<?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 Friendica\Database\DBM;
-use Friendica\Core\System;
-use dba;
use DOMDocument;
-use DomXPath;
-
-require_once("include/html2bbcode.php");
-require_once("include/items.php");
+use DOMXPath;
+use Friendica\Content\Text\HTML;
+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;
+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
+ * @param string $xml The feed data
+ * @param array $importer The user record of the importer
+ * @param array $contact The contact record of the feed
*
- * @return array In simulation mode it returns the header and the first item
+ * @return array Returns the header and the first item in dry run mode
+ * @throws \Friendica\Network\HTTPException\InternalServerErrorException
*/
- function import($xml, $importer, &$contact, &$hub, $simulate = false) {
-
- $a = get_app();
+ public static function import($xml, array $importer = [], array $contact = [])
+ {
+ $dryRun = empty($importer) && empty($contact);
- if (!$simulate) {
- logger("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("Test Atom/RSS feed", LOGGER_DEBUG);
+ Logger::info("Import Atom/RSS feed '" . $contact["name"] . "' (Contact " . $contact["id"] . ") for user " . $importer["uid"]);
}
- if ($xml == "") {
- logger('XML is empty.', LOGGER_DEBUG);
- return;
+
+ if (empty($xml)) {
+ Logger::info('XML is empty.');
+ return [];
}
if (!empty($contact['poll'])) {
$doc = new DOMDocument();
@$doc->loadXML(trim($xml));
- $xpath = new DomXPath($doc);
- $xpath->registerNamespace('atom', NAMESPACE_ATOM1);
+ $xpath = new DOMXPath($doc);
+ $xpath->registerNamespace('atom', ActivityNamespace::ATOM1);
$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/");
- $xpath->registerNamespace('poco', NAMESPACE_POCO);
+ $xpath->registerNamespace('poco', ActivityNamespace::POCO);
- $author = array();
+ $author = [];
+ $entries = null;
// Is it RDF?
if ($xpath->query('/rdf:RDF/rss:channel')->length > 0) {
- $author["author-link"] = $xpath->evaluate('/rdf:RDF/rss:channel/rss:link/text()')->item(0)->nodeValue;
- $author["author-name"] = $xpath->evaluate('/rdf:RDF/rss:channel/rss:title/text()')->item(0)->nodeValue;
+ $author["author-link"] = XML::getFirstNodeValue($xpath, '/rdf:RDF/rss:channel/rss:link/text()');
+ $author["author-name"] = XML::getFirstNodeValue($xpath, '/rdf:RDF/rss:channel/rss:title/text()');
- if ($author["author-name"] == "") {
- $author["author-name"] = $xpath->evaluate('/rdf:RDF/rss:channel/rss:description/text()')->item(0)->nodeValue;
+ if (empty($author["author-name"])) {
+ $author["author-name"] = XML::getFirstNodeValue($xpath, '/rdf:RDF/rss:channel/rss:description/text()');
}
$entries = $xpath->query('/rdf:RDF/rss:item');
}
// Is it Atom?
if ($xpath->query('/atom:feed')->length > 0) {
- $alternate = $xpath->query("atom:link[@rel='alternate']")->item(0)->attributes;
+ $alternate = XML::getFirstAttributes($xpath, "atom:link[@rel='alternate']");
if (is_object($alternate)) {
- foreach ($alternate AS $attributes) {
- if ($attributes->name == "href") {
- $author["author-link"] = $attributes->textContent;
+ foreach ($alternate AS $attribute) {
+ if ($attribute->name == "href") {
+ $author["author-link"] = $attribute->textContent;
}
}
}
- if ($author["author-link"] == "") {
- $author["author-link"] = $author["author-id"];
- }
- if ($author["author-link"] == "") {
- $self = $xpath->query("atom:link[@rel='self']")->item(0)->attributes;
+ if (empty($author["author-link"])) {
+ $self = XML::getFirstAttributes($xpath, "atom:link[@rel='self']");
if (is_object($self)) {
- foreach ($self AS $attributes) {
- if ($attributes->name == "href") {
- $author["author-link"] = $attributes->textContent;
+ foreach ($self AS $attribute) {
+ if ($attribute->name == "href") {
+ $author["author-link"] = $attribute->textContent;
}
}
}
}
- if ($author["author-link"] == "") {
- $author["author-link"] = $xpath->evaluate('/atom:feed/atom:id/text()')->item(0)->nodeValue;
+ if (empty($author["author-link"])) {
+ $author["author-link"] = XML::getFirstNodeValue($xpath, '/atom:feed/atom:id/text()');
}
- $author["author-avatar"] = $xpath->evaluate('/atom:feed/atom:logo/text()')->item(0)->nodeValue;
+ $author["author-avatar"] = XML::getFirstNodeValue($xpath, '/atom:feed/atom:logo/text()');
- $author["author-name"] = $xpath->evaluate('/atom:feed/atom:title/text()')->item(0)->nodeValue;
+ $author["author-name"] = XML::getFirstNodeValue($xpath, '/atom:feed/atom:title/text()');
- if ($author["author-name"] == "") {
- $author["author-name"] = $xpath->evaluate('/atom:feed/atom:subtitle/text()')->item(0)->nodeValue;
+ if (empty($author["author-name"])) {
+ $author["author-name"] = XML::getFirstNodeValue($xpath, '/atom:feed/atom:subtitle/text()');
}
- if ($author["author-name"] == "") {
- $author["author-name"] = $xpath->evaluate('/atom:feed/atom:author/atom:name/text()')->item(0)->nodeValue;
+
+ if (empty($author["author-name"])) {
+ $author["author-name"] = XML::getFirstNodeValue($xpath, '/atom:feed/atom:author/atom:name/text()');
}
- $value = $xpath->evaluate('atom:author/poco:displayName/text()')->item(0)->nodeValue;
+
+ $value = XML::getFirstNodeValue($xpath, 'atom:author/poco:displayName/text()');
if ($value != "") {
$author["author-name"] = $value;
}
- if ($simulate) {
- $author["author-id"] = $xpath->evaluate('/atom:feed/atom:author/atom:uri/text()')->item(0)->nodeValue;
- $value = $xpath->evaluate('atom:author/poco:preferredUsername/text()')->item(0)->nodeValue;
+ if ($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;
+ }
+
+ $value = XML::getFirstNodeValue($xpath, 'atom:author/poco:preferredUsername/text()');
if ($value != "") {
$author["author-nick"] = $value;
}
- $value = $xpath->evaluate('atom:author/poco:address/poco:formatted/text()', $context)->item(0)->nodeValue;
+
+ $value = XML::getFirstNodeValue($xpath, 'atom:author/poco:address/poco:formatted/text()');
if ($value != "") {
$author["author-location"] = $value;
}
- $value = $xpath->evaluate('atom:author/poco:note/text()')->item(0)->nodeValue;
+
+ $value = XML::getFirstNodeValue($xpath, 'atom:author/poco:note/text()');
if ($value != "") {
$author["author-about"] = $value;
}
- $avatar = $xpath->evaluate("atom:author/atom:link[@rel='avatar']")->item(0)->attributes;
+
+ $avatar = XML::getFirstAttributes($xpath, "atom:author/atom:link[@rel='avatar']");
if (is_object($avatar)) {
- foreach ($avatar AS $attributes) {
- if ($attributes->name == "href") {
- $author["author-avatar"] = $attributes->textContent;
+ foreach ($avatar AS $attribute) {
+ if ($attribute->name == "href") {
+ $author["author-avatar"] = $attribute->textContent;
}
}
}
}
- $author["edited"] = $author["created"] = $xpath->query('/atom:feed/atom:updated/text()')->item(0)->nodeValue;
+ $author["edited"] = $author["created"] = XML::getFirstNodeValue($xpath, '/atom:feed/atom:updated/text()');
- $author["app"] = $xpath->evaluate('/atom:feed/atom:generator/text()')->item(0)->nodeValue;
+ $author["app"] = XML::getFirstNodeValue($xpath, '/atom:feed/atom:generator/text()');
$entries = $xpath->query('/atom:feed/atom:entry');
}
// Is it RSS?
if ($xpath->query('/rss/channel')->length > 0) {
- $author["author-link"] = $xpath->evaluate('/rss/channel/link/text()')->item(0)->nodeValue;
+ $author["author-link"] = XML::getFirstNodeValue($xpath, '/rss/channel/link/text()');
- $author["author-name"] = $xpath->evaluate('/rss/channel/title/text()')->item(0)->nodeValue;
- $author["author-avatar"] = $xpath->evaluate('/rss/channel/image/url/text()')->item(0)->nodeValue;
+ $author["author-name"] = XML::getFirstNodeValue($xpath, '/rss/channel/title/text()');
+ $author["author-avatar"] = XML::getFirstNodeValue($xpath, '/rss/channel/image/url/text()');
- if ($author["author-name"] == "") {
- $author["author-name"] = $xpath->evaluate('/rss/channel/copyright/text()')->item(0)->nodeValue;
+ if (empty($author["author-name"])) {
+ $author["author-name"] = XML::getFirstNodeValue($xpath, '/rss/channel/copyright/text()');
}
- if ($author["author-name"] == "") {
- $author["author-name"] = $xpath->evaluate('/rss/channel/description/text()')->item(0)->nodeValue;
+
+ if (empty($author["author-name"])) {
+ $author["author-name"] = XML::getFirstNodeValue($xpath, '/rss/channel/description/text()');
}
- $author["edited"] = $author["created"] = $xpath->query('/rss/channel/pubDate/text()')->item(0)->nodeValue;
- $author["app"] = $xpath->evaluate('/rss/channel/generator/text()')->item(0)->nodeValue;
+ $author["edited"] = $author["created"] = XML::getFirstNodeValue($xpath, '/rss/channel/pubDate/text()');
+
+ $author["app"] = XML::getFirstNodeValue($xpath, '/rss/channel/generator/text()');
$entries = $xpath->query('/rss/channel/item');
}
- if (!$simulate) {
+ if (!$dryRun) {
$author["author-link"] = $contact["url"];
- if ($author["author-name"] == "") {
+ if (empty($author["author-name"])) {
$author["author-name"] = $contact["name"];
}
+
$author["author-avatar"] = $contact["thumb"];
$author["owner-link"] = $contact["url"];
$author["owner-avatar"] = $contact["thumb"];
}
- $header = array();
- $header["uid"] = $importer["uid"];
- $header["network"] = NETWORK_FEED;
- $header["type"] = "remote";
+ $header = [];
+ $header["uid"] = $importer["uid"] ?? 0;
+ $header["network"] = Protocol::FEED;
$header["wall"] = 0;
$header["origin"] = 0;
$header["gravity"] = GRAVITY_PARENT;
- $header["private"] = 2;
- $header["verb"] = ACTIVITY_POST;
- $header["object-type"] = ACTIVITY_OBJ_NOTE;
+ $header["private"] = Item::PUBLIC;
+ $header["verb"] = Activity::POST;
+ $header["object-type"] = Activity\ObjectType::NOTE;
- $header["contact-id"] = $contact["id"];
-
- if (!strlen($contact["notify"])) {
- // one way feed - no remote comment ability
- $header["last-child"] = 0;
- }
+ $header["contact-id"] = $contact["id"] ?? 0;
if (!is_object($entries)) {
- logger("There are no entries in this feed.", LOGGER_DEBUG);
- return;
+ Logger::info("There are no entries in this feed.");
+ return [];
}
- $items = array();
+ $items = [];
- $entrylist = array();
-
- foreach ($entries AS $entry) {
- $entrylist[] = $entry;
+ // 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 = $max_items;
}
- foreach (array_reverse($entrylist) AS $entry) {
+
+ // Importing older entries first
+ for ($i = $total_items; $i >= 0; --$i) {
+ $entry = $entries->item($i);
+
$item = array_merge($header, $author);
- $alternate = $xpath->query("atom:link[@rel='alternate']", $entry)->item(0)->attributes;
+ $alternate = XML::getFirstAttributes($xpath, "atom:link[@rel='alternate']", $entry);
if (!is_object($alternate)) {
- $alternate = $xpath->query("atom:link", $entry)->item(0)->attributes;
+ $alternate = XML::getFirstAttributes($xpath, "atom:link", $entry);
}
if (is_object($alternate)) {
- foreach ($alternate AS $attributes) {
- if ($attributes->name == "href") {
- $item["plink"] = $attributes->textContent;
+ foreach ($alternate AS $attribute) {
+ if ($attribute->name == "href") {
+ $item["plink"] = $attribute->textContent;
}
}
}
- if ($item["plink"] == "") {
- $item["plink"] = $xpath->evaluate('link/text()', $entry)->item(0)->nodeValue;
+
+ if (empty($item["plink"])) {
+ $item["plink"] = XML::getFirstNodeValue($xpath, 'link/text()', $entry);
}
- if ($item["plink"] == "") {
- $item["plink"] = $xpath->evaluate('rss:link/text()', $entry)->item(0)->nodeValue;
+
+ if (empty($item["plink"])) {
+ $item["plink"] = XML::getFirstNodeValue($xpath, 'rss:link/text()', $entry);
}
- $item["uri"] = $xpath->evaluate('atom:id/text()', $entry)->item(0)->nodeValue;
+ $item["uri"] = XML::getFirstNodeValue($xpath, 'atom:id/text()', $entry);
- if ($item["uri"] == "") {
- $item["uri"] = $xpath->evaluate('guid/text()', $entry)->item(0)->nodeValue;
+ if (empty($item["uri"])) {
+ $item["uri"] = XML::getFirstNodeValue($xpath, 'guid/text()', $entry);
}
- if ($item["uri"] == "") {
+
+ if (empty($item["uri"])) {
$item["uri"] = $item["plink"];
}
$orig_plink = $item["plink"];
- $item["plink"] = original_url($item["plink"]);
+ $item["plink"] = Network::finalUrl($item["plink"]);
$item["parent-uri"] = $item["uri"];
- if (!$simulate) {
+ if (!$dryRun) {
$condition = ["`uid` = ? AND `uri` = ? AND `network` IN (?, ?)",
- $importer["uid"], $item["uri"], NETWORK_FEED, NETWORK_DFRN];
- $previous = dba::select('item', ['id'], $condition, ['limit' => 1]);
- if (DBM::is_result($previous)) {
- logger("Item with uri ".$item["uri"]." for user ".$importer["uid"]." already existed under id ".$previous["id"], LOGGER_DEBUG);
+ $importer["uid"], $item["uri"], Protocol::FEED, Protocol::DFRN];
+ $previous = Item::selectFirst(['id'], $condition);
+ if (DBA::isResult($previous)) {
+ Logger::info("Item with uri " . $item["uri"] . " for user " . $importer["uid"] . " already existed under id " . $previous["id"]);
continue;
}
}
- $item["title"] = $xpath->evaluate('atom:title/text()', $entry)->item(0)->nodeValue;
+ $item["title"] = XML::getFirstNodeValue($xpath, 'atom:title/text()', $entry);
- if ($item["title"] == "") {
- $item["title"] = $xpath->evaluate('title/text()', $entry)->item(0)->nodeValue;
+ if (empty($item["title"])) {
+ $item["title"] = XML::getFirstNodeValue($xpath, 'title/text()', $entry);
}
- if ($item["title"] == "") {
- $item["title"] = $xpath->evaluate('rss:title/text()', $entry)->item(0)->nodeValue;
+ if (empty($item["title"])) {
+ $item["title"] = XML::getFirstNodeValue($xpath, 'rss:title/text()', $entry);
}
- $published = $xpath->query('atom:published/text()', $entry)->item(0)->nodeValue;
- if ($published == "") {
- $published = $xpath->query('pubDate/text()', $entry)->item(0)->nodeValue;
+ $item["title"] = html_entity_decode($item["title"], ENT_QUOTES, 'UTF-8');
+
+ $published = XML::getFirstNodeValue($xpath, 'atom:published/text()', $entry);
+
+ if (empty($published)) {
+ $published = XML::getFirstNodeValue($xpath, 'pubDate/text()', $entry);
}
- if ($published == "") {
- $published = $xpath->query('dc:date/text()', $entry)->item(0)->nodeValue;
+
+ if (empty($published)) {
+ $published = XML::getFirstNodeValue($xpath, 'dc:date/text()', $entry);
}
- $updated = $xpath->query('atom:updated/text()', $entry)->item(0)->nodeValue;
- if ($updated == "") {
+ $updated = XML::getFirstNodeValue($xpath, 'atom:updated/text()', $entry);
+
+ if (empty($updated) && !empty($published)) {
$updated = $published;
}
+
+ if (empty($published) && !empty($updated)) {
+ $published = $updated;
+ }
+
if ($published != "") {
$item["created"] = $published;
}
+
if ($updated != "") {
$item["edited"] = $updated;
}
- $creator = $xpath->query('author/text()', $entry)->item(0)->nodeValue;
- if ($creator == "") {
- $creator = $xpath->query('atom:author/atom:name/text()', $entry)->item(0)->nodeValue;
+ $creator = XML::getFirstNodeValue($xpath, 'author/text()', $entry);
+
+ if (empty($creator)) {
+ $creator = XML::getFirstNodeValue($xpath, 'atom:author/atom:name/text()', $entry);
}
- if ($creator == "") {
- $creator = $xpath->query('dc:creator/text()', $entry)->item(0)->nodeValue;
+
+ if (empty($creator)) {
+ $creator = XML::getFirstNodeValue($xpath, 'dc:creator/text()', $entry);
}
+
if ($creator != "") {
$item["author-name"] = $creator;
}
- if ($pubDate != "") {
- $item["edited"] = $item["created"] = $pubDate;
- }
- $creator = $xpath->query('dc:creator/text()', $entry)->item(0)->nodeValue;
+
+ $creator = XML::getFirstNodeValue($xpath, 'dc:creator/text()', $entry);
if ($creator != "") {
$item["author-name"] = $creator;
// <category>Ausland</category>
// <media:thumbnail width="152" height="76" url="http://www.taz.de/picture/667875/192/14388767.jpg"/>
- $attachments = array();
+ $attachments = [];
- $enclosures = $xpath->query("enclosure", $entry);
+ $enclosures = $xpath->query("enclosure|atom:link[@rel='enclosure']", $entry);
foreach ($enclosures AS $enclosure) {
$href = "";
$length = "";
$type = "";
- $title = "";
-
- foreach ($enclosure->attributes AS $attributes) {
- if ($attributes->name == "url") {
- $href = $attributes->textContent;
- } elseif ($attributes->name == "length") {
- $length = $attributes->textContent;
- } elseif ($attributes->name == "type") {
- $type = $attributes->textContent;
+
+ foreach ($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 = $attribute->textContent;
}
}
- if (strlen($item["attach"])) {
+
+ if (!empty($item["attach"])) {
$item["attach"] .= ',';
+ } else {
+ $item["attach"] = '';
}
- $attachments[] = array("link" => $href, "type" => $type, "length" => $length);
+ $attachments[] = ["link" => $href, "type" => $type, "length" => $length];
- $item["attach"] .= '[attach]href="'.$href.'" length="'.$length.'" type="'.$type.'"[/attach]';
+ $item["attach"] .= '[attach]href="' . $href . '" length="' . $length . '" type="' . $type . '"[/attach]';
}
$tags = '';
+ $taglist = [];
$categories = $xpath->query("category", $entry);
foreach ($categories AS $category) {
$hashtag = $category->nodeValue;
$tags .= ', ';
}
- $taglink = "#[url=" . System::baseUrl() . "/search?tag=" . rawurlencode($hashtag) . "]" . $hashtag . "[/url]";
+ $taglink = "#[url=" . DI::baseUrl() . "/search?tag=" . $hashtag . "]" . $hashtag . "[/url]";
$tags .= $taglink;
+ $taglist[] = $hashtag;
}
- $body = trim($xpath->evaluate('atom:content/text()', $entry)->item(0)->nodeValue);
+ $body = trim(XML::getFirstNodeValue($xpath, 'atom:content/text()', $entry));
- if ($body == "") {
- $body = trim($xpath->evaluate('content:encoded/text()', $entry)->item(0)->nodeValue);
+ if (empty($body)) {
+ $body = trim(XML::getFirstNodeValue($xpath, 'content:encoded/text()', $entry));
}
- if ($body == "") {
- $body = trim($xpath->evaluate('description/text()', $entry)->item(0)->nodeValue);
+
+ $summary = trim(XML::getFirstNodeValue($xpath, 'atom:summary/text()', $entry));
+
+ if (empty($summary)) {
+ $summary = trim(XML::getFirstNodeValue($xpath, 'description/text()', $entry));
}
- if ($body == "") {
- $body = trim($xpath->evaluate('atom:summary/text()', $entry)->item(0)->nodeValue);
+
+ if (empty($body)) {
+ $body = $summary;
+ $summary = '';
+ }
+
+ if ($body == $summary) {
+ $summary = '';
}
// remove the content of the title if it is identically to the body
// This helps with auto generated titles e.g. from tumblr
- if (title_is_body($item["title"], $body)) {
+ if (self::titleIsBody($item["title"], $body)) {
$item["title"] = "";
}
- $item["body"] = html2bbcode($body, $basepath);
+ $item["body"] = HTML::toBBCode($body, $basepath);
if (($item["body"] == '') && ($item["title"] != '')) {
$item["body"] = $item["title"];
$item["title"] = '';
}
+ $preview = '';
if (!empty($contact["fetch_further_information"]) && ($contact["fetch_further_information"] < 3)) {
- $preview = "";
-
// Handle enclosures and treat them as preview picture
foreach ($attachments AS $attachment) {
if ($attachment["type"] == "image/jpeg") {
// Remove a possible link to the item itself
$item["body"] = str_replace($item["plink"], '', $item["body"]);
- $item["body"] = preg_replace('/\[url\=\](\w+.*?)\[\/url\]/i', '', $item["body"]);
+ $item["body"] = trim(preg_replace('/\[url\=\](\w+.*?)\[\/url\]/i', '', $item["body"]));
// Replace the content when the title is longer than the body
$replace = (strlen($item["title"]) > strlen($item["body"]));
}
if ($replace) {
- $item["body"] = $item["title"];
+ $item["body"] = trim($item["title"]);
}
+
+ $data = ParseUrl::getSiteinfoCached($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
+ 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'];
+ }
+ }
+
// 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"], false, $preview, ($contact["fetch_further_information"] == 2), $contact["ffi_keyword_blacklist"]);
- $item["object-type"] = ACTIVITY_OBJ_BOOKMARK;
+ $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"]);
+ $taglist = get_page_keywords($item["plink"], $preview, ($contact["fetch_further_information"] == 2), $contact["ffi_keyword_blacklist"]);
+ $item["object-type"] = Activity\ObjectType::BOOKMARK;
unset($item["attach"]);
} else {
- if ($contact["fetch_further_information"] == 3) {
+ if (!empty($summary)) {
+ $item["body"] = '[abstract]' . HTML::toBBCode($summary, $basepath) . "[/abstract]\n" . $item["body"];
+ }
+
+ if (!empty($contact["fetch_further_information"]) && ($contact["fetch_further_information"] == 3)) {
if (!empty($tags)) {
$item["tag"] = $tags;
} else {
- $item["tag"] = add_page_keywords($item["plink"], false, $preview, true, $contact["ffi_keyword_blacklist"]);
+ // @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"]);
+ $taglist = get_page_keywords($item["plink"], $preview, true, $contact["ffi_keyword_blacklist"]);
}
- $item["body"] .= "\n".$item['tag'];
+ $item["body"] .= "\n" . $item['tag'];
+ } else {
+ $taglist = [];
}
- if (!strstr($item["body"], '[url') && ($item['plink'] != '')) {
- $item["body"] .= "[hr][url]".$item['plink']."[/url]";
+
+ // Add the link to the original feed entry if not present in feed
+ if (($item['plink'] != '') && !strstr($item["body"], $item['plink'])) {
+ $item["body"] .= "[hr][url]" . $item['plink'] . "[/url]";
}
}
- if (!$simulate) {
- logger("Stored feed: ".print_r($item, true), LOGGER_DEBUG);
+ if ($dryRun) {
+ $items[] = $item;
+ break;
+ } else {
+ Logger::info("Stored feed: " . print_r($item, true));
- $notify = item_is_remote_self($contact, $item);
+ $notify = Item::isRemoteSelf($contact, $item);
// Distributed items should have a well formatted URI.
// Additionally we have to avoid conflicts with identical URI between imported feeds and these items.
if ($notify) {
- $item['guid'] = uri_to_guid($orig_plink, $a->get_hostname());
+ $item['guid'] = Item::guidFromUri($orig_plink, DI::baseUrl()->getHostname());
unset($item['uri']);
unset($item['parent-uri']);
+
+ // Set the delivery priority for "remote self" to "medium"
+ $notify = PRIORITY_MEDIUM;
}
- $id = item_store($item, false, $notify);
+ $id = Item::insert($item, false, $notify);
- logger("Feed for contact ".$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 array("header" => $author, "items" => $items);
+ return ["header" => $author, "items" => $items];
+ }
+
+ private static function titleIsBody($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);
}
}