require_once('include/oembed.php');
require_once('include/salmon.php');
require_once('include/crypto.php');
+require_once('include/Photo.php');
+
function get_feed_for(&$a, $dfrn_id, $owner_nick, $last_update, $direction = 0) {
}
return '';
-}
+}
+
+/* limit_body_size()
+ *
+ * The purpose of this function is to apply system message length limits to
+ * imported messages without including any embedded photos in the length
+ */
+if(! function_exists('limit_body_size')) {
+function limit_body_size($body) {
+
+ logger('limit_body_size: start', LOGGER_DEBUG);
+
+ $maxlen = get_max_import_size();
+
+ // If the length of the body, including the embedded images, is smaller
+ // than the maximum, then don't waste time looking for the images
+ if($maxlen && (strlen($body) > $maxlen)) {
+
+ logger('limit_body_size: the total body length exceeds the limit', LOGGER_DEBUG);
+
+ $orig_body = $body;
+ $new_body = '';
+ $textlen = 0;
+ $max_found = false;
+
+ $img_start = strpos($orig_body, '[img');
+ $img_st_close = ($img_start !== false ? strpos(substr($orig_body, $img_start), ']') : false);
+ $img_end = ($img_start !== false ? strpos(substr($orig_body, $img_start), '[/img]') : false);
+ while(($img_st_close !== false) && ($img_end !== false)) {
+
+ $img_st_close++; // make it point to AFTER the closing bracket
+ $img_end += $img_start;
+ $img_end += strlen('[/img]');
+
+ if(! strcmp(substr($orig_body, $img_start + $img_st_close, 5), 'data:')) {
+ // This is an embedded image
+
+ if( ($textlen + $img_start) > $maxlen ) {
+ if($textlen < $maxlen) {
+ logger('limit_body_size: the limit happens before an embedded image', LOGGER_DEBUG);
+ $new_body = $new_body . substr($orig_body, 0, $maxlen - $textlen);
+ $textlen = $maxlen;
+ }
+ }
+ else {
+ $new_body = $new_body . substr($orig_body, 0, $img_start);
+ $textlen += $img_start;
+ }
+
+ $new_body = $new_body . substr($orig_body, $img_start, $img_end - $img_start);
+ }
+ else {
+
+ if( ($textlen + $img_end) > $maxlen ) {
+ if($textlen < $maxlen) {
+ logger('limit_body_size: the limit happens before the end of a non-embedded image', LOGGER_DEBUG);
+ $new_body = $new_body . substr($orig_body, 0, $maxlen - $textlen);
+ $textlen = $maxlen;
+ }
+ }
+ else {
+ $new_body = $new_body . substr($orig_body, 0, $img_end);
+ $textlen += $img_end;
+ }
+ }
+ $orig_body = substr($orig_body, $img_end);
+
+ if($orig_body === false) // in case the body ends on a closing image tag
+ $orig_body = '';
+
+ $img_start = strpos($orig_body, '[img');
+ $img_st_close = ($img_start !== false ? strpos(substr($orig_body, $img_start), ']') : false);
+ $img_end = ($img_start !== false ? strpos(substr($orig_body, $img_start), '[/img]') : false);
+ }
+
+ if( ($textlen + strlen($orig_body)) > $maxlen) {
+ if($textlen < $maxlen) {
+ logger('limit_body_size: the limit happens after the end of the last image', LOGGER_DEBUG);
+ $new_body = $new_body . substr($orig_body, 0, $maxlen - $textlen);
+ $textlen = $maxlen;
+ }
+ }
+ else {
+ logger('limit_body_size: the text size with embedded images extracted did not violate the limit', LOGGER_DEBUG);
+ $new_body = $new_body . $orig_body;
+ $textlen += strlen($orig_body);
+ }
+
+ return $new_body;
+ }
+ else
+ return $body;
+}}
+
+function title_is_body($title, $body) {
+ $title = strip_tags($title);
+ $title = trim($title);
+ $title = str_replace(array("\n", "\r", "\t", " "), array("","","",""), $title);
+
+ $body = strip_tags($body);
+ $body = trim($body);
+ $body = str_replace(array("\n", "\r", "\t", " "), array("","","",""), $body);
+
+ if (strlen($title) < strlen($body))
+ $body = substr($body, 0, strlen($title));
+
+ if (($title != $body) and (substr($title, -3) == "...")) {
+ $pos = strrpos($title, "...");
+ if ($pos > 0) {
+ $title = substr($title, 0, $pos);
+ $body = substr($body, 0, $pos);
+ }
+ }
+
+ return($title == $body);
+}
$res['body'] = unxmlify($item->get_content());
$res['plink'] = unxmlify($item->get_link(0));
+ // 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
$res['author-avatar'] = unxmlify($link['attribs']['']['href']);
}
}
- }
+ }
$rawactor = $item->get_item_tags(NAMESPACE_ACTIVITY, 'actor');
$res['author-avatar'] = unxmlify($link['attribs']['']['href']);
}
}
- }
+ }
$rawactor = $feed->get_feed_tags(NAMESPACE_ACTIVITY, 'subject');
$res['app'] = strip_tags(unxmlify($apps[0]['attribs']['']['source']));
if($res['app'] === 'web')
$res['app'] = 'OStatus';
- }
+ }
// base64 encoded json structure representing Diaspora signature
$res['body'] = notags(base64url_decode($res['body']));
}
- $maxlen = get_max_import_size();
- if($maxlen && (strlen($res['body']) > $maxlen))
- $res['body'] = substr($res['body'],0, $maxlen);
+
+ $res['body'] = limit_body_size($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
foreach($base as $link) {
if(!x($res, 'owner-avatar') || !$res['owner-avatar']) {
- if($link['attribs']['']['rel'] === 'photo' || $link['attribs']['']['rel'] === 'avatar')
+ if($link['attribs']['']['rel'] === 'photo' || $link['attribs']['']['rel'] === 'avatar')
$res['owner-avatar'] = unxmlify($link['attribs']['']['href']);
}
}
call_hooks('parse_atom', $arr);
+ //if (($res["title"] != "") or (strpos($res["body"], "RT @") > 0)) {
+ if (strpos($res["body"], "RT @") !== false) {
+ $debugfile = tempnam("/home/ike/log", "item-res2-");
+ file_put_contents($debugfile, serialize($arr));
+ }
+
return $res;
}
if((strpos($arr['body'],'<') !== false) || (strpos($arr['body'],'>') !== false))
$arr['body'] = strip_tags($arr['body']);
+ require_once('Text/LanguageDetect.php');
+ $naked_body = preg_replace('/\[(.+?)\]/','',$arr['body']);
+ $l = new Text_LanguageDetect;
+ $lng = $l->detectConfidence($naked_body);
+ $arr['postopts'] = (($lng['language']) ? 'lang=' . $lng['language'] . ';' . $lng['confidence'] : '');
+
$arr['wall'] = ((x($arr,'wall')) ? intval($arr['wall']) : 0);
$arr['uri'] = ((x($arr,'uri')) ? notags(trim($arr['uri'])) : random_string());
if($r[0]['uri'] != $r[0]['parent-uri']) {
$arr['thr-parent'] = $arr['parent-uri'];
$arr['parent-uri'] = $r[0]['parent-uri'];
- $z = q("SELECT `id` FROM `item` WHERE `uri` = '%s' AND `parent-uri` = '%s' AND `uid` = %d
+ $z = q("SELECT * FROM `item` WHERE `uri` = '%s' AND `parent-uri` = '%s' AND `uid` = %d
ORDER BY `id` ASC LIMIT 1",
dbesc($r[0]['parent-uri']),
dbesc($r[0]['parent-uri']),
// Now process the feed
- if($feed->get_item_quantity()) {
+ if($feed->get_item_quantity()) {
logger('consume_feed: feed item count = ' . $feed->get_item_quantity());
foreach($items as $item) {
- $is_reply = false;
+ $is_reply = false;
$item_id = $item->get_id();
$rawthread = $item->get_item_tags( NAMESPACE_THREAD,'in-reply-to');
if(isset($rawthread[0]['attribs']['']['ref'])) {
continue;
// Have we seen it? If not, import it.
-
+
$item_id = $item->get_id();
$datarray = get_atom_elements($feed,$item);
-
if((! x($datarray,'author-name')) && ($contact['network'] != NETWORK_DFRN))
$datarray['author-name'] = $contact['name'];
if((! x($datarray,'author-link')) && ($contact['network'] != NETWORK_DFRN))
return $o;
}
-function fix_private_photos($s,$uid, $item = null, $cid = 0) {
+function fix_private_photos($s, $uid, $item = null, $cid = 0) {
$a = get_app();
logger('fix_private_photos', LOGGER_DEBUG);
$site = substr($a->get_baseurl(),strpos($a->get_baseurl(),'://'));
- if(preg_match("/\[img(.*?)\](.*?)\[\/img\]/is",$s,$matches)) {
- $image = $matches[2];
+ $orig_body = $s;
+ $new_body = '';
+
+ $img_start = strpos($orig_body, '[img');
+ $img_st_close = ($img_start !== false ? strpos(substr($orig_body, $img_start), ']') : false);
+ $img_len = ($img_start !== false ? strpos(substr($orig_body, $img_start + $img_st_close + 1), '[/img]') : false);
+ while( ($img_st_close !== false) && ($img_len !== false) ) {
+
+ $img_st_close++; // make it point to AFTER the closing bracket
+ $image = substr($orig_body, $img_start + $img_st_close, $img_len);
+
logger('fix_private_photos: found photo ' . $image, LOGGER_DEBUG);
+
+
if(stristr($image , $site . '/photo/')) {
+ // Only embed locally hosted photos
$replace = false;
$i = basename($image);
$i = str_replace(array('.jpg','.png'),array('',''),$i);
$x = strpos($i,'-');
+
if($x) {
$res = substr($i,$x+1);
$i = substr($i,0,$x);
// 3. Otherwise, if we have an item, see if the item permissions match the photo
// permissions, regardless of order but first check to see if they're an exact
// match to save some processing overhead.
-
- // Currently we only embed one private photo per message so as not to hit import
- // size limits at the receiving end.
-
- // To embed multiples, we would need to parse out the embedded photos on message
- // receipt and limit size based only on the text component. Would also need to
- // ignore all photos during bbcode translation and item localisation, as these
- // will hit internal regex backtrace limits.
if(has_permissions($r[0])) {
if($cid) {
}
}
if($replace) {
+ $data = $r[0]['data'];
+ $type = $r[0]['type'];
+
+ // If a custom width and height were specified, apply before embedding
+ if(preg_match("/\[img\=([0-9]*)x([0-9]*)\]/is", substr($orig_body, $img_start, $img_st_close), $match)) {
+ logger('fix_private_photos: scaling photo', LOGGER_DEBUG);
+
+ $width = intval($match[1]);
+ $height = intval($match[2]);
+
+ $ph = new Photo($data, $type);
+ if($ph->is_valid()) {
+ $ph->scaleImage(max($width, $height));
+ $data = $ph->imageString();
+ $type = $ph->getType();
+ }
+ }
+
logger('fix_private_photos: replacing photo', LOGGER_DEBUG);
- $s = str_replace($image, 'data:' . $r[0]['type'] . ';base64,' . base64_encode($r[0]['data']), $s);
- logger('fix_private_photos: replaced: ' . $s, LOGGER_DATA);
+ $image = 'data:' . $type . ';base64,' . base64_encode($data);
+ logger('fix_private_photos: replaced: ' . $image, LOGGER_DATA);
}
}
}
}
+
+ $new_body = $new_body . substr($orig_body, 0, $img_start + $img_st_close) . $image . '[/img]';
+ $orig_body = substr($orig_body, $img_start + $img_st_close + $img_len + strlen('[/img]'));
+ if($orig_body === false)
+ $orig_body = '';
+
+ $img_start = strpos($orig_body, '[img');
+ $img_st_close = ($img_start !== false ? strpos(substr($orig_body, $img_start), ']') : false);
+ $img_len = ($img_start !== false ? strpos(substr($orig_body, $img_start + $img_st_close + 1), '[/img]') : false);
}
- return($s);
+
+ $new_body = $new_body . $orig_body;
+
+ return($new_body);
}
$dnow = substr($dthen,0,8) . '28';
$ret = array();
- while($dnow >= $dthen) {
+ // Starting with the current month, get the first and last days of every
+ // month down to and including the month of the first post
+ while(substr($dnow, 0, 7) >= substr($dthen, 0, 7)) {
$dstart = substr($dnow,0,8) . '01';
$dend = substr($dnow,0,8) . get_dim(intval($dnow),intval(substr($dnow,5)));
$start_month = datetime_convert('','',$dstart,'Y-m-d');
return $o;
}
-
function store_diaspora_retract_sig($item, $user, $baseurl) {
// Note that we can't add a target_author_signature
// if the comment was deleted by a remote user. That should be ok, because if a remote user is deleting
}
else {
$r = q("SELECT `nick`, `url` FROM `contact` WHERE `id` = '%d' LIMIT 1",
- $item['contact-id']
+ $item['contact-id'] // If this function gets called, drop_item() has already checked remote_user() == $item['contact-id']
);
if(count($r)) {
// The below handle only works for NETWORK_DFRN. I think that's ok, because this function