From 5d4719f0096925fc14d8a0504d0045a1b35ef08a Mon Sep 17 00:00:00 2001 From: Michael Vogel Date: Fri, 4 Apr 2014 10:52:53 +0200 Subject: [PATCH] The function to fetch data about a site (via the "parse url" function) is moved from diaspora to another place, since it is multi purpose --- include/diaspora.php | 59 ++++++-------------------------------- include/items.php | 67 +++++++++++++++++++++++++++++++++----------- 2 files changed, 60 insertions(+), 66 deletions(-) diff --git a/include/diaspora.php b/include/diaspora.php index 7476a5c26d..feb57a0404 100755 --- a/include/diaspora.php +++ b/include/diaspora.php @@ -7,47 +7,6 @@ require_once('include/contact_selectors.php'); require_once('include/queue_fn.php'); require_once('include/lock.php'); -function diaspora_add_page_info($url) { - require_once("mod/parse_url.php"); - $data = parseurl_getsiteinfo($url, true); - - logger('diaspora_add_page_info: fetch page info for '.$url.' '.print_r($data, true), LOGGER_DATA); - - if (($data["type"] != "link") OR ($data["title"] == $url)) - return(""); - - if (is_string($data["title"])) - $text .= "[bookmark=".$url."]".trim($data["title"])."[/bookmark]"; - - if (sizeof($data["images"]) > 0) { - $imagedata = $data["images"][0]; - $text .= '[img]'.$imagedata["src"].'[/img]'; - } - - if (is_string($data["text"])) - $text .= "[quote]".$data["text"]."[/quote]"; - - return("\n[class=type-".$data["type"]."]".$text."[/class]"); -} - -function diaspora_add_page_info_to_body($body) { - - logger('diaspora_add_page_info_to_body: fetch page info for body '.$body, LOGGER_DATA); - - $URLSearchString = "^\[\]"; - - // Adding these spaces is a quick hack due to my problems with regular expressions :) - preg_match("/[^@#]\[url\]([$URLSearchString]*)\[\/url\]/ism", " ".$body, $matches); - - if (!$matches) - preg_match("/[^@#]\[url\=([$URLSearchString]*)\](.*?)\[\/url\]/ism", " ".$body, $matches); - - if ($matches) - $body .= diaspora_add_page_info($matches[1]); - - return $body; -} - function diaspora_dispatch_public($msg) { $enabled = intval(get_config('system','diaspora_enabled')); @@ -526,7 +485,7 @@ function diaspora_decode($importer,$xml) { $base = $dom->env; elseif($dom->data) $base = $dom; - + if(! $base) { logger('mod-diaspora: unable to locate salmon data in xml '); http_status_exit(400); @@ -654,7 +613,7 @@ function diaspora_request($importer,$xml) { $arr['author-avatar'] = $arr['owner-avatar'] = $self[0]['thumb']; $arr['verb'] = ACTIVITY_FRIEND; $arr['object-type'] = ACTIVITY_OBJ_PERSON; - + $A = '[url=' . $self[0]['url'] . ']' . $self[0]['name'] . '[/url]'; $B = '[url=' . $contact['url'] . ']' . $contact['name'] . '[/url]'; $BPhoto = '[url=' . $contact['url'] . ']' . '[img]' . $contact['thumb'] . '[/img][/url]'; @@ -713,7 +672,7 @@ function diaspora_request($importer,$xml) { 1, 2 ); - + // find the contact record we just created $contact_record = diaspora_get_contact_by_handle($importer['uid'],$sender_handle); @@ -734,7 +693,7 @@ function diaspora_request($importer,$xml) { if($importer['page-flags'] == PAGE_NORMAL) { $hash = random_string() . (string) time(); // Generate a confirm_key - + $ret = q("INSERT INTO `intro` ( `uid`, `contact-id`, `blocked`, `knowyou`, `note`, `hash`, `datetime` ) VALUES ( %d, %d, %d, %d, '%s', '%s', '%s' )", intval($importer['uid']), @@ -753,7 +712,7 @@ function diaspora_request($importer,$xml) { require_once('include/Photo.php'); $photos = import_profile_photo($contact_record['photo'],$importer['uid'],$contact_record['id']); - + // technically they are sharing with us (CONTACT_IS_SHARING), // but if our page-type is PAGE_COMMUNITY or PAGE_SOAPBOX // we are going to change the relationship and make them a follower. @@ -868,7 +827,7 @@ function diaspora_post($importer,$xml,$msg) { $body = diaspora2bb($xml->raw_message); // Add OEmbed and other information to the body - $body = diaspora_add_page_info_to_body($body); + $body = add_page_info_to_body($body, false, true); $datarray = array(); @@ -1025,7 +984,7 @@ function diaspora_reshare($importer,$xml,$msg) { $body = scale_external_images($body); // Add OEmbed and other information to the body - $body = diaspora_add_page_info_to_body($body); + $body = add_page_info_to_body($body, false, true); } else { // Maybe it is a reshare of a photo that will be delivered at a later time (testing) @@ -1445,12 +1404,12 @@ function diaspora_comment($importer,$xml,$msg) { foreach($myconv as $conv) { // now if we find a match, it means we're in this conversation - + if(! link_compare($conv['author-link'],$importer_url)) continue; require_once('include/enotify.php'); - + $conv_parent = $conv['parent']; notification(array( diff --git a/include/items.php b/include/items.php index ac8c34794a..1516c12015 100755 --- a/include/items.php +++ b/include/items.php @@ -856,9 +856,10 @@ function get_atom_elements($feed, $item, $contact = array()) { } if (isset($contact["network"]) AND ($contact["network"] == NETWORK_FEED) AND $contact['fetch_further_information']) { - $res["body"] = $res["title"]."\n\n[class=type-link]".fetch_siteinfo($res['plink'])."[/class]"; + $res["body"] = $res["title"].add_page_info($res['plink']); $res["title"] = ""; - } + } elseif (isset($contact["network"]) AND ($contact["network"] == NETWORK_OSTATUS)) + $res["body"] = add_page_info_to_body($res["body"]); $arr = array('feed' => $feed, 'item' => $item, 'result' => $res); @@ -874,29 +875,63 @@ function get_atom_elements($feed, $item, $contact = array()) { return $res; } -function fetch_siteinfo($url) { - require_once("mod/parse_url.php"); +function add_page_info($url, $no_photos = false) { + require_once("mod/parse_url.php"); + $data = parseurl_getsiteinfo($url, true); - // Fetch site infos - but only from the meta data - $data = parseurl_getsiteinfo($url, true); + logger('add_page_info: fetch page info for '.$url.' '.print_r($data, true), LOGGER_DEBUG); - $text = ""; + // It maybe is a rich content, but if it does have everything that a link has, + // then treat it that way + if (($data["type"] == "rich") AND is_string($data["title"]) AND + is_string($data["text"]) AND (sizeof($data["images"]) > 0)) + $data["type"] = "link"; - if (!is_string($data["text"]) AND (sizeof($data["images"]) == 0) AND ($data["title"] == $url)) + if ((($data["type"] != "link") AND ($data["type"] != "video") AND ($data["type"] != "photo")) OR ($data["title"] == $url)) + return(""); + + if ($no_photos AND ($data["type"] == "photo")) return(""); - if (is_string($data["title"])) - $text .= "[bookmark=".$url."]".trim($data["title"])."[/bookmark]\n"; + if (($data["type"] != "photo") AND is_string($data["title"])) + $text .= "[bookmark=".$url."]".trim($data["title"])."[/bookmark]"; - if (sizeof($data["images"]) > 0) { - $imagedata = $data["images"][0]; - $text .= '[img='.$imagedata["width"].'x'.$imagedata["height"].']'.$imagedata["src"].'[/img]' . "\n"; + if (($data["type"] != "video") AND (sizeof($data["images"]) > 0)) { + $imagedata = $data["images"][0]; + $text .= '[img]'.$imagedata["src"].'[/img]'; + } + + if (($data["type"] != "photo") AND is_string($data["text"])) + $text .= "[quote]".$data["text"]."[/quote]"; + + return("\n[class=type-".$data["type"]."]".$text."[/class]"); +} + +function add_page_info_to_body($body, $texturl = false, $no_photos = false) { + + logger('add_page_info_to_body: fetch page info for body '.$body, LOGGER_DEBUG); + + $URLSearchString = "^\[\]"; + + // Adding these spaces is a quick hack due to my problems with regular expressions :) + preg_match("/[^@#]\[url\]([$URLSearchString]*)\[\/url\]/ism", " ".$body, $matches); + + if (!$matches) + preg_match("/[^@#]\[url\=([$URLSearchString]*)\](.*?)\[\/url\]/ism", " ".$body, $matches); + + // Convert urls without bbcode elements + if (!$matches AND $texturl) { + preg_match("/([^\]\='".'"'."]|^)(https?\:\/\/[a-zA-Z0-9\:\/\-\?\&\;\.\=\_\~\#\%\$\!\+\,]+)/ism", " ".$body, $matches); + + // Yeah, a hack. I really hate regular expressions :) + if ($matches) + $matches[1] = $matches[2]; } - if (is_string($data["text"])) - $text .= "[quote]".$data["text"]."[/quote]"; + if ($matches) + $body .= add_page_info($matches[1], $no_photos); - return($text); + return $body; } function encode_rel_links($links) {