X-Git-Url: https://git.mxchange.org/?a=blobdiff_plain;f=src%2FUtil%2FParseUrl.php;h=9a3de88cf2ac789d5866edf28d41e35bdf6c412e;hb=c9a6063a2a6bcf1af3c063c9ccf789a27b548e1f;hp=1188214200cdc7d7971f65737886b0591008530e;hpb=53e9203d37ee0c1a2afed0faf295e3c622ac2e17;p=friendica.git
diff --git a/src/Util/ParseUrl.php b/src/Util/ParseUrl.php
index 1188214200..9a3de88cf2 100644
--- a/src/Util/ParseUrl.php
+++ b/src/Util/ParseUrl.php
@@ -8,13 +8,10 @@ namespace Friendica\Util;
use DOMDocument;
use DOMXPath;
use Friendica\Content\OEmbed;
-use Friendica\Core\Addon;
+use Friendica\Core\Hook;
use Friendica\Core\Logger;
use Friendica\Database\DBA;
use Friendica\Object\Image;
-use Friendica\Util\Strings;
-
-require_once 'include/dba.php';
/**
* @brief Class with methods for extracting certain content from an url
@@ -25,10 +22,10 @@ class ParseUrl
* @brief Search for chached embeddable data of an url otherwise fetch it
*
* @param string $url The url of the page which should be scraped
- * @param bool $no_guessing If true the parse doens't search for
- * preview pictures
- * @param bool $do_oembed The false option is used by the function fetch_oembed()
- * to avoid endless loops
+ * @param bool $no_guessing If true the parse doens't search for
+ * preview pictures
+ * @param bool $do_oembed The false option is used by the function fetch_oembed()
+ * to avoid endless loops
*
* @return array which contains needed data for embedding
* string 'url' => The url of the parsed page
@@ -40,7 +37,8 @@ class ParseUrl
* array'images' = Array of preview pictures
* string 'keywords' => The tags which belong to the content
*
- * @see ParseUrl::getSiteinfo() for more information about scraping
+ * @throws \Friendica\Network\HTTPException\InternalServerErrorException
+ * @see ParseUrl::getSiteinfo() for more information about scraping
* embeddable content
*/
public static function getSiteinfoCached($url, $no_guessing = false, $do_oembed = true)
@@ -71,6 +69,7 @@ class ParseUrl
return $data;
}
+
/**
* @brief Parse a page for embeddable content information
*
@@ -82,11 +81,11 @@ class ParseUrl
* \
*
* @param string $url The url of the page which should be scraped
- * @param bool $no_guessing If true the parse doens't search for
- * preview pictures
- * @param bool $do_oembed The false option is used by the function fetch_oembed()
- * to avoid endless loops
- * @param int $count Internal counter to avoid endless loops
+ * @param bool $no_guessing If true the parse doens't search for
+ * preview pictures
+ * @param bool $do_oembed The false option is used by the function fetch_oembed()
+ * to avoid endless loops
+ * @param int $count Internal counter to avoid endless loops
*
* @return array which contains needed data for embedding
* string 'url' => The url of the parsed page
@@ -98,7 +97,8 @@ class ParseUrl
* array'images' = Array of preview pictures
* string 'keywords' => The tags which belong to the content
*
- * @todo https://developers.google.com/+/plugins/snippet/
+ * @throws \Friendica\Network\HTTPException\InternalServerErrorException
+ * @todo https://developers.google.com/+/plugins/snippet/
* @verbatim
*
*
@@ -113,8 +113,6 @@ class ParseUrl
*/
public static function getSiteinfo($url, $no_guessing = false, $do_oembed = true, $count = 1)
{
- $a = get_app();
-
$siteinfo = [];
// Check if the URL does contain a scheme
@@ -184,11 +182,10 @@ class ParseUrl
$charset = trim(trim(trim(array_pop($matches)), ';,'));
}
- if ($charset == '') {
- $charset = 'utf-8';
- }
+ if ($charset && strtoupper($charset) != 'UTF-8') {
+ // See https://github.com/friendica/friendica/issues/5470#issuecomment-418351211
+ $charset = str_ireplace('latin-1', 'latin1', $charset);
- if (($charset != '') && (strtoupper($charset) != 'UTF-8')) {
Logger::log('detected charset ' . $charset, Logger::DEBUG);
$body = iconv($charset, 'UTF-8//TRANSLIT', $body);
}
@@ -425,7 +422,7 @@ class ParseUrl
Logger::log('Siteinfo for ' . $url . ' ' . print_r($siteinfo, true), Logger::DEBUG);
- Addon::callHooks('getsiteinfo', $siteinfo);
+ Hook::callAll('getsiteinfo', $siteinfo);
return $siteinfo;
}