From: Brion Vibber Date: Thu, 30 Sep 2010 18:29:31 +0000 (-0700) Subject: Always specify UTF-8 targt charset for html_entity_decode(); default is 8-bit ISO... X-Git-Url: https://git.mxchange.org/?a=commitdiff_plain;h=1acc7d66c63e0b9f794791e3a2e2b0f60bc2ebb1;p=quix0rs-gnu-social.git Always specify UTF-8 targt charset for html_entity_decode(); default is 8-bit ISO-8859-1 which causes things to break when we later pass them through things that expect to work with UTF-8. For instance, running through preg_replace() with the /u option results in NULL, leading to problems with OStatus and SubMirror generating their plaintext versions and doing length-cropping. --- diff --git a/lib/activityobject.php b/lib/activityobject.php index 95615d581c..c957933d04 100644 --- a/lib/activityobject.php +++ b/lib/activityobject.php @@ -203,7 +203,7 @@ class ActivityObject $title = ActivityUtils::childHtmlContent($element, self::TITLE); - $this->title = html_entity_decode(strip_tags($title)); + $this->title = html_entity_decode(strip_tags($title), ENT_QUOTES, 'UTF-8'); $this->source = $this->_getSource($element); diff --git a/plugins/OStatus/classes/Ostatus_profile.php b/plugins/OStatus/classes/Ostatus_profile.php index 047435f668..10cee917e1 100644 --- a/plugins/OStatus/classes/Ostatus_profile.php +++ b/plugins/OStatus/classes/Ostatus_profile.php @@ -558,7 +558,7 @@ class Ostatus_profile extends Memcached_DataObject // Get (safe!) HTML and text versions of the content $rendered = $this->purify($sourceContent); - $content = html_entity_decode(strip_tags($rendered)); + $content = html_entity_decode(strip_tags($rendered), ENT_QUOTES, 'UTF-8'); $shortened = common_shorten_links($content); @@ -569,7 +569,7 @@ class Ostatus_profile extends Memcached_DataObject if (Notice::contentTooLong($shortened)) { $attachment = $this->saveHTMLFile($note->title, $rendered); - $summary = html_entity_decode(strip_tags($note->summary)); + $summary = html_entity_decode(strip_tags($note->summary), ENT_QUOTES, 'UTF-8'); if (empty($summary)) { $summary = $content; } diff --git a/plugins/TwitterBridge/daemons/twitterstatusfetcher.php b/plugins/TwitterBridge/daemons/twitterstatusfetcher.php index 590fa2954d..cef67b1806 100755 --- a/plugins/TwitterBridge/daemons/twitterstatusfetcher.php +++ b/plugins/TwitterBridge/daemons/twitterstatusfetcher.php @@ -321,7 +321,7 @@ class TwitterStatusFetcher extends ParallelizingDaemon $notice->is_local = Notice::GATEWAY; - $notice->content = html_entity_decode($status->text); + $notice->content = html_entity_decode($status->text, ENT_QUOTES, 'UTF-8'); $notice->rendered = $this->linkify($status); if (Event::handle('StartNoticeSave', array(&$notice))) { diff --git a/scripts/importtwitteratom.php b/scripts/importtwitteratom.php index 261dfb1d02..a29526f27e 100644 --- a/scripts/importtwitteratom.php +++ b/scripts/importtwitteratom.php @@ -89,7 +89,7 @@ function importActivityStream($user, $doc) $html = htmLawed($html, $config); - $content = html_entity_decode(strip_tags($html)); + $content = html_entity_decode(strip_tags($html), ENT_QUOTES, 'UTF-8'); $notice = Notice::saveNew($user->id, $content, diff --git a/scripts/install_cli.php b/scripts/install_cli.php index 61fbe18ef6..dadbcf66f0 100755 --- a/scripts/install_cli.php +++ b/scripts/install_cli.php @@ -208,7 +208,7 @@ END_HELP; $breakout = preg_replace('/+]\bhref="(.*)"[^>]*>(.*)<\/a>/', '\2 <\1>', $html); - return html_entity_decode(strip_tags($breakout)); + return html_entity_decode(strip_tags($breakout), ENT_QUOTES, 'UTF-8'); } } diff --git a/scripts/restoreuser.php b/scripts/restoreuser.php index de3816dd53..82eb9bbaa1 100644 --- a/scripts/restoreuser.php +++ b/scripts/restoreuser.php @@ -213,7 +213,7 @@ function postNote($user, $activity) // Get (safe!) HTML and text versions of the content $rendered = purify($sourceContent); - $content = html_entity_decode(strip_tags($rendered)); + $content = html_entity_decode(strip_tags($rendered), ENT_QUOTES, 'UTF-8'); $shortened = common_shorten_links($content);