Detect input encodings from EXIF/IPTC data and convert to utf-8 as

appropriate.  This allows us to switch the exif value column back to
varchar and improves the way that we deal with non-utf8 data in our
embedded EXIF/IPTC data.

1 files changed, 4 insertions, 1 deletions

diff --git a/modules/tag/helpers/tag_event.php b/modules/tag/helpers/tag_event.php
index a301c441..a4a6ec26 100644
--- a/modules/tag/helpers/tag_event.php
+++ b/modules/tag/helpers/tag_event.php
@@ -34,7 +34,10 @@ class tag_event_Core {
         if (!empty($iptc["2#025"])) {
           foreach($iptc["2#025"] as $tag) {
             $tag = str_replace("\0",  "", $tag);
-            $tags[$tag]= 1;
+            if (mb_detect_encoding($tag) != "UTF-8") {
+              $tag = utf8_encode($tag);
+            }
+            $tags[$tag] = 1;
           }
         }
       }