Collect separate V8 histograms for Top10 non-Google sites

content/renderer/render_thread_impl.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 "content/renderer/render_thread_impl.h"
 
 #include <algorithm>
 #include <limits>
 #include <map>
 #include <vector>
 
 #include "base/allocator/allocator_extension.h"
 #include "base/command_line.h"
 #include "base/lazy_instance.h"
 #include "base/location.h"
 #include "base/logging.h"
 #include "base/memory/discardable_memory_allocator.h"
 #include "base/memory/shared_memory.h"
 #include "base/metrics/field_trial.h"
 #include "base/metrics/histogram.h"
 #include "base/path_service.h"
 #include "base/single_thread_task_runner.h"
 #include "base/strings/string16.h"
 #include "base/strings/string_number_conversions.h"
+#include "base/strings/string_split.h"
 #include "base/strings/string_tokenizer.h"
 #include "base/strings/sys_string_conversions.h"
 #include "base/strings/utf_string_conversions.h"
 #include "base/thread_task_runner_handle.h"
 #include "base/threading/simple_thread.h"
 #include "base/threading/thread_local.h"
 #include "base/threading/thread_restrictions.h"
 #include "base/trace_event/memory_dump_manager.h"
 #include "base/trace_event/trace_event.h"
 #include "base/values.h"
@@ skipping 89 matching lines @@
 #include "gpu/command_buffer/common/gles2_cmd_utils.h"
 #include "ipc/ipc_channel_handle.h"
 #include "ipc/ipc_platform_file.h"
 #include "ipc/mojo/ipc_channel_mojo.h"
 #include "media/base/audio_hardware_config.h"
 #include "media/base/media.h"
 #include "media/renderers/gpu_video_accelerator_factories.h"
 #include "mojo/common/common_type_converters.h"
 #include "net/base/net_errors.h"
 #include "net/base/port_util.h"
+#include "net/base/registry_controlled_domains/registry_controlled_domain.h"
 #include "skia/ext/event_tracer_impl.h"
 #include "skia/ext/skia_memory_dump_provider.h"
 #include "third_party/WebKit/public/platform/WebImageGenerator.h"
 #include "third_party/WebKit/public/platform/WebString.h"
 #include "third_party/WebKit/public/platform/WebThread.h"
 #include "third_party/WebKit/public/web/WebCache.h"
 #include "third_party/WebKit/public/web/WebColorName.h"
 #include "third_party/WebKit/public/web/WebDatabase.h"
 #include "third_party/WebKit/public/web/WebDocument.h"
 #include "third_party/WebKit/public/web/WebFrame.h"
@@ skipping 137 matching lines @@
   if (host == "mail.google.com")
     return ".gmail";
   if (host == "docs.google.com" || host == "drive.google.com")
     return ".docs";
   if (host == "plus.google.com")
     return ".plus";
   if (host == "inbox.google.com")
     return ".inbox";
   if (host == "www.youtube.com")
     return ".youtube";
+
+  // The Top10 sites have different TLD and/or subdomains
+  // depending on the localization
+   if (host == "sina.com.cn")
+    return ".top10";
+
+   std::string domain =
+        net::registry_controlled_domains::GetDomainAndRegistry(
+            host,
+            net::registry_controlled_domains::INCLUDE_PRIVATE_REGISTRIES);
+
+  if (!domain.empty()) {
+     std::vector<base::StringPiece> host_tokens = base::SplitStringPiece(
+       domain, ".", base::TRIM_WHITESPACE, base::SPLIT_WANT_NONEMPTY);
+
+    if (host_tokens.size() >= 2) {

[jochen (gone - plz use gerrit), 2015/10/23 12:16:21]

why >= 2?

what's wrong with e.g. amazon.com?

given that none of those sites owns all TLDs, I still think it would be better
to hardcode the set of URLs that are actually in the top10

[battre, 2015/10/23 17:49:59]

Do you expect that the traffic to sites not owned by the brands would be
noticeable?

[Michael Hablich, 2015/10/26 13:10:39]

on '.size() >= 2':
Well, it will trigger for 'amazon.com' or 'amazon.co.uk'. Length != index or
something has changed in the definition of size(). 

On the filtering of TLDs:
-Redid it a little bit. Now the TLD is only ignored if this scheme applies to
the particular site.

+      if ((host_tokens[0] == "facebook") ||
+          (host_tokens[0] == "baidu") ||
+          (host_tokens[0] == "yahoo") ||
+          (host_tokens[0] == "amazon") ||
+          (host_tokens[0] == "qq") ||
+          (host_tokens[0] == "twitter") ||
+          (host_tokens[0] == "taobao") ||
+          (host_tokens[0] == "live") ||
+          (host_tokens[0] == "wikipedia")) {
+        return ".top10";

[Alexei Svitkine (slow), 2015/10/22 16:43:06]

Can you make a helper function IsAlexaTop10Site() and have the logic in this
function just do:

if (IsAlexaTop10Site(host))
  return ".top10";

[Michael Hablich, 2015/10/26 13:10:39]

Done.

+      }
+    }
+  }
+
   return std::string();
 }
 
 void* CreateHistogram(
     const char *name, int min, int max, size_t buckets) {
   if (min <= 0)
     min = 1;
   std::string histogram_name;
   RenderThreadImpl* render_thread_impl = RenderThreadImpl::current();
   if (render_thread_impl) {  // Can be null in tests.
@@ skipping 1664 matching lines @@
 }
 
 void RenderThreadImpl::PendingRenderFrameConnect::OnConnectionError() {
   size_t erased =
       RenderThreadImpl::current()->pending_render_frame_connects_.erase(
           routing_id_);
   DCHECK_EQ(1u, erased);
 }
 
 }  // namespace content