rewrite: leave out charset in top-frame and don't modify it in replay frame

to allow browser to detect best charset, as it would on original page if it is absent)
see #170 for details

pywb/rewrite/rewrite_content.py

@@ -237,8 +237,9 @@ class RewriteContent:
         m = RewriteContent.CHARSET_REGEX.search(buff)
         if m:
             charset = m.group(1)
-            content_type = 'text/html; charset=' + charset
-            status_headers.replace_header('content-type', content_type)
+        #    content_type = 'text/html; charset=' + charset
+        #    status_headers.replace_header('content-type', content_type)
+
         return charset
 
     @staticmethod

pywb/rewrite/test/test_rewrite_live.py

@@ -207,7 +207,7 @@ def test_example_1():
 
 
     # verify utf-8 charset detection
-    assert status_headers.get_header('content-type') == 'text/html; charset=utf-8'
+    assert status_headers.get_header('content-type') == 'text/html'
 
     assert '/pywb/20131226101010/http://www.iana.org/domains/example' in buff, buff
 

pywb/webapp/handlers.py

@@ -107,7 +107,7 @@ class SearchPageWbUrlHandler(WbUrlHandler):
     def get_top_frame_response(self, wbrequest):
         params = self.get_top_frame_params(wbrequest, mod=self.replay_mod)
 
-        headers = [('Content-Type', 'text/html; charset=utf-8')]
+        headers = [('Content-Type', 'text/html')]
         status_headers = StatusAndHeaders('200 OK', headers)
 
         template_result = self.frame_insert_view.render_to_string(**params)