function get_atom_elements($feed, $item, $contact = array()) { require_once 'library/HTMLPurifier.auto.php'; require_once 'include/html2bbcode.php'; $best_photo = array(); $res = array(); $author = $item->get_author(); if ($author) { $res['author-name'] = unxmlify($author->get_name()); $res['author-link'] = unxmlify($author->get_link()); } else { $res['author-name'] = unxmlify($feed->get_title()); $res['author-link'] = unxmlify($feed->get_permalink()); } $res['uri'] = unxmlify($item->get_id()); $res['title'] = unxmlify($item->get_title()); $res['body'] = unxmlify($item->get_content()); $res['plink'] = unxmlify($item->get_link(0)); if (isset($contact["network"]) and $contact["network"] == NETWORK_FEED and strstr($res['plink'], ".app.net/")) { logger("get_atom_elements: detected app.net posting: " . print_r($res, true), LOGGER_DEBUG); $res['title'] = ""; $res['body'] = nl2br($res['body']); } // removing the content of the title if its identically to the body // This helps with auto generated titles e.g. from tumblr if (title_is_body($res["title"], $res["body"])) { $res['title'] = ""; } if ($res['plink']) { $base_url = implode('/', array_slice(explode('/', $res['plink']), 0, 3)); } else { $base_url = ''; } // look for a photo. We should check media size and find the best one, // but for now let's just find any author photo // Additionally we look for an alternate author link. On OStatus this one is the one we want. $authorlinks = $item->feed->data["child"][SIMPLEPIE_NAMESPACE_ATOM_10]["feed"][0]["child"][SIMPLEPIE_NAMESPACE_ATOM_10]["author"][0]["child"]["http://www.w3.org/2005/Atom"]["link"]; if (is_array($authorlinks)) { foreach ($authorlinks as $link) { $linkdata = array_shift($link["attribs"]); if ($linkdata["rel"] == "alternate") { $res["author-link"] = $linkdata["href"]; } } } $rawauthor = $item->get_item_tags(SIMPLEPIE_NAMESPACE_ATOM_10, 'author'); if ($rawauthor && $rawauthor[0]['child'][SIMPLEPIE_NAMESPACE_ATOM_10]['link']) { $base = $rawauthor[0]['child'][SIMPLEPIE_NAMESPACE_ATOM_10]['link']; foreach ($base as $link) { if ($link['attribs']['']['rel'] === 'alternate') { $res['author-link'] = unxmlify($link['attribs']['']['href']); } if (!x($res, 'author-avatar') || !$res['author-avatar']) { if ($link['attribs']['']['rel'] === 'photo' || $link['attribs']['']['rel'] === 'avatar') { $res['author-avatar'] = unxmlify($link['attribs']['']['href']); } } } } $rawactor = $item->get_item_tags(NAMESPACE_ACTIVITY, 'actor'); if ($rawactor && activity_match($rawactor[0]['child'][NAMESPACE_ACTIVITY]['object-type'][0]['data'], ACTIVITY_OBJ_PERSON)) { $base = $rawactor[0]['child'][SIMPLEPIE_NAMESPACE_ATOM_10]['link']; if ($base && count($base)) { foreach ($base as $link) { if ($link['attribs']['']['rel'] === 'alternate' && !$res['author-link']) { $res['author-link'] = unxmlify($link['attribs']['']['href']); } if (!x($res, 'author-avatar') || !$res['author-avatar']) { if ($link['attribs']['']['rel'] === 'avatar' || $link['attribs']['']['rel'] === 'photo') { $res['author-avatar'] = unxmlify($link['attribs']['']['href']); } } } } } // No photo/profile-link on the item - look at the feed level if (!x($res, 'author-link') || !x($res, 'author-avatar')) { $rawauthor = $feed->get_feed_tags(SIMPLEPIE_NAMESPACE_ATOM_10, 'author'); if ($rawauthor && $rawauthor[0]['child'][SIMPLEPIE_NAMESPACE_ATOM_10]['link']) { $base = $rawauthor[0]['child'][SIMPLEPIE_NAMESPACE_ATOM_10]['link']; foreach ($base as $link) { if ($link['attribs']['']['rel'] === 'alternate' && !$res['author-link']) { $res['author-link'] = unxmlify($link['attribs']['']['href']); } if (!$res['author-avatar']) { if ($link['attribs']['']['rel'] === 'photo' || $link['attribs']['']['rel'] === 'avatar') { $res['author-avatar'] = unxmlify($link['attribs']['']['href']); } } } } $rawactor = $feed->get_feed_tags(NAMESPACE_ACTIVITY, 'subject'); if ($rawactor && activity_match($rawactor[0]['child'][NAMESPACE_ACTIVITY]['object-type'][0]['data'], ACTIVITY_OBJ_PERSON)) { $base = $rawactor[0]['child'][SIMPLEPIE_NAMESPACE_ATOM_10]['link']; if ($base && count($base)) { foreach ($base as $link) { if ($link['attribs']['']['rel'] === 'alternate' && !$res['author-link']) { $res['author-link'] = unxmlify($link['attribs']['']['href']); } if (!x($res, 'author-avatar')) { if ($link['attribs']['']['rel'] === 'avatar' || $link['attribs']['']['rel'] === 'photo') { $res['author-avatar'] = unxmlify($link['attribs']['']['href']); } } } } } } $apps = $item->get_item_tags(NAMESPACE_STATUSNET, 'notice_info'); if ($apps && $apps[0]['attribs']['']['source']) { $res['app'] = strip_tags(unxmlify($apps[0]['attribs']['']['source'])); if ($res['app'] === 'web') { $res['app'] = 'OStatus'; } } // base64 encoded json structure representing Diaspora signature $dsig = $item->get_item_tags(NAMESPACE_DFRN, 'diaspora_signature'); if ($dsig) { $res['dsprsig'] = unxmlify($dsig[0]['data']); } $dguid = $item->get_item_tags(NAMESPACE_DFRN, 'diaspora_guid'); if ($dguid) { $res['guid'] = unxmlify($dguid[0]['data']); } $bm = $item->get_item_tags(NAMESPACE_DFRN, 'bookmark'); if ($bm) { $res['bookmark'] = unxmlify($bm[0]['data']) === 'true' ? 1 : 0; } /** * If there's a copy of the body content which is guaranteed to have survived mangling in transit, use it. */ $have_real_body = false; $rawenv = $item->get_item_tags(NAMESPACE_DFRN, 'env'); if ($rawenv) { $have_real_body = true; $res['body'] = $rawenv[0]['data']; $res['body'] = str_replace(array(' ', "\t", "\r", "\n"), array('', '', '', ''), $res['body']); // make sure nobody is trying to sneak some html tags by us $res['body'] = notags(base64url_decode($res['body'])); } $res['body'] = limit_body_size($res['body']); // It isn't certain at this point whether our content is plaintext or html and we'd be foolish to trust // the content type. Our own network only emits text normally, though it might have been converted to // html if we used a pubsubhubbub transport. But if we see even one html tag in our text, we will // have to assume it is all html and needs to be purified. // It doesn't matter all that much security wise - because before this content is used anywhere, we are // going to escape any tags we find regardless, but this lets us import a limited subset of html from // the wild, by sanitising it and converting supported tags to bbcode before we rip out any remaining // html. if (strpos($res['body'], '<') !== false && strpos($res['body'], '>') !== false) { $res['body'] = reltoabs($res['body'], $base_url); $res['body'] = html2bb_video($res['body']); $res['body'] = oembed_html2bbcode($res['body']); $config = HTMLPurifier_Config::createDefault(); $config->set('Cache.DefinitionImpl', null); // we shouldn't need a whitelist, because the bbcode converter // will strip out any unsupported tags. $purifier = new HTMLPurifier($config); $res['body'] = $purifier->purify($res['body']); $res['body'] = @html2bbcode($res['body']); } elseif (!$have_real_body) { // it's not one of our messages and it has no tags // so it's probably just text. We'll escape it just to be safe. $res['body'] = escape_tags($res['body']); } // this tag is obsolete but we keep it for really old sites $allow = $item->get_item_tags(NAMESPACE_DFRN, 'comment-allow'); if ($allow && $allow[0]['data'] == 1) { $res['last-child'] = 1; } else { $res['last-child'] = 0; } $private = $item->get_item_tags(NAMESPACE_DFRN, 'private'); if ($private && intval($private[0]['data']) > 0) { $res['private'] = intval($private[0]['data']); } else { $res['private'] = 0; } $extid = $item->get_item_tags(NAMESPACE_DFRN, 'extid'); if ($extid && $extid[0]['data']) { $res['extid'] = $extid[0]['data']; } $rawlocation = $item->get_item_tags(NAMESPACE_DFRN, 'location'); if ($rawlocation) { $res['location'] = unxmlify($rawlocation[0]['data']); } $rawcreated = $item->get_item_tags(SIMPLEPIE_NAMESPACE_ATOM_10, 'published'); if ($rawcreated) { $res['created'] = unxmlify($rawcreated[0]['data']); } $rawedited = $item->get_item_tags(SIMPLEPIE_NAMESPACE_ATOM_10, 'updated'); if ($rawedited) { $res['edited'] = unxmlify($rawedited[0]['data']); } if (x($res, 'edited') && !x($res, 'created')) { $res['created'] = $res['edited']; } if (!$res['created']) { $res['created'] = $item->get_date('c'); } if (!$res['edited']) { $res['edited'] = $item->get_date('c'); } // Disallow time travelling posts $d1 = strtotime($res['created']); $d2 = strtotime($res['edited']); $d3 = strtotime('now'); if ($d1 > $d3) { $res['created'] = datetime_convert(); } if ($d2 > $d3) { $res['edited'] = datetime_convert(); } $rawowner = $item->get_item_tags(NAMESPACE_DFRN, 'owner'); if ($rawowner[0]['child'][SIMPLEPIE_NAMESPACE_ATOM_10]['name'][0]['data']) { $res['owner-name'] = unxmlify($rawowner[0]['child'][SIMPLEPIE_NAMESPACE_ATOM_10]['name'][0]['data']); } elseif ($rawowner[0]['child'][NAMESPACE_DFRN]['name'][0]['data']) { $res['owner-name'] = unxmlify($rawowner[0]['child'][NAMESPACE_DFRN]['name'][0]['data']); } if ($rawowner[0]['child'][SIMPLEPIE_NAMESPACE_ATOM_10]['uri'][0]['data']) { $res['owner-link'] = unxmlify($rawowner[0]['child'][SIMPLEPIE_NAMESPACE_ATOM_10]['uri'][0]['data']); } elseif ($rawowner[0]['child'][NAMESPACE_DFRN]['uri'][0]['data']) { $res['owner-link'] = unxmlify($rawowner[0]['child'][NAMESPACE_DFRN]['uri'][0]['data']); } if ($rawowner[0]['child'][SIMPLEPIE_NAMESPACE_ATOM_10]['link']) { $base = $rawowner[0]['child'][SIMPLEPIE_NAMESPACE_ATOM_10]['link']; foreach ($base as $link) { if (!x($res, 'owner-avatar') || !$res['owner-avatar']) { if ($link['attribs']['']['rel'] === 'photo' || $link['attribs']['']['rel'] === 'avatar') { $res['owner-avatar'] = unxmlify($link['attribs']['']['href']); } } } } $rawgeo = $item->get_item_tags(NAMESPACE_GEORSS, 'point'); if ($rawgeo) { $res['coord'] = unxmlify($rawgeo[0]['data']); } if ($contact["network"] == NETWORK_FEED) { $res['verb'] = ACTIVITY_POST; $res['object-type'] = ACTIVITY_OBJ_NOTE; } $rawverb = $item->get_item_tags(NAMESPACE_ACTIVITY, 'verb'); // select between supported verbs if ($rawverb) { $res['verb'] = unxmlify($rawverb[0]['data']); } // translate OStatus unfollow to activity streams if it happened to get selected if (x($res, 'verb') && $res['verb'] === 'http://ostatus.org/schema/1.0/unfollow') { $res['verb'] = ACTIVITY_UNFOLLOW; } $cats = $item->get_categories(); if ($cats) { $tag_arr = array(); foreach ($cats as $cat) { $term = $cat->get_term(); if (!$term) { $term = $cat->get_label(); } $scheme = $cat->get_scheme(); if ($scheme && $term && stristr($scheme, 'X-DFRN:')) { $tag_arr[] = substr($scheme, 7, 1) . '[url=' . unxmlify(substr($scheme, 9)) . ']' . unxmlify($term) . '[/url]'; } elseif ($term) { $tag_arr[] = notags(trim($term)); } } $res['tag'] = implode(',', $tag_arr); } $attach = $item->get_enclosures(); if ($attach) { $att_arr = array(); foreach ($attach as $att) { $len = intval($att->get_length()); $link = str_replace(array(',', '"'), array('%2D', '%22'), notags(trim(unxmlify($att->get_link())))); $title = str_replace(array(',', '"'), array('%2D', '%22'), notags(trim(unxmlify($att->get_title())))); $type = str_replace(array(',', '"'), array('%2D', '%22'), notags(trim(unxmlify($att->get_type())))); if (strpos($type, ';')) { $type = substr($type, 0, strpos($type, ';')); } if (!$link || strpos($link, 'http') !== 0) { continue; } if (!$title) { $title = ' '; } if (!$type) { $type = 'application/octet-stream'; } $att_arr[] = '[attach]href="' . $link . '" length="' . $len . '" type="' . $type . '" title="' . $title . '"[/attach]'; } $res['attach'] = implode(',', $att_arr); } $rawobj = $item->get_item_tags(NAMESPACE_ACTIVITY, 'object'); if ($rawobj) { $res['object'] = '<object>' . "\n"; $child = $rawobj[0]['child']; if ($child[NAMESPACE_ACTIVITY]['object-type'][0]['data']) { $res['object-type'] = $child[NAMESPACE_ACTIVITY]['object-type'][0]['data']; $res['object'] .= '<type>' . $child[NAMESPACE_ACTIVITY]['object-type'][0]['data'] . '</type>' . "\n"; } if (x($child[SIMPLEPIE_NAMESPACE_ATOM_10], 'id') && $child[SIMPLEPIE_NAMESPACE_ATOM_10]['id'][0]['data']) { $res['object'] .= '<id>' . $child[SIMPLEPIE_NAMESPACE_ATOM_10]['id'][0]['data'] . '</id>' . "\n"; } if (x($child[SIMPLEPIE_NAMESPACE_ATOM_10], 'link') && $child[SIMPLEPIE_NAMESPACE_ATOM_10]['link']) { $res['object'] .= '<link>' . encode_rel_links($child[SIMPLEPIE_NAMESPACE_ATOM_10]['link']) . '</link>' . "\n"; } if (x($child[SIMPLEPIE_NAMESPACE_ATOM_10], 'title') && $child[SIMPLEPIE_NAMESPACE_ATOM_10]['title'][0]['data']) { $res['object'] .= '<title>' . $child[SIMPLEPIE_NAMESPACE_ATOM_10]['title'][0]['data'] . '</title>' . "\n"; } if (x($child[SIMPLEPIE_NAMESPACE_ATOM_10], 'content') && $child[SIMPLEPIE_NAMESPACE_ATOM_10]['content'][0]['data']) { $body = $child[SIMPLEPIE_NAMESPACE_ATOM_10]['content'][0]['data']; if (!$body) { $body = $child[SIMPLEPIE_NAMESPACE_ATOM_10]['summary'][0]['data']; } // preserve a copy of the original body content in case we later need to parse out any microformat information, e.g. events $res['object'] .= '<orig>' . xmlify($body) . '</orig>' . "\n"; if (strpos($body, '<') !== false || strpos($body, '>') !== false) { $body = html2bb_video($body); $config = HTMLPurifier_Config::createDefault(); $config->set('Cache.DefinitionImpl', null); $purifier = new HTMLPurifier($config); $body = $purifier->purify($body); $body = html2bbcode($body); } $res['object'] .= '<content>' . $body . '</content>' . "\n"; } $res['object'] .= '</object>' . "\n"; } $rawobj = $item->get_item_tags(NAMESPACE_ACTIVITY, 'target'); if ($rawobj) { $res['target'] = '<target>' . "\n"; $child = $rawobj[0]['child']; if ($child[NAMESPACE_ACTIVITY]['object-type'][0]['data']) { $res['target'] .= '<type>' . $child[NAMESPACE_ACTIVITY]['object-type'][0]['data'] . '</type>' . "\n"; } if (x($child[SIMPLEPIE_NAMESPACE_ATOM_10], 'id') && $child[SIMPLEPIE_NAMESPACE_ATOM_10]['id'][0]['data']) { $res['target'] .= '<id>' . $child[SIMPLEPIE_NAMESPACE_ATOM_10]['id'][0]['data'] . '</id>' . "\n"; } if (x($child[SIMPLEPIE_NAMESPACE_ATOM_10], 'link') && $child[SIMPLEPIE_NAMESPACE_ATOM_10]['link']) { $res['target'] .= '<link>' . encode_rel_links($child[SIMPLEPIE_NAMESPACE_ATOM_10]['link']) . '</link>' . "\n"; } if (x($child[SIMPLEPIE_NAMESPACE_ATOM_10], 'data') && $child[SIMPLEPIE_NAMESPACE_ATOM_10]['title'][0]['data']) { $res['target'] .= '<title>' . $child[SIMPLEPIE_NAMESPACE_ATOM_10]['title'][0]['data'] . '</title>' . "\n"; } if (x($child[SIMPLEPIE_NAMESPACE_ATOM_10], 'data') && $child[SIMPLEPIE_NAMESPACE_ATOM_10]['content'][0]['data']) { $body = $child[SIMPLEPIE_NAMESPACE_ATOM_10]['content'][0]['data']; if (!$body) { $body = $child[SIMPLEPIE_NAMESPACE_ATOM_10]['summary'][0]['data']; } // preserve a copy of the original body content in case we later need to parse out any microformat information, e.g. events $res['target'] .= '<orig>' . xmlify($body) . '</orig>' . "\n"; if (strpos($body, '<') !== false || strpos($body, '>') !== false) { $body = html2bb_video($body); $config = HTMLPurifier_Config::createDefault(); $config->set('Cache.DefinitionImpl', null); $purifier = new HTMLPurifier($config); $body = $purifier->purify($body); $body = html2bbcode($body); } $res['target'] .= '<content>' . $body . '</content>' . "\n"; } $res['target'] .= '</target>' . "\n"; } // This is some experimental stuff. By now retweets are shown with "RT:" // But: There is data so that the message could be shown similar to native retweets // There is some better way to parse this array - but it didn't worked for me. $child = $item->feed->data["child"][SIMPLEPIE_NAMESPACE_ATOM_10]["feed"][0]["child"][SIMPLEPIE_NAMESPACE_ATOM_10]["entry"][0]["child"]["http://activitystrea.ms/spec/1.0/"][object][0]["child"]; if (is_array($child)) { logger('get_atom_elements: Looking for status.net repeated message'); $message = $child["http://activitystrea.ms/spec/1.0/"]["object"][0]["child"][SIMPLEPIE_NAMESPACE_ATOM_10]["content"][0]["data"]; $orig_id = ostatus_convert_href($child["http://activitystrea.ms/spec/1.0/"]["object"][0]["child"][SIMPLEPIE_NAMESPACE_ATOM_10]["id"][0]["data"]); $author = $child[SIMPLEPIE_NAMESPACE_ATOM_10]["author"][0]["child"][SIMPLEPIE_NAMESPACE_ATOM_10]; $uri = $author["uri"][0]["data"]; $name = $author["name"][0]["data"]; $avatar = @array_shift($author["link"][2]["attribs"]); $avatar = $avatar["href"]; if ($name != "" and $uri != "" and $avatar != "" and $message != "") { logger('get_atom_elements: fixing sender of repeated message. ' . $orig_id, LOGGER_DEBUG); if (!intval(get_config('system', 'wall-to-wall_share'))) { $prefix = share_header($name, $uri, $avatar, "", "", $orig_link); $res["body"] = $prefix . html2bbcode($message) . "[/share]"; } else { $res["owner-name"] = $res["author-name"]; $res["owner-link"] = $res["author-link"]; $res["owner-avatar"] = $res["author-avatar"]; $res["author-name"] = $name; $res["author-link"] = $uri; $res["author-avatar"] = $avatar; $res["body"] = html2bbcode($message); } } } if (isset($contact["network"]) and $contact["network"] == NETWORK_FEED and $contact['fetch_further_information']) { $preview = ""; // Handle enclosures and treat them as preview picture if (isset($attach)) { foreach ($attach as $attachment) { if ($attachment->type == "image/jpeg") { $preview = $attachment->link; } } } $res["body"] = $res["title"] . add_page_info($res['plink'], false, $preview, $contact['fetch_further_information'] == 2, $contact['ffi_keyword_blacklist']); $res["tag"] = add_page_keywords($res['plink'], false, $preview, $contact['fetch_further_information'] == 2, $contact['ffi_keyword_blacklist']); $res["title"] = ""; $res["object-type"] = ACTIVITY_OBJ_BOOKMARK; unset($res["attach"]); } elseif (isset($contact["network"]) and $contact["network"] == NETWORK_OSTATUS) { $res["body"] = add_page_info_to_body($res["body"]); } elseif (isset($contact["network"]) and $contact["network"] == NETWORK_FEED and strstr($res['plink'], ".app.net/")) { $res["body"] = add_page_info_to_body($res["body"]); } $arr = array('feed' => $feed, 'item' => $item, 'result' => $res); call_hooks('parse_atom', $arr); return $res; }
/** * @param object $feed * @param array $item * @param[out] array $author * @return multitype:multitype: string NULL number Ambigous <NULL, string, number> Ambigous <mixed, string> Ambigous <multitype:multitype:string Ambigous <NULL, string> , multitype:multitype:string unknown > multitype:NULL unknown */ function get_atom_elements($feed, $item, &$author) { //$best_photo = array(); $res = array(); $found_author = $item->get_author(); if ($found_author) { $author['author_name'] = unxmlify($found_author->get_name()); $author['author_link'] = unxmlify($found_author->get_link()); $author['author_is_feed'] = false; } else { $author['author_name'] = unxmlify($feed->get_title()); $author['author_link'] = unxmlify($feed->get_permalink()); $author['author_is_feed'] = true; } if (substr($author['author_link'], -1, 1) == '/') { $author['author_link'] = substr($author['author_link'], 0, -1); } $res['mid'] = base64url_encode(unxmlify($item->get_id())); $res['title'] = unxmlify($item->get_title()); $res['body'] = unxmlify($item->get_content()); $res['plink'] = unxmlify($item->get_link(0)); $res['item_flags'] = ITEM_RSS; // removing the content of the title if its identically to the body // This helps with auto generated titles e.g. from tumblr if (title_is_body($res["title"], $res["body"])) { $res['title'] = ""; } if ($res['plink']) { $base_url = implode('/', array_slice(explode('/', $res['plink']), 0, 3)); } else { $base_url = ''; } // look for a photo. We should check media size and find the best one, // but for now let's just find any author photo $rawauthor = $item->get_item_tags(SIMPLEPIE_NAMESPACE_ATOM_10, 'author'); if ($rawauthor && $rawauthor[0]['child'][SIMPLEPIE_NAMESPACE_ATOM_10]['link']) { $base = $rawauthor[0]['child'][SIMPLEPIE_NAMESPACE_ATOM_10]['link']; foreach ($base as $link) { if (!x($author, 'author_photo') || !$author['author_photo']) { if ($link['attribs']['']['rel'] === 'photo' || $link['attribs']['']['rel'] === 'avatar') { $author['author_photo'] = unxmlify($link['attribs']['']['href']); } } } } $rawactor = $item->get_item_tags(NAMESPACE_ACTIVITY, 'actor'); if ($rawactor && activity_match($rawactor[0]['child'][NAMESPACE_ACTIVITY]['obj_type'][0]['data'], ACTIVITY_OBJ_PERSON)) { $base = $rawactor[0]['child'][SIMPLEPIE_NAMESPACE_ATOM_10]['link']; if ($base && count($base)) { foreach ($base as $link) { if ($link['attribs']['']['rel'] === 'alternate' && !$res['author_link']) { $author['author_link'] = unxmlify($link['attribs']['']['href']); } if (!x($author, 'author_photo') || !$author['author_photo']) { if ($link['attribs']['']['rel'] === 'avatar' || $link['attribs']['']['rel'] === 'photo') { $author['author_photo'] = unxmlify($link['attribs']['']['href']); } } } } } // check for a yahoo media element (github etc.) if (!$author['author_photo']) { $rawmedia = $item->get_item_tags(NAMESPACE_YMEDIA, 'thumbnail'); if ($rawmedia && $rawmedia[0]['attribs']['']['url']) { $author['author_photo'] = strip_tags(unxmlify($rawmedia[0]['attribs']['']['url'])); } } // No photo/profile-link on the item - look at the feed level if (!x($author, 'author_link') || !x($author, 'author_photo')) { $rawauthor = $feed->get_feed_tags(SIMPLEPIE_NAMESPACE_ATOM_10, 'author'); if ($rawauthor && $rawauthor[0]['child'][SIMPLEPIE_NAMESPACE_ATOM_10]['link']) { $base = $rawauthor[0]['child'][SIMPLEPIE_NAMESPACE_ATOM_10]['link']; foreach ($base as $link) { if ($link['attribs']['']['rel'] === 'alternate' && !$author['author_link']) { $author['author_link'] = unxmlify($link['attribs']['']['href']); $author['author_is_feed'] = true; } if (!$author['author_photo']) { if ($link['attribs']['']['rel'] === 'photo' || $link['attribs']['']['rel'] === 'avatar') { $author['author_photo'] = unxmlify($link['attribs']['']['href']); } } } } $rawactor = $feed->get_feed_tags(NAMESPACE_ACTIVITY, 'subject'); if ($rawactor && activity_match($rawactor[0]['child'][NAMESPACE_ACTIVITY]['obj_type'][0]['data'], ACTIVITY_OBJ_PERSON)) { $base = $rawactor[0]['child'][SIMPLEPIE_NAMESPACE_ATOM_10]['link']; if ($base && count($base)) { foreach ($base as $link) { if ($link['attribs']['']['rel'] === 'alternate' && !$res['author_link']) { $author['author_link'] = unxmlify($link['attribs']['']['href']); } if (!x($author, 'author_photo')) { if ($link['attribs']['']['rel'] === 'avatar' || $link['attribs']['']['rel'] === 'photo') { $author['author_photo'] = unxmlify($link['attribs']['']['href']); } } } } } } $apps = $item->get_item_tags(NAMESPACE_STATUSNET, 'notice_info'); if ($apps && $apps[0]['attribs']['']['source']) { $res['app'] = strip_tags(unxmlify($apps[0]['attribs']['']['source'])); } /* * If there's a copy of the body content which is guaranteed to have survived mangling in transit, use it. */ $have_real_body = false; $rawenv = $item->get_item_tags(NAMESPACE_DFRN, 'env'); if ($rawenv) { $have_real_body = true; $res['body'] = $rawenv[0]['data']; $res['body'] = str_replace(array(' ', "\t", "\r", "\n"), array('', '', '', ''), $res['body']); // make sure nobody is trying to sneak some html tags by us $res['body'] = notags(base64url_decode($res['body'])); // We could probably turn these old Friendica bbcode bookmarks into bookmark tags but we'd have to // create a term table item for them. For now just make sure they stay as links. $res['body'] = preg_replace('/\\[bookmark(.*?)\\](.*?)\\[\\/bookmark\\]/', '[url$1]$2[/url]', $res['body']); } $res['body'] = limit_body_size($res['body']); // It isn't certain at this point whether our content is plaintext or html and we'd be foolish to trust // the content type. Our own network only emits text normally, though it might have been converted to // html if we used a pubsubhubbub transport. But if we see even one html tag in our text, we will // have to assume it is all html and needs to be purified. // It doesn't matter all that much security wise - because before this content is used anywhere, we are // going to escape any tags we find regardless, but this lets us import a limited subset of html from // the wild, by sanitising it and converting supported tags to bbcode before we rip out any remaining // html. if (strpos($res['body'], '<') !== false && strpos($res['body'], '>') !== false) { $res['body'] = reltoabs($res['body'], $base_url); $res['body'] = html2bb_video($res['body']); $res['body'] = oembed_html2bbcode($res['body']); $res['body'] = purify_html($res['body']); $res['body'] = @html2bbcode($res['body']); } elseif (!$have_real_body) { // it's not one of our messages and it has no tags // so it's probably just text. We'll escape it just to be safe. $res['body'] = escape_tags($res['body']); } if ($res['plink'] && $res['title']) { $res['body'] = '#^[url=' . $res['plink'] . ']' . $res['title'] . '[/url]' . "\n\n" . $res['body']; $terms = array(); $terms[] = array('otype' => TERM_OBJ_POST, 'type' => TERM_BOOKMARK, 'url' => $res['plink'], 'term' => $res['title']); } elseif ($res['plink']) { $res['body'] = '#^[url]' . $res['plink'] . '[/url]' . "\n\n" . $res['body']; $terms = array(); $terms[] = array('otype' => TERM_OBJ_POST, 'type' => TERM_BOOKMARK, 'url' => $res['plink'], 'term' => $res['plink']); } $private = $item->get_item_tags(NAMESPACE_DFRN, 'private'); if ($private && intval($private[0]['data']) > 0) { $res['item_private'] = intval($private[0]['data']) ? 1 : 0; } else { $res['item_private'] = 0; } $rawlocation = $item->get_item_tags(NAMESPACE_DFRN, 'location'); if ($rawlocation) { $res['location'] = unxmlify($rawlocation[0]['data']); } $rawcreated = $item->get_item_tags(SIMPLEPIE_NAMESPACE_ATOM_10, 'published'); if ($rawcreated) { $res['created'] = unxmlify($rawcreated[0]['data']); } $rawedited = $item->get_item_tags(SIMPLEPIE_NAMESPACE_ATOM_10, 'updated'); if ($rawedited) { $res['edited'] = unxmlify($rawedited[0]['data']); } if (x($res, 'edited') && !x($res, 'created')) { $res['created'] = $res['edited']; } if (!$res['created']) { $res['created'] = $item->get_date('c'); } if (!$res['edited']) { $res['edited'] = $item->get_date('c'); } // Disallow time travelling posts $d1 = strtotime($res['created']); $d2 = strtotime($res['edited']); $d3 = strtotime('now'); if ($d1 > $d3) { $res['created'] = datetime_convert(); } if ($d2 > $d3) { $res['edited'] = datetime_convert(); } $res['created'] = datetime_convert('UTC', 'UTC', $res['created']); $res['edited'] = datetime_convert('UTC', 'UTC', $res['edited']); $rawowner = $item->get_item_tags(NAMESPACE_DFRN, 'owner'); if (!$rawowner) { $rawowner = $item->get_item_tags(NAMESPACE_ZOT, 'owner'); } if ($rawowner[0]['child'][SIMPLEPIE_NAMESPACE_ATOM_10]['name'][0]['data']) { $author['owner_name'] = unxmlify($rawowner[0]['child'][SIMPLEPIE_NAMESPACE_ATOM_10]['name'][0]['data']); } elseif ($rawowner[0]['child'][NAMESPACE_DFRN]['name'][0]['data']) { $author['owner_name'] = unxmlify($rawowner[0]['child'][NAMESPACE_DFRN]['name'][0]['data']); } if ($rawowner[0]['child'][SIMPLEPIE_NAMESPACE_ATOM_10]['uri'][0]['data']) { $author['owner_link'] = unxmlify($rawowner[0]['child'][SIMPLEPIE_NAMESPACE_ATOM_10]['uri'][0]['data']); } elseif ($rawowner[0]['child'][NAMESPACE_DFRN]['uri'][0]['data']) { $author['owner_link'] = unxmlify($rawowner[0]['child'][NAMESPACE_DFRN]['uri'][0]['data']); } if ($rawowner[0]['child'][SIMPLEPIE_NAMESPACE_ATOM_10]['link']) { $base = $rawowner[0]['child'][SIMPLEPIE_NAMESPACE_ATOM_10]['link']; foreach ($base as $link) { if (!x($author, 'owner_photo') || !$author['owner_photo']) { if ($link['attribs']['']['rel'] === 'photo' || $link['attribs']['']['rel'] === 'avatar') { $author['owner_photo'] = unxmlify($link['attribs']['']['href']); } } } } $rawgeo = $item->get_item_tags(NAMESPACE_GEORSS, 'point'); if ($rawgeo) { $res['coord'] = unxmlify($rawgeo[0]['data']); } $rawverb = $item->get_item_tags(NAMESPACE_ACTIVITY, 'verb'); // select between supported verbs if ($rawverb) { $res['verb'] = unxmlify($rawverb[0]['data']); } // translate OStatus unfollow to activity streams if it happened to get selected if (x($res, 'verb') && $res['verb'] === 'http://ostatus.org/schema/1.0/unfollow') { $res['verb'] = ACTIVITY_UNFOLLOW; } $cats = $item->get_categories(); if ($cats) { if (is_null($terms)) { $terms = array(); } foreach ($cats as $cat) { $term = $cat->get_term(); if (!$term) { $term = $cat->get_label(); } $scheme = $cat->get_scheme(); $termurl = ''; if ($scheme && $term && stristr($scheme, 'X-DFRN:')) { $termtype = substr($scheme, 7, 1) === '#' ? TERM_HASHTAG : TERM_MENTION; $termurl = unxmlify(substr($scheme, 9)); } else { $termtype = TERM_CATEGORY; } $termterm = notags(trim(unxmlify($term))); if ($termterm) { $terms[] = array('otype' => TERM_OBJ_POST, 'type' => $termtype, 'url' => $termurl, 'term' => $termterm); } } } if (!is_null($terms)) { $res['term'] = $terms; } $attach = $item->get_enclosures(); if ($attach) { $res['attach'] = array(); foreach ($attach as $att) { $len = intval($att->get_length()); $link = str_replace(array(',', '"'), array('%2D', '%22'), notags(trim(unxmlify($att->get_link())))); $title = str_replace(array(',', '"'), array('%2D', '%22'), notags(trim(unxmlify($att->get_title())))); $type = str_replace(array(',', '"'), array('%2D', '%22'), notags(trim(unxmlify($att->get_type())))); if (strpos($type, ';')) { $type = substr($type, 0, strpos($type, ';')); } if (!$link || strpos($link, 'http') !== 0) { continue; } if (!$title) { $title = ' '; } if (!$type) { $type = 'application/octet-stream'; } $res['attach'][] = array('href' => $link, 'length' => $len, 'type' => $type, 'title' => $title); } } $rawobj = $item->get_item_tags(NAMESPACE_ACTIVITY, 'object'); if ($rawobj) { $obj = array(); $child = $rawobj[0]['child']; if ($child[NAMESPACE_ACTIVITY]['obj_type'][0]['data']) { $res['obj_type'] = $child[NAMESPACE_ACTIVITY]['obj_type'][0]['data']; $obj['type'] = $child[NAMESPACE_ACTIVITY]['obj_type'][0]['data']; } if (x($child[SIMPLEPIE_NAMESPACE_ATOM_10], 'id') && $child[SIMPLEPIE_NAMESPACE_ATOM_10]['id'][0]['data']) { $obj['id'] = $child[SIMPLEPIE_NAMESPACE_ATOM_10]['id'][0]['data']; } if (x($child[SIMPLEPIE_NAMESPACE_ATOM_10], 'link') && $child[SIMPLEPIE_NAMESPACE_ATOM_10]['link']) { $obj['link'] = encode_rel_links($child[SIMPLEPIE_NAMESPACE_ATOM_10]['link']); } if (x($child[SIMPLEPIE_NAMESPACE_ATOM_10], 'title') && $child[SIMPLEPIE_NAMESPACE_ATOM_10]['title'][0]['data']) { $obj['title'] = $child[SIMPLEPIE_NAMESPACE_ATOM_10]['title'][0]['data']; } if (x($child[SIMPLEPIE_NAMESPACE_ATOM_10], 'content') && $child[SIMPLEPIE_NAMESPACE_ATOM_10]['content'][0]['data']) { $body = $child[SIMPLEPIE_NAMESPACE_ATOM_10]['content'][0]['data']; if (!$body) { $body = $child[SIMPLEPIE_NAMESPACE_ATOM_10]['summary'][0]['data']; } // preserve a copy of the original body content in case we later need to parse out any microformat information, e.g. events $obj['orig'] = xmlify($body); if (strpos($body, '<') !== false || strpos($body, '>') !== false) { $body = purify_html($body); $body = html2bbcode($body); } $obj['content'] = $body; } $res['object'] = $obj; } $rawobj = $item->get_item_tags(NAMESPACE_ACTIVITY, 'target'); if ($rawobj) { $obj = array(); $child = $rawobj[0]['child']; if ($child[NAMESPACE_ACTIVITY]['obj_type'][0]['data']) { $res['tgt_type'] = $child[NAMESPACE_ACTIVITY]['obj_type'][0]['data']; $obj['type'] = $child[NAMESPACE_ACTIVITY]['obj_type'][0]['data']; } if (x($child[SIMPLEPIE_NAMESPACE_ATOM_10], 'id') && $child[SIMPLEPIE_NAMESPACE_ATOM_10]['id'][0]['data']) { $obj['id'] = $child[SIMPLEPIE_NAMESPACE_ATOM_10]['id'][0]['data']; } if (x($child[SIMPLEPIE_NAMESPACE_ATOM_10], 'link') && $child[SIMPLEPIE_NAMESPACE_ATOM_10]['link']) { $obj['link'] = encode_rel_links($child[SIMPLEPIE_NAMESPACE_ATOM_10]['link']); } if (x($child[SIMPLEPIE_NAMESPACE_ATOM_10], 'title') && $child[SIMPLEPIE_NAMESPACE_ATOM_10]['title'][0]['data']) { $obj['title'] = $child[SIMPLEPIE_NAMESPACE_ATOM_10]['title'][0]['data']; } if (x($child[SIMPLEPIE_NAMESPACE_ATOM_10], 'content') && $child[SIMPLEPIE_NAMESPACE_ATOM_10]['content'][0]['data']) { $body = $child[SIMPLEPIE_NAMESPACE_ATOM_10]['content'][0]['data']; if (!$body) { $body = $child[SIMPLEPIE_NAMESPACE_ATOM_10]['summary'][0]['data']; } // preserve a copy of the original body content in case we later need to parse out any microformat information, e.g. events $obj['orig'] = xmlify($body); if (strpos($body, '<') !== false || strpos($body, '>') !== false) { $body = purify_html($body); $body = html2bbcode($body); } $obj['content'] = $body; } $res['target'] = $obj; } $res['public_policy'] = 'specific'; $res['comment_policy'] = 'none'; $arr = array('feed' => $feed, 'item' => $item, 'result' => $res); call_hooks('parse_atom', $arr); logger('get_atom_elements: author: ' . print_r($author, true), LOGGER_DATA); logger('get_atom_elements: ' . print_r($res, true), LOGGER_DATA); return $res; }
function onepoll_run(&$argv, &$argc) { global $a, $db; if (is_null($a)) { $a = new App(); } if (is_null($db)) { @(include ".htconfig.php"); require_once "include/dba.php"; $db = new dba($db_host, $db_user, $db_pass, $db_data); unset($db_host, $db_user, $db_pass, $db_data); } require_once 'include/session.php'; require_once 'include/datetime.php'; require_once 'library/simplepie/simplepie.inc'; require_once 'include/items.php'; require_once 'include/Contact.php'; require_once 'include/email.php'; require_once 'include/socgraph.php'; require_once 'include/pidfile.php'; require_once 'include/queue_fn.php'; load_config('config'); load_config('system'); $a->set_baseurl(get_config('system', 'url')); load_hooks(); logger('onepoll: start'); $manual_id = 0; $generation = 0; $hub_update = false; $force = false; $restart = false; if ($argc > 1 && intval($argv[1])) { $contact_id = intval($argv[1]); } if (!$contact_id) { logger('onepoll: no contact'); return; } $lockpath = get_lockpath(); if ($lockpath != '') { $pidfile = new pidfile($lockpath, 'onepoll' . $contact_id); if ($pidfile->is_already_running()) { logger("onepoll: Already running for contact " . $contact_id); if ($pidfile->running_time() > 9 * 60) { $pidfile->kill(); logger("killed stale process"); } exit; } } $d = datetime_convert(); // Only poll from those with suitable relationships, // and which have a polling address and ignore Diaspora since // we are unable to match those posts with a Diaspora GUID and prevent duplicates. $contacts = q("SELECT `contact`.* FROM `contact`\n\t\tWHERE ( `rel` = %d OR `rel` = %d ) AND `poll` != ''\n\t\tAND NOT `network` IN ( '%s', '%s', '%s' )\n\t\tAND `contact`.`id` = %d\n\t\tAND `self` = 0 AND `contact`.`blocked` = 0 AND `contact`.`readonly` = 0\n\t\tAND `contact`.`archive` = 0 LIMIT 1", intval(CONTACT_IS_SHARING), intval(CONTACT_IS_FRIEND), dbesc(NETWORK_DIASPORA), dbesc(NETWORK_FACEBOOK), dbesc(NETWORK_PUMPIO), intval($contact_id)); if (!count($contacts)) { return; } $contact = $contacts[0]; $xml = false; $t = $contact['last-update']; if ($contact['subhub']) { $poll_interval = get_config('system', 'pushpoll_frequency'); $contact['priority'] = $poll_interval !== false ? intval($poll_interval) : 3; $hub_update = false; if (datetime_convert('UTC', 'UTC', 'now') > datetime_convert('UTC', 'UTC', $t . " + 1 day")) { $hub_update = true; } } else { $hub_update = false; } $importer_uid = $contact['uid']; $r = q("SELECT `contact`.*, `user`.`page-flags` FROM `contact` INNER JOIN `user` on `contact`.`uid` = `user`.`uid` WHERE `user`.`uid` = %d AND `contact`.`self` = 1 LIMIT 1", intval($importer_uid)); if (!count($r)) { return; } $importer = $r[0]; logger("onepoll: poll: ({$contact['id']}) IMPORTER: {$importer['name']}, CONTACT: {$contact['name']}"); $last_update = $contact['last-update'] === '0000-00-00 00:00:00' ? datetime_convert('UTC', 'UTC', 'now - 7 days', ATOM_TIME) : datetime_convert('UTC', 'UTC', $contact['last-update'], ATOM_TIME); if ($contact['network'] === NETWORK_DFRN) { $idtosend = $orig_id = $contact['dfrn-id'] ? $contact['dfrn-id'] : $contact['issued-id']; if (intval($contact['duplex']) && $contact['dfrn-id']) { $idtosend = '0:' . $orig_id; } if (intval($contact['duplex']) && $contact['issued-id']) { $idtosend = '1:' . $orig_id; } // they have permission to write to us. We already filtered this in the contact query. $perm = 'rw'; // But this may be our first communication, so set the writable flag if it isn't set already. if (!intval($contact['writable'])) { q("update contact set writable = 1 where id = %d", intval($contact['id'])); } $url = $contact['poll'] . '?dfrn_id=' . $idtosend . '&dfrn_version=' . DFRN_PROTOCOL_VERSION . '&type=data&last_update=' . $last_update . '&perm=' . $perm; $handshake_xml = fetch_url($url); $html_code = $a->get_curl_code(); logger('onepoll: handshake with url ' . $url . ' returns xml: ' . $handshake_xml, LOGGER_DATA); if (!strlen($handshake_xml) || $html_code >= 400 || !$html_code) { logger("poller: {$url} appears to be dead - marking for death "); // dead connection - might be a transient event, or this might // mean the software was uninstalled or the domain expired. // Will keep trying for one month. mark_for_death($contact); // set the last-update so we don't keep polling $r = q("UPDATE `contact` SET `last-update` = '%s' WHERE `id` = %d", dbesc(datetime_convert()), intval($contact['id'])); return; } if (!strstr($handshake_xml, '<')) { logger('poller: response from ' . $url . ' did not contain XML.'); mark_for_death($contact); $r = q("UPDATE `contact` SET `last-update` = '%s' WHERE `id` = %d", dbesc(datetime_convert()), intval($contact['id'])); return; } $res = parse_xml_string($handshake_xml); if (intval($res->status) == 1) { logger("poller: {$url} replied status 1 - marking for death "); // we may not be friends anymore. Will keep trying for one month. // set the last-update so we don't keep polling $r = q("UPDATE `contact` SET `last-update` = '%s' WHERE `id` = %d", dbesc(datetime_convert()), intval($contact['id'])); mark_for_death($contact); } else { if ($contact['term-date'] != '0000-00-00 00:00:00') { logger("poller: {$url} back from the dead - removing mark for death"); unmark_for_death($contact); } } if (intval($res->status) != 0 || !strlen($res->challenge) || !strlen($res->dfrn_id)) { return; } if ((double) $res->dfrn_version > 2.21 && $contact['poco'] == '') { q("update contact set poco = '%s' where id = %d", dbesc(str_replace('/profile/', '/poco/', $contact['url'])), intval($contact['id'])); } $postvars = array(); $sent_dfrn_id = hex2bin((string) $res->dfrn_id); $challenge = hex2bin((string) $res->challenge); $final_dfrn_id = ''; if ($contact['duplex'] && strlen($contact['prvkey'])) { openssl_private_decrypt($sent_dfrn_id, $final_dfrn_id, $contact['prvkey']); openssl_private_decrypt($challenge, $postvars['challenge'], $contact['prvkey']); } else { openssl_public_decrypt($sent_dfrn_id, $final_dfrn_id, $contact['pubkey']); openssl_public_decrypt($challenge, $postvars['challenge'], $contact['pubkey']); } $final_dfrn_id = substr($final_dfrn_id, 0, strpos($final_dfrn_id, '.')); if (strpos($final_dfrn_id, ':') == 1) { $final_dfrn_id = substr($final_dfrn_id, 2); } if ($final_dfrn_id != $orig_id) { logger('poller: ID did not decode: ' . $contact['id'] . ' orig: ' . $orig_id . ' final: ' . $final_dfrn_id); // did not decode properly - cannot trust this site return; } $postvars['dfrn_id'] = $idtosend; $postvars['dfrn_version'] = DFRN_PROTOCOL_VERSION; $postvars['perm'] = 'rw'; $xml = post_url($contact['poll'], $postvars); } elseif ($contact['network'] === NETWORK_OSTATUS || $contact['network'] === NETWORK_DIASPORA || $contact['network'] === NETWORK_FEED) { // Upgrading DB fields from an older Friendica version // Will only do this once per notify-enabled OStatus contact // or if relationship changes $stat_writeable = $contact['notify'] && ($contact['rel'] == CONTACT_IS_FOLLOWER || $contact['rel'] == CONTACT_IS_FRIEND) ? 1 : 0; if ($contact['network'] === NETWORK_OSTATUS && get_pconfig($importer_uid, 'system', 'ostatus_autofriend')) { $stat_writeable = 1; } if ($stat_writeable != $contact['writable']) { q("UPDATE `contact` SET `writable` = %d WHERE `id` = %d", intval($stat_writeable), intval($contact['id'])); } // Are we allowed to import from this person? if ($contact['rel'] == CONTACT_IS_FOLLOWER || $contact['blocked'] || $contact['readonly']) { return; } $xml = fetch_url($contact['poll']); } elseif ($contact['network'] === NETWORK_MAIL || $contact['network'] === NETWORK_MAIL2) { logger("Mail: Fetching", LOGGER_DEBUG); $mail_disabled = function_exists('imap_open') && !get_config('system', 'imap_disabled') ? 0 : 1; if ($mail_disabled) { return; } logger("Mail: Enabled", LOGGER_DEBUG); $mbox = null; $x = q("SELECT `prvkey` FROM `user` WHERE `uid` = %d LIMIT 1", intval($importer_uid)); $mailconf = q("SELECT * FROM `mailacct` WHERE `server` != '' AND `uid` = %d LIMIT 1", intval($importer_uid)); if (count($x) && count($mailconf)) { $mailbox = construct_mailbox_name($mailconf[0]); $password = ''; openssl_private_decrypt(hex2bin($mailconf[0]['pass']), $password, $x[0]['prvkey']); $mbox = email_connect($mailbox, $mailconf[0]['user'], $password); unset($password); logger("Mail: Connect to " . $mailconf[0]['user']); if ($mbox) { q("UPDATE `mailacct` SET `last_check` = '%s' WHERE `id` = %d AND `uid` = %d", dbesc(datetime_convert()), intval($mailconf[0]['id']), intval($importer_uid)); logger("Mail: Connected to " . $mailconf[0]['user']); } else { logger("Mail: Connection error " . $mailconf[0]['user'] . " " . print_r(imap_errors())); } } if ($mbox) { $msgs = email_poll($mbox, $contact['addr']); if (count($msgs)) { logger("Mail: Parsing " . count($msgs) . " mails for " . $mailconf[0]['user'], LOGGER_DEBUG); $metas = email_msg_meta($mbox, implode(',', $msgs)); if (count($metas) != count($msgs)) { logger("onepoll: for " . $mailconf[0]['user'] . " there are " . count($msgs) . " messages but received " . count($metas) . " metas", LOGGER_DEBUG); } else { $msgs = array_combine($msgs, $metas); foreach ($msgs as $msg_uid => $meta) { logger("Mail: Parsing mail " . $msg_uid, LOGGER_DATA); $datarray = array(); $datarray['verb'] = ACTIVITY_POST; $datarray['object-type'] = ACTIVITY_OBJ_NOTE; // $meta = email_msg_meta($mbox,$msg_uid); // $headers = email_msg_headers($mbox,$msg_uid); $datarray['uri'] = msgid2iri(trim($meta->message_id, '<>')); // Have we seen it before? $r = q("SELECT * FROM `item` WHERE `uid` = %d AND `uri` = '%s' LIMIT 1", intval($importer_uid), dbesc($datarray['uri'])); if (count($r)) { logger("Mail: Seen before " . $msg_uid . " for " . $mailconf[0]['user'] . " UID: " . $importer_uid . " URI: " . $datarray['uri'], LOGGER_DEBUG); // Only delete when mails aren't automatically moved or deleted if ($mailconf[0]['action'] != 1 and $mailconf[0]['action'] != 3) { if ($meta->deleted && !$r[0]['deleted']) { q("UPDATE `item` SET `deleted` = 1, `changed` = '%s' WHERE `id` = %d", dbesc(datetime_convert()), intval($r[0]['id'])); } } switch ($mailconf[0]['action']) { case 0: logger("Mail: Seen before " . $msg_uid . " for " . $mailconf[0]['user'] . ". Doing nothing.", LOGGER_DEBUG); break; case 1: logger("Mail: Deleting " . $msg_uid . " for " . $mailconf[0]['user']); imap_delete($mbox, $msg_uid, FT_UID); break; case 2: logger("Mail: Mark as seen " . $msg_uid . " for " . $mailconf[0]['user']); imap_setflag_full($mbox, $msg_uid, "\\Seen", ST_UID); break; case 3: logger("Mail: Moving " . $msg_uid . " to " . $mailconf[0]['movetofolder'] . " for " . $mailconf[0]['user']); imap_setflag_full($mbox, $msg_uid, "\\Seen", ST_UID); if ($mailconf[0]['movetofolder'] != "") { imap_mail_move($mbox, $msg_uid, $mailconf[0]['movetofolder'], FT_UID); } break; } continue; } // look for a 'references' or an 'in-reply-to' header and try to match with a parent item we have locally. // $raw_refs = ((x($headers,'references')) ? str_replace("\t",'',$headers['references']) : ''); $raw_refs = property_exists($meta, 'references') ? str_replace("\t", '', $meta->references) : ''; if (!trim($raw_refs)) { $raw_refs = property_exists($meta, 'in_reply_to') ? str_replace("\t", '', $meta->in_reply_to) : ''; } $raw_refs = trim($raw_refs); // Don't allow a blank reference in $refs_arr if ($raw_refs) { $refs_arr = explode(' ', $raw_refs); if (count($refs_arr)) { for ($x = 0; $x < count($refs_arr); $x++) { $refs_arr[$x] = "'" . msgid2iri(str_replace(array('<', '>', ' '), array('', '', ''), dbesc($refs_arr[$x]))) . "'"; } } $qstr = implode(',', $refs_arr); $r = q("SELECT `uri` , `parent-uri` FROM `item` WHERE `uri` IN ( {$qstr} ) AND `uid` = %d LIMIT 1", intval($importer_uid)); if (count($r)) { $datarray['parent-uri'] = $r[0]['parent-uri']; } // Set the parent as the top-level item // $datarray['parent-uri'] = $r[0]['uri']; } // Decoding the header $subject = imap_mime_header_decode($meta->subject); $datarray['title'] = ""; foreach ($subject as $subpart) { if ($subpart->charset != "default") { $datarray['title'] .= iconv($subpart->charset, 'UTF-8//IGNORE', $subpart->text); } else { $datarray['title'] .= $subpart->text; } } $datarray['title'] = notags(trim($datarray['title'])); //$datarray['title'] = notags(trim($meta->subject)); $datarray['created'] = datetime_convert('UTC', 'UTC', $meta->date); // Is it a reply? $reply = (substr(strtolower($datarray['title']), 0, 3) == "re:" or substr(strtolower($datarray['title']), 0, 3) == "re-" or $raw_refs != ""); // Remove Reply-signs in the subject $datarray['title'] = RemoveReply($datarray['title']); // If it seems to be a reply but a header couldn't be found take the last message with matching subject if (!x($datarray, 'parent-uri') and $reply) { $r = q("SELECT `uri` , `parent-uri` FROM `item` WHERE `title` = \"%s\" AND `uid` = %d ORDER BY `created` DESC LIMIT 1", dbesc(protect_sprintf($datarray['title'])), intval($importer_uid)); if (count($r)) { $datarray['parent-uri'] = $r[0]['parent-uri']; } } if (!x($datarray, 'parent-uri')) { $datarray['parent-uri'] = $datarray['uri']; } $r = email_get_msg($mbox, $msg_uid, $reply); if (!$r) { logger("Mail: can't fetch msg " . $msg_uid . " for " . $mailconf[0]['user']); continue; } $datarray['body'] = escape_tags($r['body']); $datarray['body'] = limit_body_size($datarray['body']); logger("Mail: Importing " . $msg_uid . " for " . $mailconf[0]['user']); // some mailing lists have the original author as 'from' - add this sender info to msg body. // todo: adding a gravatar for the original author would be cool if (!stristr($meta->from, $contact['addr'])) { $from = imap_mime_header_decode($meta->from); $fromdecoded = ""; foreach ($from as $frompart) { if ($frompart->charset != "default") { $fromdecoded .= iconv($frompart->charset, 'UTF-8//IGNORE', $frompart->text); } else { $fromdecoded .= $frompart->text; } } $fromarr = imap_rfc822_parse_adrlist($fromdecoded, $a->get_hostname()); $frommail = $fromarr[0]->mailbox . "@" . $fromarr[0]->host; if (isset($fromarr[0]->personal)) { $fromname = $fromarr[0]->personal; } else { $fromname = $frommail; } //$datarray['body'] = "[b]".t('From: ') . escape_tags($fromdecoded) . "[/b]\n\n" . $datarray['body']; $datarray['author-name'] = $fromname; $datarray['author-link'] = "mailto:" . $frommail; $datarray['author-avatar'] = $contact['photo']; $datarray['owner-name'] = $contact['name']; $datarray['owner-link'] = "mailto:" . $contact['addr']; $datarray['owner-avatar'] = $contact['photo']; } else { $datarray['author-name'] = $contact['name']; $datarray['author-link'] = 'mailbox'; $datarray['author-avatar'] = $contact['photo']; } $datarray['uid'] = $importer_uid; $datarray['contact-id'] = $contact['id']; if ($datarray['parent-uri'] === $datarray['uri']) { $datarray['private'] = 1; } if ($contact['network'] === NETWORK_MAIL && !get_pconfig($importer_uid, 'system', 'allow_public_email_replies')) { $datarray['private'] = 1; $datarray['allow_cid'] = '<' . $contact['id'] . '>'; } $stored_item = item_store($datarray); q("UPDATE `item` SET `last-child` = 0 WHERE `parent-uri` = '%s' AND `uid` = %d", dbesc($datarray['parent-uri']), intval($importer_uid)); q("UPDATE `item` SET `last-child` = 1 WHERE `id` = %d", intval($stored_item)); switch ($mailconf[0]['action']) { case 0: logger("Mail: Seen before " . $msg_uid . " for " . $mailconf[0]['user'] . ". Doing nothing.", LOGGER_DEBUG); break; case 1: logger("Mail: Deleting " . $msg_uid . " for " . $mailconf[0]['user']); imap_delete($mbox, $msg_uid, FT_UID); break; case 2: logger("Mail: Mark as seen " . $msg_uid . " for " . $mailconf[0]['user']); imap_setflag_full($mbox, $msg_uid, "\\Seen", ST_UID); break; case 3: logger("Mail: Moving " . $msg_uid . " to " . $mailconf[0]['movetofolder'] . " for " . $mailconf[0]['user']); imap_setflag_full($mbox, $msg_uid, "\\Seen", ST_UID); if ($mailconf[0]['movetofolder'] != "") { imap_mail_move($mbox, $msg_uid, $mailconf[0]['movetofolder'], FT_UID); } break; } } } } else { logger("Mail: no mails for " . $mailconf[0]['user']); } logger("Mail: closing connection for " . $mailconf[0]['user']); imap_close($mbox); } } elseif ($contact['network'] === NETWORK_FACEBOOK) { // This is picked up by the Facebook plugin on a cron hook. // Ignored here. } elseif ($contact['network'] === NETWORK_PUMPIO) { // This is picked up by the pump.io plugin on a cron hook. // Ignored here. } if ($xml) { logger('poller: received xml : ' . $xml, LOGGER_DATA); if (!strstr($xml, '<')) { logger('poller: post_handshake: response from ' . $url . ' did not contain XML.'); $r = q("UPDATE `contact` SET `last-update` = '%s' WHERE `id` = %d", dbesc(datetime_convert()), intval($contact['id'])); return; } consume_feed($xml, $importer, $contact, $hub, 1, 1); // do it twice. Ensures that children of parents which may be later in the stream aren't tossed consume_feed($xml, $importer, $contact, $hub, 1, 2); $hubmode = 'subscribe'; if ($contact['network'] === NETWORK_DFRN || $contact['blocked'] || $contact['readonly']) { $hubmode = 'unsubscribe'; } if (($contact['network'] === NETWORK_OSTATUS || $contact['network'] == NETWORK_FEED) && !$contact['hub-verify']) { $hub_update = true; } if (strlen($hub) && $hub_update && ($contact['rel'] != CONTACT_IS_FOLLOWER || $contact['network'] == NETWORK_FEED)) { logger('poller: hub ' . $hubmode . ' : ' . $hub . ' contact name : ' . $contact['name'] . ' local user : '******'name']); $hubs = explode(',', $hub); if (count($hubs)) { foreach ($hubs as $h) { $h = trim($h); if (!strlen($h)) { continue; } subscribe_to_hub($h, $importer, $contact, $hubmode); } } } } $updated = datetime_convert(); $r = q("UPDATE `contact` SET `last-update` = '%s', `success_update` = '%s' WHERE `id` = %d", dbesc($updated), dbesc($updated), intval($contact['id'])); // load current friends if possible. if ($contact['poco']) { $r = q("SELECT count(*) as total from glink\n\t\t\twhere `cid` = %d and updated > UTC_TIMESTAMP() - INTERVAL 1 DAY", intval($contact['id'])); } if (count($r)) { if (!$r[0]['total']) { poco_load($contact['id'], $importer_uid, 0, $contact['poco']); } } return; }