Improved ATOM distinction, added OPML

This commit is contained in:
Michael 2023-05-06 13:52:39 +00:00
parent 74bcc33fdb
commit d4f0c1a8dc
2 changed files with 108 additions and 53 deletions

View file

@ -41,6 +41,8 @@ class Conversation
const PARCEL_RDF = 12; const PARCEL_RDF = 12;
const PARCEL_RSS = 13; const PARCEL_RSS = 13;
const PARCEL_ATOM = 14; const PARCEL_ATOM = 14;
const PARCEL_ATOM03 = 15;
const PARCEL_OPML = 16;
const PARCEL_TWITTER = 67; const PARCEL_TWITTER = 67;
const PARCEL_UNKNOWN = 255; const PARCEL_UNKNOWN = 255;

View file

@ -93,11 +93,8 @@ class Feed
@$doc->loadXML($xml); @$doc->loadXML($xml);
$xpath = new DOMXPath($doc); $xpath = new DOMXPath($doc);
if (strpos($xml, ActivityNamespace::ATOM03) && !strpos($xml, ActivityNamespace::ATOM1)) { $xpath->registerNamespace('atom', ActivityNamespace::ATOM1);
$xpath->registerNamespace('atom', ActivityNamespace::ATOM03); $xpath->registerNamespace('atom03', ActivityNamespace::ATOM03);
} else {
$xpath->registerNamespace('atom', ActivityNamespace::ATOM1);
}
$xpath->registerNamespace('dc', 'http://purl.org/dc/elements/1.1/'); $xpath->registerNamespace('dc', 'http://purl.org/dc/elements/1.1/');
$xpath->registerNamespace('content', 'http://purl.org/rss/1.0/modules/content/'); $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('rdf', 'http://www.w3.org/1999/02/22-rdf-syntax-ns#');
@ -106,6 +103,7 @@ class Feed
$xpath->registerNamespace('poco', ActivityNamespace::POCO); $xpath->registerNamespace('poco', ActivityNamespace::POCO);
$author = []; $author = [];
$atomns = '';
$entries = null; $entries = null;
$protocol = Conversation::PARCEL_UNKNOWN; $protocol = Conversation::PARCEL_UNKNOWN;
@ -121,10 +119,23 @@ class Feed
$entries = $xpath->query('/rdf:RDF/rss:item'); $entries = $xpath->query('/rdf:RDF/rss:item');
} }
if ($xpath->query('/opml')->length > 0) {
$protocol = Conversation::PARCEL_OPML;
$author['author-name'] = XML::getFirstNodeValue($xpath, '/opml/head/title/text()');
$entries = $xpath->query('/opml/body/outline');
}
// Is it Atom? // Is it Atom?
if ($xpath->query('/atom:feed')->length > 0) { if ($xpath->query('/atom:feed')->length > 0) {
$protocol = Conversation::PARCEL_ATOM; $protocol = Conversation::PARCEL_ATOM;
$alternate = XML::getFirstAttributes($xpath, "atom:link[@rel='alternate']"); $atomns = 'atom';
} elseif ($xpath->query('/atom03:feed')->length > 0) {
$protocol = Conversation::PARCEL_ATOM03;
$atomns = 'atom03';
}
if (!empty($atomns)) {
$alternate = XML::getFirstAttributes($xpath, $atomns . ":link[@rel='alternate']");
if (is_object($alternate)) { if (is_object($alternate)) {
foreach ($alternate as $attribute) { foreach ($alternate as $attribute) {
if ($attribute->name == 'href') { if ($attribute->name == 'href') {
@ -134,7 +145,7 @@ class Feed
} }
if (empty($author['author-link'])) { if (empty($author['author-link'])) {
$self = XML::getFirstAttributes($xpath, "atom:link[@rel='self']"); $self = XML::getFirstAttributes($xpath, $atomns . ":link[@rel='self']");
if (is_object($self)) { if (is_object($self)) {
foreach ($self as $attribute) { foreach ($self as $attribute) {
if ($attribute->name == 'href') { if ($attribute->name == 'href') {
@ -145,50 +156,50 @@ class Feed
} }
if (empty($author['author-link'])) { if (empty($author['author-link'])) {
$author['author-link'] = XML::getFirstNodeValue($xpath, '/atom:feed/atom:id/text()'); $author['author-link'] = XML::getFirstNodeValue($xpath, '/' . $atomns . ':feed/' . $atomns . ':id/text()');
} }
$author['author-avatar'] = XML::getFirstNodeValue($xpath, '/atom:feed/atom:logo/text()'); $author['author-avatar'] = XML::getFirstNodeValue($xpath, '/' . $atomns . ':feed/' . $atomns . ':logo/text()');
$author['author-name'] = XML::getFirstNodeValue($xpath, '/atom:feed/atom:title/text()'); $author['author-name'] = XML::getFirstNodeValue($xpath, '/' . $atomns . ':feed/' . $atomns . ':title/text()');
if (empty($author['author-name'])) { if (empty($author['author-name'])) {
$author['author-name'] = XML::getFirstNodeValue($xpath, '/atom:feed/atom:subtitle/text()'); $author['author-name'] = XML::getFirstNodeValue($xpath, '/' . $atomns . ':feed/' . $atomns . ':subtitle/text()');
} }
if (empty($author['author-name'])) { if (empty($author['author-name'])) {
$author['author-name'] = XML::getFirstNodeValue($xpath, '/atom:feed/atom:author/atom:name/text()'); $author['author-name'] = XML::getFirstNodeValue($xpath, '/' . $atomns . ':feed/' . $atomns . ':author/' . $atomns . ':name/text()');
} }
$value = XML::getFirstNodeValue($xpath, 'atom:author/poco:displayName/text()'); $value = XML::getFirstNodeValue($xpath, '' . $atomns . ':author/poco:displayName/text()');
if ($value != '') { if ($value != '') {
$author['author-name'] = $value; $author['author-name'] = $value;
} }
if ($dryRun) { if ($dryRun) {
$author['author-id'] = XML::getFirstNodeValue($xpath, '/atom:feed/atom:author/atom:id/text()'); $author['author-id'] = XML::getFirstNodeValue($xpath, '/' . $atomns . ':feed/' . $atomns . ':author/' . $atomns . ':id/text()');
// See https://tools.ietf.org/html/rfc4287#section-3.2.2 // See https://tools.ietf.org/html/rfc4287#section-3.2.2
$value = XML::getFirstNodeValue($xpath, 'atom:author/atom:uri/text()'); $value = XML::getFirstNodeValue($xpath, $atomns . ':author/' . $atomns . ':uri/text()');
if ($value != '') { if ($value != '') {
$author['author-link'] = $value; $author['author-link'] = $value;
} }
$value = XML::getFirstNodeValue($xpath, 'atom:author/poco:preferredUsername/text()'); $value = XML::getFirstNodeValue($xpath, $atomns . ':author/poco:preferredUsername/text()');
if ($value != '') { if ($value != '') {
$author['author-nick'] = $value; $author['author-nick'] = $value;
} }
$value = XML::getFirstNodeValue($xpath, 'atom:author/poco:address/poco:formatted/text()'); $value = XML::getFirstNodeValue($xpath, $atomns . ':author/poco:address/poco:formatted/text()');
if ($value != '') { if ($value != '') {
$author['author-location'] = $value; $author['author-location'] = $value;
} }
$value = XML::getFirstNodeValue($xpath, 'atom:author/poco:note/text()'); $value = XML::getFirstNodeValue($xpath, $atomns . ':author/poco:note/text()');
if ($value != '') { if ($value != '') {
$author['author-about'] = $value; $author['author-about'] = $value;
} }
$avatar = XML::getFirstAttributes($xpath, "atom:author/atom:link[@rel='avatar']"); $avatar = XML::getFirstAttributes($xpath, $atomns . ":author/' . $atomns . ':link[@rel='avatar']");
if (is_object($avatar)) { if (is_object($avatar)) {
foreach ($avatar as $attribute) { foreach ($avatar as $attribute) {
if ($attribute->name == 'href') { if ($attribute->name == 'href') {
@ -198,11 +209,11 @@ class Feed
} }
} }
$author['edited'] = $author['created'] = XML::getFirstNodeValue($xpath, '/atom:feed/atom:updated/text()'); $author['edited'] = $author['created'] = XML::getFirstNodeValue($xpath, '/' . $atomns . ':feed/' . $atomns . ':updated/text()');
$author['app'] = XML::getFirstNodeValue($xpath, '/atom:feed/atom:generator/text()'); $author['app'] = XML::getFirstNodeValue($xpath, '/' . $atomns . ':feed/' . $atomns . ':generator/text()');
$entries = $xpath->query('/atom:feed/atom:entry'); $entries = $xpath->query('/' . $atomns . ':feed/' . $atomns . ':entry');
} }
// Is it RSS? // Is it RSS?
@ -299,9 +310,9 @@ class Feed
$item = array_merge($header, $author); $item = array_merge($header, $author);
$alternate = XML::getFirstAttributes($xpath, "atom:link[@rel='alternate']", $entry); $alternate = XML::getFirstAttributes($xpath, $atomns . ":link[@rel='alternate']", $entry);
if (!is_object($alternate)) { if (!is_object($alternate)) {
$alternate = XML::getFirstAttributes($xpath, 'atom:link', $entry); $alternate = XML::getFirstAttributes($xpath, $atomns . ':link', $entry);
} }
if (is_object($alternate)) { if (is_object($alternate)) {
foreach ($alternate as $attribute) { foreach ($alternate as $attribute) {
@ -311,6 +322,40 @@ class Feed
} }
} }
if ($entry->nodeName == 'outline') {
$isrss = false;
$plink = '';
$uri = '';
foreach ($entry->attributes as $attribute) {
switch ($attribute->nodeName) {
case 'title':
$item['title'] = $attribute->nodeValue;
break;
case 'text':
$body = $attribute->nodeValue;
break;
case 'htmlUrl':
$plink = $attribute->nodeValue;
break;
case 'xmlUrl':
$uri = $attribute->nodeValue;
break;
case 'type':
$isrss = $attribute->nodeValue == 'rss';
break;
}
}
$item['plink'] = $plink ?: $uri;
$item['uri'] = $uri ?: $plink;
if (!$isrss || empty($item['uri'])) {
continue;
}
}
if (empty($item['plink'])) { if (empty($item['plink'])) {
$item['plink'] = XML::getFirstNodeValue($xpath, 'link/text()', $entry); $item['plink'] = XML::getFirstNodeValue($xpath, 'link/text()', $entry);
} }
@ -322,7 +367,9 @@ class Feed
// Add the base path if missing // Add the base path if missing
$item['plink'] = Network::addBasePath($item['plink'], $basepath); $item['plink'] = Network::addBasePath($item['plink'], $basepath);
$item['uri'] = XML::getFirstNodeValue($xpath, 'atom:id/text()', $entry); if (empty($item['uri'])) {
$item['uri'] = XML::getFirstNodeValue($xpath, $atomns . ':id/text()', $entry);
}
$guid = XML::getFirstNodeValue($xpath, 'guid/text()', $entry); $guid = XML::getFirstNodeValue($xpath, 'guid/text()', $entry);
if (!empty($guid)) { if (!empty($guid)) {
@ -344,7 +391,9 @@ class Feed
Logger::notice('Item URL couldn\'t get expanded', ['url' => $item['plink'], 'exception' => $exception]); Logger::notice('Item URL couldn\'t get expanded', ['url' => $item['plink'], 'exception' => $exception]);
} }
$item['title'] = XML::getFirstNodeValue($xpath, 'atom:title/text()', $entry); if (empty($item['title'])) {
$item['title'] = XML::getFirstNodeValue($xpath, $atomns . ':title/text()', $entry);
}
if (empty($item['title'])) { if (empty($item['title'])) {
$item['title'] = XML::getFirstNodeValue($xpath, 'title/text()', $entry); $item['title'] = XML::getFirstNodeValue($xpath, 'title/text()', $entry);
@ -360,7 +409,7 @@ class Feed
$item['title'] = html_entity_decode($item['title'], ENT_QUOTES, 'UTF-8'); $item['title'] = html_entity_decode($item['title'], ENT_QUOTES, 'UTF-8');
$published = XML::getFirstNodeValue($xpath, 'atom:published/text()', $entry); $published = XML::getFirstNodeValue($xpath, $atomns . ':published/text()', $entry);
if (empty($published)) { if (empty($published)) {
$published = XML::getFirstNodeValue($xpath, 'pubDate/text()', $entry); $published = XML::getFirstNodeValue($xpath, 'pubDate/text()', $entry);
@ -370,7 +419,7 @@ class Feed
$published = XML::getFirstNodeValue($xpath, 'dc:date/text()', $entry); $published = XML::getFirstNodeValue($xpath, 'dc:date/text()', $entry);
} }
$updated = XML::getFirstNodeValue($xpath, 'atom:updated/text()', $entry); $updated = XML::getFirstNodeValue($xpath, $atomns . ':updated/text()', $entry);
if (empty($updated) && !empty($published)) { if (empty($updated) && !empty($published)) {
$updated = $published; $updated = $published;
@ -406,7 +455,7 @@ class Feed
$creator = XML::getFirstNodeValue($xpath, 'author/text()', $entry); $creator = XML::getFirstNodeValue($xpath, 'author/text()', $entry);
if (empty($creator)) { if (empty($creator)) {
$creator = XML::getFirstNodeValue($xpath, 'atom:author/atom:name/text()', $entry); $creator = XML::getFirstNodeValue($xpath, $atomns . ':author/' . $atomns . ':name/text()', $entry);
} }
if (empty($creator)) { if (empty($creator)) {
@ -429,33 +478,35 @@ class Feed
$attachments = []; $attachments = [];
$enclosures = $xpath->query("enclosure|atom:link[@rel='enclosure']", $entry); $enclosures = $xpath->query("enclosure|' . $atomns . ':link[@rel='enclosure']", $entry);
foreach ($enclosures as $enclosure) { if (!empty($enclosures)) {
$href = ''; foreach ($enclosures as $enclosure) {
$length = null; $href = '';
$type = null; $length = null;
$type = null;
foreach ($enclosure->attributes as $attribute) { foreach ($enclosure->attributes as $attribute) {
if (in_array($attribute->name, ['url', 'href'])) { if (in_array($attribute->name, ['url', 'href'])) {
$href = $attribute->textContent; $href = $attribute->textContent;
} elseif ($attribute->name == 'length') { } elseif ($attribute->name == 'length') {
$length = (int)$attribute->textContent; $length = (int)$attribute->textContent;
} elseif ($attribute->name == 'type') { } elseif ($attribute->name == 'type') {
$type = $attribute->textContent; $type = $attribute->textContent;
}
} }
}
if (!empty($href)) { if (!empty($href)) {
$attachment = ['uri-id' => -1, 'type' => Post\Media::UNKNOWN, 'url' => $href, 'mimetype' => $type, 'size' => $length]; $attachment = ['uri-id' => -1, 'type' => Post\Media::UNKNOWN, 'url' => $href, 'mimetype' => $type, 'size' => $length];
$attachment = Post\Media::fetchAdditionalData($attachment); $attachment = Post\Media::fetchAdditionalData($attachment);
// By now we separate the visible media types (audio, video, image) from the rest // By now we separate the visible media types (audio, video, image) from the rest
// In the future we should try to avoid the DOCUMENT type and only use the real one - but not in the RC phase. // In the future we should try to avoid the DOCUMENT type and only use the real one - but not in the RC phase.
if (!in_array($attachment['type'], [Post\Media::AUDIO, Post\Media::IMAGE, Post\Media::VIDEO])) { if (!in_array($attachment['type'], [Post\Media::AUDIO, Post\Media::IMAGE, Post\Media::VIDEO])) {
$attachment['type'] = Post\Media::DOCUMENT; $attachment['type'] = Post\Media::DOCUMENT;
} }
$attachments[] = $attachment; $attachments[] = $attachment;
}
} }
} }
@ -465,13 +516,15 @@ class Feed
$taglist[] = $category->nodeValue; $taglist[] = $category->nodeValue;
} }
$body = trim(XML::getFirstNodeValue($xpath, 'atom:content/text()', $entry)); if (empty($body)) {
$body = trim(XML::getFirstNodeValue($xpath, $atomns . ':content/text()', $entry));
}
if (empty($body)) { if (empty($body)) {
$body = trim(XML::getFirstNodeValue($xpath, 'content:encoded/text()', $entry)); $body = trim(XML::getFirstNodeValue($xpath, 'content:encoded/text()', $entry));
} }
$summary = trim(XML::getFirstNodeValue($xpath, 'atom:summary/text()', $entry)); $summary = trim(XML::getFirstNodeValue($xpath, $atomns . ':summary/text()', $entry));
if (empty($summary)) { if (empty($summary)) {
$summary = trim(XML::getFirstNodeValue($xpath, 'description/text()', $entry)); $summary = trim(XML::getFirstNodeValue($xpath, 'description/text()', $entry));