X-Git-Url: https://git.mxchange.org/?a=blobdiff_plain;f=src%2FProtocol%2FFeed.php;h=705a094c38149b433b454fc2b5626181ebb9b598;hb=51ee24f65220f4d5e3b0717767fa399e1a5a58e5;hp=71ebe5506b9dadd78587e6123646af464d9c2d5f;hpb=2f28c2ebbfd8f66093d7081d40b1d48f65fcff20;p=friendica.git

diff --git a/src/Protocol/Feed.php b/src/Protocol/Feed.php
index 71ebe5506b..705a094c38 100644
--- a/src/Protocol/Feed.php
+++ b/src/Protocol/Feed.php
@@ -14,12 +14,11 @@ use Friendica\Core\Protocol;
 use Friendica\Core\System;
 use Friendica\Database\DBA;
 use Friendica\Model\Item;
+use Friendica\Protocol\ActivityNamespace;
+use Friendica\Util\ParseUrl;
 use Friendica\Util\Network;
 use Friendica\Util\XML;
 
-require_once 'include/dba.php';
-require_once 'include/items.php';
-
 /**
  * @brief This class contain functions to import feeds
  *
@@ -28,17 +27,18 @@ class Feed {
 	/**
 	 * @brief 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
+	 * @param string $hub      Unused dummy value for compatibility reasons
+	 * @param bool   $simulate If enabled, no data is imported
 	 *
 	 * @return array In simulation mode it returns the header and the first item
+	 * @throws \Friendica\Network\HTTPException\InternalServerErrorException
 	 */
 	public static function import($xml, $importer, &$contact, &$hub, $simulate = false) {
 
-		$a = get_app();
+		$a = \get_app();
 
 		if (!$simulate) {
 			Logger::log("Import Atom/RSS feed '".$contact["name"]."' (Contact ".$contact["id"].") for user ".$importer["uid"], Logger::DEBUG);
@@ -61,13 +61,13 @@ class Feed {
 		$doc = new DOMDocument();
 		@$doc->loadXML(trim($xml));
 		$xpath = new DOMXPath($doc);
-		$xpath->registerNamespace('atom', NAMESPACE_ATOM1);
+		$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 = [];
 		$entries = null;
@@ -123,7 +123,13 @@ class Feed {
 				$author["author-name"] = $value;
 			}
 			if ($simulate) {
-				$author["author-id"] = XML::getFirstNodeValue($xpath, '/atom:feed/atom:author/atom:uri/text()');
+				$author["author-id"] = XML::getFirstNodeValue($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 != "") {
@@ -194,8 +200,8 @@ class Feed {
 		$header["origin"] = 0;
 		$header["gravity"] = GRAVITY_PARENT;
 		$header["private"] = 2;
-		$header["verb"] = ACTIVITY_POST;
-		$header["object-type"] = ACTIVITY_OBJ_NOTE;
+		$header["verb"] = Activity::POST;
+		$header["object-type"] = Activity\ObjectType::NOTE;
 
 		$header["contact-id"] = $contact["id"];
 
@@ -262,6 +268,9 @@ class Feed {
 			if (empty($item["title"])) {
 				$item["title"] = XML::getFirstNodeValue($xpath, 'rss:title/text()', $entry);
 			}
+
+			$item["title"] = html_entity_decode($item["title"], ENT_QUOTES, 'UTF-8');
+
 			$published = XML::getFirstNodeValue($xpath, 'atom:published/text()', $entry);
 
 			if (empty($published)) {
@@ -314,7 +323,6 @@ class Feed {
 				$href = "";
 				$length = "";
 				$type = "";
-				$title = "";
 
 				foreach ($enclosure->attributes AS $attribute) {
 					if (in_array($attribute->name, ["url", "href"])) {
@@ -344,7 +352,7 @@ class Feed {
 					$tags .= ', ';
 				}
 
-				$taglink = "#[url=" . System::baseUrl() . "/search?tag=" . rawurlencode($hashtag) . "]" . $hashtag . "[/url]";
+				$taglink = "#[url=" . System::baseUrl() . "/search?tag=" . $hashtag . "]" . $hashtag . "[/url]";
 				$tags .= $taglink;
 			}
 
@@ -353,11 +361,20 @@ class Feed {
 			if (empty($body)) {
 				$body = trim(XML::getFirstNodeValue($xpath, 'content:encoded/text()', $entry));
 			}
-			if (empty($body)) {
-				$body = trim(XML::getFirstNodeValue($xpath, 'description/text()', $entry));
+
+			$summary = trim(XML::getFirstNodeValue($xpath, 'atom:summary/text()', $entry));
+
+			if (empty($summary)) {
+				$summary = trim(XML::getFirstNodeValue($xpath, 'description/text()', $entry));
 			}
+
 			if (empty($body)) {
-				$body = trim(XML::getFirstNodeValue($xpath, 'atom:summary/text()', $entry));
+				$body = $summary;
+				$summary = '';
+			}
+
+			if ($body == $summary) {
+				$summary = '';
 			}
 
 			// remove the content of the title if it is identically to the body
@@ -383,7 +400,7 @@ class Feed {
 
 				// 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"]));
@@ -399,15 +416,32 @@ class Feed {
 				}
 
 				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"], $preview, ($contact["fetch_further_information"] == 2), $contact["ffi_keyword_blacklist"]);
-				$item["object-type"] = ACTIVITY_OBJ_BOOKMARK;
+				$item["object-type"] = Activity\ObjectType::BOOKMARK;
 				unset($item["attach"]);
 			} else {
+				if (!empty($summary)) {
+					$item["body"] = '[abstract]' . HTML::toBBCode($summary, $basepath) . "[/abstract]\n" . $item["body"];
+				}
+
 				if ($contact["fetch_further_information"] == 3) {
 					if (!empty($tags)) {
 						$item["tag"] = $tags;