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.

3 files changed, 3 insertions, 3 deletions

diff --git a/scripts/importtwitteratom.php b/scripts/importtwitteratom.php
index 261dfb1d0..a29526f27 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 61fbe18ef..dadbcf66f 100755
--- a/scripts/install_cli.php
+++ b/scripts/install_cli.php
@@ -208,7 +208,7 @@ END_HELP;
         $breakout = preg_replace('/<a[^>+]\bhref="(.*)"[^>]*>(.*)<\/a>/',
                                  '\2 &lt;\1&gt;',
                                  $html);
-        return html_entity_decode(strip_tags($breakout));
+        return html_entity_decode(strip_tags($breakout), ENT_QUOTES, 'UTF-8');
     }
 }
 
diff --git a/scripts/restoreuser.php b/scripts/restoreuser.php
index de3816dd5..82eb9bbaa 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);