}
/**
- * Parse the Json-Ld parts
+ * Convert tags from CSV to an array
+ *
+ * @param string $string Tags
+ * @return array with formatted Hashtags
+ */
+ public static function convertTagsToArray($string)
+ {
+ $arr_tags = str_getcsv($string);
+ if (count($arr_tags)) {
+ // add the # sign to every tag
+ array_walk($arr_tags, ["self", "arrAddHashes"]);
+
+ return $arr_tags;
+ }
+ }
+
+ /**
+ * Add a hasht sign to a string
+ *
+ * This method is used as callback function
+ *
+ * @param string $tag The pure tag name
+ * @param int $k Counter for internal use
+ * @return void
+ */
+ private static function arrAddHashes(&$tag, $k)
+ {
+ $tag = "#" . $tag;
+ }
+
+ /**
+ * Add a scheme to an url
*
- * @param array $siteinfo
- * @param array $jsonld
+ * The src attribute of some html elements (e.g. images)
+ * can miss the scheme so we need to add the correct
+ * scheme
+ *
+ * @param string $url The url which possibly does have
+ * a missing scheme (a link to an image)
+ * @param string $scheme The url with a correct scheme
+ * (e.g. the url from the webpage which does contain the image)
+ *
+ * @return string The url with a scheme
+ */
+ private static function completeUrl($url, $scheme)
+ {
+ $urlarr = parse_url($url);
+
+ // If the url does allready have an scheme
+ // we can stop the process here
+ if (isset($urlarr["scheme"])) {
+ return($url);
+ }
+
+ $schemearr = parse_url($scheme);
+
+ $complete = $schemearr["scheme"]."://".$schemearr["host"];
+
+ if (!empty($schemearr["port"])) {
+ $complete .= ":".$schemearr["port"];
+ }
+
+ if (!empty($urlarr["path"])) {
+ if (strpos($urlarr["path"], "/") !== 0) {
+ $complete .= "/";
+ }
+
+ $complete .= $urlarr["path"];
+ }
+
+ if (!empty($urlarr["query"])) {
+ $complete .= "?".$urlarr["query"];
+ }
+
+ if (!empty($urlarr["fragment"])) {
+ $complete .= "#".$urlarr["fragment"];
+ }
+
+ return($complete);
+ }
+
+ /**
+ * Parse the Json-Ld parts of a web page
+ *
+ * @param array $siteinfo
+ * @param array $jsonld
* @return array siteinfo
*/
private static function parseParts(array $siteinfo, array $jsonld)
/**
* Improve the siteinfo with information from the provided JSON-LD information
* @see https://jsonld.com/
+ * @see https://schema.org/
*
* @param array $siteinfo
* @param array $jsonld
}
// Silently ignore some types that aren't processed
- if (in_array($type, ['SiteNavigationElement', 'JobPosting', 'CreativeWork',
+ if (in_array($type, ['SiteNavigationElement', 'JobPosting', 'CreativeWork', 'MusicAlbum',
'WPHeader', 'WPSideBar', 'WPFooter', 'LegalService',
'ItemList', 'BreadcrumbList', 'Blog', 'Dataset', 'Product'])) {
return $siteinfo;
return self::parseJsonLdWebOrganization($siteinfo, $jsonld);
case 'Person':
case 'Patient':
- case 'PerformingGroup':
+ case 'PerformingGroup':
case 'DanceGroup';
case 'MusicGroup':
case 'TheaterGroup':
}
/**
- * Improve the siteinfo with information from the provided JSON-LD information concerning authors and publishers
+ * Fetch author and publisher data
*
* @param array $siteinfo
* @param array $jsonld
$jsonldinfo['author_name'] = trim($jsonld['author']);
}
- Logger::info('Fetched author information', ['fetched' => $jsonldinfo]);
+ Logger::info('Fetched Author information', ['fetched' => $jsonldinfo]);
return array_merge($siteinfo, $jsonldinfo);
}
/**
- * Improve the siteinfo with information from the provided JSON-LD Article information
+ * Fetch data from the provided JSON-LD Article type
* @see https://schema.org/Article
*
* @param array $siteinfo
}
/**
- * Improve the siteinfo with information from the provided JSON-LD WebPage information
+ * Fetch data from the provided JSON-LD WebPage type
* @see https://schema.org/WebPage
*
* @param array $siteinfo
$jsonldinfo = self::parseJsonLdAuthor($jsonldinfo, $jsonld);
- Logger::info('Fetched webpage information', ['url' => $siteinfo['url'], 'fetched' => $jsonldinfo]);
+ Logger::info('Fetched WebPage information', ['url' => $siteinfo['url'], 'fetched' => $jsonldinfo]);
return array_merge($siteinfo, $jsonldinfo);
}
/**
- * Improve the siteinfo with information from the provided JSON-LD WebSite information
+ * Fetch data from the provided JSON-LD WebSite type
* @see https://schema.org/WebSite
*
* @param array $siteinfo
}
/**
- * Improve the siteinfo with information from the provided JSON-LD Organization information
+ * Fetch data from the provided JSON-LD Organization type
* @see https://schema.org/Organization
*
* @param array $siteinfo
}
/**
- * Improve the siteinfo with information from the provided JSON-LD Person information
+ * Fetch data from the provided JSON-LD Person type
* @see https://schema.org/Person
*
* @param array $siteinfo
}
/**
- * Improve the siteinfo with information from the provided JSON-LD MediaObject
+ * Fetch data from the provided JSON-LD MediaObject type
* @see https://schema.org/MediaObject
*
* @param array $siteinfo
$siteinfo[$name][] = $media;
return $siteinfo;
}
-
- /**
- * Convert tags from CSV to an array
- *
- * @param string $string Tags
- * @return array with formatted Hashtags
- */
- public static function convertTagsToArray($string)
- {
- $arr_tags = str_getcsv($string);
- if (count($arr_tags)) {
- // add the # sign to every tag
- array_walk($arr_tags, ["self", "arrAddHashes"]);
-
- return $arr_tags;
- }
- }
-
- /**
- * Add a hasht sign to a string
- *
- * This method is used as callback function
- *
- * @param string $tag The pure tag name
- * @param int $k Counter for internal use
- * @return void
- */
- private static function arrAddHashes(&$tag, $k)
- {
- $tag = "#" . $tag;
- }
-
- /**
- * Add a scheme to an url
- *
- * The src attribute of some html elements (e.g. images)
- * can miss the scheme so we need to add the correct
- * scheme
- *
- * @param string $url The url which possibly does have
- * a missing scheme (a link to an image)
- * @param string $scheme The url with a correct scheme
- * (e.g. the url from the webpage which does contain the image)
- *
- * @return string The url with a scheme
- */
- private static function completeUrl($url, $scheme)
- {
- $urlarr = parse_url($url);
-
- // If the url does allready have an scheme
- // we can stop the process here
- if (isset($urlarr["scheme"])) {
- return($url);
- }
-
- $schemearr = parse_url($scheme);
-
- $complete = $schemearr["scheme"]."://".$schemearr["host"];
-
- if (!empty($schemearr["port"])) {
- $complete .= ":".$schemearr["port"];
- }
-
- if (!empty($urlarr["path"])) {
- if (strpos($urlarr["path"], "/") !== 0) {
- $complete .= "/";
- }
-
- $complete .= $urlarr["path"];
- }
-
- if (!empty($urlarr["query"])) {
- $complete .= "?".$urlarr["query"];
- }
-
- if (!empty($urlarr["fragment"])) {
- $complete .= "#".$urlarr["fragment"];
- }
-
- return($complete);
- }
}
projects / friendica.git / commitdiff