Don't create a sync node when updating an URL that wasn't typed.

chrome/browser/sync/glue/typed_url_change_processor.cc

 // Copyright (c) 2012 The Chromium Authors. All rights reserved.
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file.
 
 #include "chrome/browser/sync/glue/typed_url_change_processor.h"
 
 #include "base/location.h"
 #include "base/metrics/histogram.h"
 #include "base/strings/string_util.h"
 #include "base/strings/utf_string_conversions.h"
@@ skipping 139 matching lines @@
 bool TypedUrlChangeProcessor::CreateOrUpdateSyncNode(
     history::URLRow url, syncer::WriteTransaction* trans) {
   DCHECK_GE(url.typed_count(), 0);
   // Get the visits for this node.
   history::VisitVector visit_vector;
   if (!model_associator_->FixupURLAndGetVisits(&url, &visit_vector)) {
     DLOG(ERROR) << "Could not load visits for url: " << url.url();
     return false;
   }
 
+  if (std::find_if(visit_vector.begin(), visit_vector.end(),

[maniscalco, 2015/05/08 19:38:00]

Question about performance.  How big does visit_vector get and how often is
CreateOrUpdateSycnNode called?  If the vector is on the order of tens of items,
then I'm not worried.  Just want to make sure this isn't going to be super
expensive.

[mpawlowski, 2015/05/11 09:27:18]

Good point, I've checked with an old profile with loads of history and it seems
this can get big. I've just seen a 400+ sized vector for facebook.com.

I'm not sure what's the best way to approach this now. The only way to know if
an URL should be synced is by establishing whether it's been typed. There are
two tables in the history database that govern this: 'urls' and 'visits'. Each
entry in 'urls' has a 'typed_count' (which is used widely through typed history
sync code) but it's currently a broken heuristic - if I type "facebook.com" and
it gets redirected to "https://www.facebook.com", the second address has
'typed_count' = 0 even though the corresponding visit in the 'visits' table has
type PAGE_TRANSITION_TYPED. This is why I decided to inspect the visits database
instead of urls.

Maybe I should investigate fixing 'typed_count' in the 'urls' table so that it
is incremented for URLs that are results of server-side redirections to things
typed into the address bar. Or come up with a fast method of checking the
'visits' table within HistoryBackend that doesn't require iterating through that
much data (don't know if it's possible).

+                   [](const history::VisitRow& visit) {
+                     return ui::PageTransitionCoreTypeIs(
+                         visit.transition, ui::PAGE_TRANSITION_TYPED);
+                   }) == visit_vector.end())
+    // This URL has no TYPED visits, don't sync it.
+    return false;
+
   syncer::ReadNode typed_url_root(trans);
   if (typed_url_root.InitTypeRoot(syncer::TYPED_URLS) !=
           syncer::BaseNode::INIT_OK) {
     syncer::SyncError error(FROM_HERE,
                             syncer::SyncError::DATATYPE_ERROR,
                             "No top level folder",
                             syncer::TYPED_URLS);
     error_handler()->OnSingleDataTypeUnrecoverableError(error);
     return false;
   }
@@ skipping 169 matching lines @@
 }
 
 void TypedUrlChangeProcessor::StopObserving() {
   DCHECK(backend_loop_ == base::MessageLoop::current());
   DCHECK(history_backend_);
   DCHECK(profile_);
   history_backend_observer_.RemoveAll();
 }
 
 }  // namespace browser_sync