 -05:00
if (!empty($item['body']) && (strpos($data['title'], $item['body']) === false) && (strpos($data['text'], $item['body']) === false)) {
// The body is not part of the fetched page info title or page info text. So we add the text to the body
$item['body'] .= "\n\n" . $data['text'];
} else {
// Else we replace the body with the page info text
$item['body'] = $data['text'];
}
}
2017-12-13 02:03:42 -05:00
// 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_denylist"]);
$taglist = get_page_keywords($item["plink"], $preview, ($contact["fetch_further_information"] == 2), $contact["ffi_keyword_denylist"]);
2019-10-24 18:10:20 -04:00
$item["object-type"] = Activity\ObjectType::BOOKMARK;
2017-12-13 02:03:42 -05:00
unset($item["attach"]);
} else {
if (!empty($summary)) {
2019-03-16 07:18:36 -04:00
$item["body"] = '[abstract]' . HTML::toBBCode($summary, $basepath) . "[/abstract]\n" . $item["body"];
}
2020-01-04 21:19:02 -05:00
if (!empty($contact["fetch_further_information"]) && ($contact["fetch_further_information"] == 3)) {
2020-05-02 01:08:05 -04:00
if (empty($taglist)) {
$taglist = get_page_keywords($item["plink"], $preview, true, $contact["ffi_keyword_denylist"]);
2017-12-13 02:03:42 -05:00
}
2020-05-02 01:43:00 -04:00
$item["body"] .= "\n" . self::tagToString($taglist);
} else {
$taglist = [];
2017-12-13 02:03:42 -05:00
}
2020-01-03 09:09:03 -05:00
2018-01-12 00:55:14 -05:00
// Add the link to the original feed entry if not present in feed
2018-01-29 01:03:39 -05:00
if (($item['plink'] != '') && !strstr($item["body"], $item['plink'])) {
2020-01-03 09:09:03 -05:00
$item["body"] .= "[hr][url]" . $item['plink'] . "[/url]";
}
}
if ($dryRun) {
$items[] = $item;
break;
} else {
Logger::info("Stored feed: " . print_r($item, true));
$notify = Item::isRemoteSelf($contact, $item);
2017-12-13 02:03:42 -05:00
// Distributed items should have a well formatted URI.
// Additionally we have to avoid conflicts with identical URI between imported feeds and these items.
if ($notify) {
2019-12-29 20:17:16 -05:00
$item['guid'] = Item::guidFromUri($orig_plink, DI::baseUrl()->getHostname());
2017-12-13 02:03:42 -05:00
unset($item['uri']);
unset($item['parent-uri']);
2018-05-15 15:29:14 -04:00
// Set the delivery priority for "remote self" to "medium"
$notify = PRIORITY_MEDIUM;
2017-12-13 02:03:42 -05:00
}
2020-04-15 07:39:00 -04:00
2020-05-12 17:49:12 -04:00
$id = Item::insert($item, $notify);
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 $tag) {
2020-04-17 03:55:23 -04:00
Tag::store($feeditem['uri-id'], Tag::HASHTAG, $tag);
}
}
2017-12-13 02:03:42 -05:00
}
2017-03-15 02:00:22 -04:00
}
2017-12-13 02:03:42 -05:00
return ["header" => $author, "items" => $items];
}
2020-05-02 01:43:00 -04:00
/**
* 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)
{
$title = strip_tags($title);
$title = trim($title);
$title = html_entity_decode($title, ENT_QUOTES, 'UTF-8');
$title = str_replace(["\n", "\r", "\t", " "], ["", "", "", ""], $title);
$body = strip_tags($body);
$body = trim($body);
$body = html_entity_decode($body, ENT_QUOTES, 'UTF-8');
$body = str_replace(["\n", "\r", "\t", " "], ["", "", "", ""], $body);
if (strlen($title) < strlen($body)) {
$body = substr($body, 0, strlen($title));
}
if (($title != $body) && (substr($title, -3) == "...")) {
$pos = strrpos($title, "...");
if ($pos > 0) {
$title = substr($title, 0, $pos);
$body = substr($body, 0, $pos);
}
}
return ($title == $body);
}
}