Tweaks to handle text types better and make set operation clearer.

levkowetz · levkowetz · commit 2fd344f810df · 2018-03-07T21:10:47.000Z
- Legacy-Id: 14745
diff --git a/ietf/secr/proceedings/utils.py b/ietf/secr/proceedings/utils.py
@@ -4,6 +4,7 @@
 
 from django.conf import settings
 from django.contrib import messages
+from django.utils.encoding import smart_text
 
 import debug                            # pyflakes:ignore
 
@@ -36,8 +37,9 @@ def handle_upload_file(file,filename,meeting,subdir, request=None):
     destination = open(os.path.join(path,filename), 'wb+')
     if extension in settings.MEETING_VALID_MIME_TYPE_EXTENSIONS['text/html']:
         file.open()
-        text = file.read().decode('utf-8')
-        # Whole file sanitization; add back '<html>' (sanitize will remove it)
+        text = smart_text(file.read())
+        # Whole file sanitization; add back what's missing from a complete
+        # document (sanitize will remove these).
         clean = u"""<!DOCTYPE html>
         <html lang="en">
         <head><title>%s</title></head>
diff --git a/ietf/utils/html.py b/ietf/utils/html.py
@@ -26,7 +26,7 @@ def __iter__(self):
         for token in Filter.__iter__(self):
             if token["type"] in ["EmptyTag", "StartTag"]:
                 open_tags.append(token["name"])
-            if not set(strip_completely) & set(open_tags):
+            if not (set(open_tags) & set(strip_completely)):
                 yield token
             if token["type"] in ["EmptyTag", "EndTag"]:
                 open_tags.pop()
